Computer Vision Speech Processing Pattern Recognition Human-Computer Interaction Multimodal Interface Augmented Reality Human-Agent Interaction Human Interface Human Face Recognition Image Processing
Computer Vision Speech Processing Pattern Recognition Human-Computer Interaction Multimodal Interface Augmented Reality Human-Agent Interaction Human Interface Human Face Recognition ...See More
Computer Vision Speech Processing Pattern Recognition Human-Computer Interaction Multimodal Interface Augmented Reality Human-Agent Interaction Human Interface Human Face Recognition Image Processing
Research Areas
Informatics / Entertainment and game informatics
Informatics / Human interfaces and interactions
Informatics / Intelligent informatics
Academic & Professional Experience
2009/04 - Today Toyo UniversityFaculty of Information Sciences and ArtsAssociate Professor
2007/04 - 2009/03 Toyo UniversityFaculty of EngineeringAssociate Professor
2005/04 - 2007/03 Toyo UniversityFaculty of EngineeringAssistant Professor
2002/04 - 2005/03 Toyo UniversityFaculty of EngineeringLecturer
2000/04 - 2002/03 Waseda UniversitySchool of Science and EngineeringResearch Associate
Association Memberships
ACM IEEE THE JAPANESE SOCIETY FOR ARTIFICIAL INTELLIGENCE INFORMATION PROCESSING SOCIETY OF JAPAN THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS
2024 11th International Conference on Soft Computing & Machine Intelligence (ISCMI) IEEE 83 - 87 2024/11 [Refereed]
Automatic generation of training data for semantic segmentation using game engineYuqian Zhang; Murakami Makoto2024 11th International Conference on Soft Computing & Machine Intelligence (ISCMI) IEEE 8...See More
International Journal of Artificial Intelligence & Applications Academy and Industry Research Collaboration Center (AIRCC) 14 (5) 13 - 23 0976-2191 2023/09 [Refereed]
Subverting Characters Stereotypes: Exploring the Role of AI in Stereotype SubversionXiaohan Feng; Makoto MurakamiInternational Journal of Artificial Intelligence & Applications Academy and Industry Re...See More
International Journal of Artificial Intelligence & Applications Academy and Industry Research Collaboration Center (AIRCC) 14 (5) 13 - 23 0976-2191 2023/09 [Refereed]
2023 International Conference on Power, Communication, Computing and Networking Technologies ACM 1 - 5 2023/09 [Refereed]
Promotion of enjoyment by balancing competitive play in racing videogameWataru Yaguchi; Makoto Murakami2023 International Conference on Power, Communication, Computing and Networking Technologies ACM ...See More
International Journal of Artificial Intelligence & Applications Academy and Industry Research Collaboration Center (AIRCC) 14 (2) 51 - 62 0976-2191 2023/03 [Refereed]
Design That Uses AI to Overturn Stereotypes: Make Witches Wicked AgainXiaohan Feng; Makoto MurakamiInternational Journal of Artificial Intelligence & Applications Academy and Industry Research Collabo...See More
International Journal of Artificial Intelligence & Applications Academy and Industry Research Collaboration Center (AIRCC) 14 (2) 51 - 62 0976-2191 2023/03 [Refereed]
Proceedings of the 6th International Conference on Digital Signal Processing ACM 104 - 109 2022/02 [Refereed]
Human Motion Generation Using Variational Recurrent Neural NetworkMakoto Murakami; Takahiro IkezawaProceedings of the 6th International Conference on Digital Signal Processing ACM 104 - 109 2022/02 [R...See More
2021 10th International Congress on Advanced Applied Informatics (IIAI-AAI) IEEE 798 - 803 2021/07 [Refereed]
Design outside the stereotypes: Restoring the dragon from RevelationXiaohan Feng; Makoto Murakami2021 10th International Congress on Advanced Applied Informatics (IIAI-AAI) IEEE 798 - 803 2021/07 [Ref...See More
ICMI 2013 - Proceedings of the 2013 ACM International Conference on Multimodal Interaction 397 - 404 2013 [Refereed]
Investigating appropriate spatial relationship between user and ar character agent for communication using AR WoZ systemReina Aramaki; Makoto MurakamiICMI 2013 - Proceedings of the 2013 ACM Internatio...See More
IMT Information and Media Technologies Editorial Board 7 (3) 1145 - 1150 1881-0896 2012
A Method to Synthesize Three Dimensional Face Models by Mapping from a Word Space to a Physical Model Space and the Inspection of the Mapping FunctionSugimoto Futoshi; Murakami Makoto; Kato ChiekoIMT ...See More
Journal of Information Processing 20 (3) 531 - 536 0387-5806 2012 [Refereed]
A method to synthesize three dimensional face models by mapping from a word space to a physical model space and the inspection of the mapping functionFutoshi Sugimoto; Makoto Murakami; Chieko KatoJour...See More
Biomedical Fuzzy Systems Association Biomedical Fuzzy Systems Association 13 (2) 9 - 18 1345-1537 2011/10 [Refereed]
An Interaction Strategy in Image Searching System Using Interactive Genetic AlgorithmFutoshi Sugimoto; Makoto Murakami; Chieko KatoBiomedical Fuzzy Systems Association Biomedical Fuzzy Systems Associa...See More
International Journal of Space-Based and Situated Computing 1 (2/3) 113 - 121 2011/05 [Refereed]
Sensing, collecting, and discovering the home environment information for ecological lifestyleMotoi Yamagiwa; Makoto Murakami; Minoru UeharaInternational Journal of Space-Based and Situated Computing ...See More
A Proposal of 3 FT Orthogonal RAID and Its Implementation in Virtual Large-scale DiskMinoru Uehara; Makoto Murakami; Motoi YamagiwaIPSJ Journal 一般社団法人情報処理学会 52 (2) 434 - 445 1882-7764 2011/02 [Referee...See More
COMPUTER SYSTEMS SCIENCE AND ENGINEERING 25 (2) 161 - 170 0267-6192 2010/03 [Refereed]
A reconstruction method for ultrasonic deterioration image by the combination of constructive solid geometry and strongly typed genetic programmingMotoi Yamagiwa; Minoru Uehara; Makoto Murakami; Masah...See More
COMPUTER SYSTEMS SCIENCE AND ENGINEERING 25 (2) 103 - 109 0267-6192 2010/03 [Refereed]
Decision model for a system to start communicating with a humanMakoto Murakami; Motoi Yamagiwa; Minoru Uehara; Satoshi Ushiyama; Katsuhiko ShiraiCOMPUTER SYSTEMS SCIENCE AND ENGINEERING 25 (2) 103 - 1...See More
Proceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010 401 - 406 2010 [Refereed]
Construction of decision model for a system to start communicating with a human using hidden Markov modelYoshito Ogawa; Jungo Katsuyama; Takahiro Miyajima; Katsuhiko Shirai; Makoto MurakamiProceedings...See More
Proceedings - 13th International Conference on Network-Based Information Systems, NBiS 2010 457 - 462 2010 [Refereed]
A proposal of indoor life environment monitoring for ecological lifestyleMotoi Yamagiwa; Makoto Murakami; Minoru UeharaProceedings - 13th International Conference on Network-Based Information Systems,...See More
Proceedings - 13th International Conference on Network-Based Information Systems, NBiS 2010 457 - 462 2010 [Refereed]
Reliability Evaluation of Small World Cellular Neural Networks
Katsuyoshi Matsumoto; Minoru Uehara; Motoi Yamagiwa; Makoto Murakami; Hideki Mori
GESTS International Transactions on Computer Science and Engineering 55 (1) 69 - 80 2009/08 [Refereed]
Reliability Evaluation of Small World Cellular Neural NetworksKatsuyoshi Matsumoto; Minoru Uehara; Motoi Yamagiwa; Makoto Murakami; Hideki MoriGESTS International Transactions on Computer Science and ...See More
Reliability Evaluation of Small World Cellular Neural Networks
Katsuyoshi Matsumoto; Minoru Uehara; Motoi Yamagiwa; Makoto Murakami; Hideki Mori
GESTS International Transactions on Computer Science and Engineering 55 (1) 69 - 80 2009/08 [Refereed]
2009 RISP Workshop on Nonlinear Circuits and Signal Processing 581 - 584 2009 [Refereed]
Stereo Vision-based Detection and Tracking of Humans Using Reeb GraphAkimasa Yuki; Makoto Murakami; Katsuhiko Shirai2009 RISP Workshop on Nonlinear Circuits and Signal Processing 581 - 584 2009 [Refer...See More
International Workshop on Advanced Image Technology 4 pages 2009 [Refereed]
Human Motion and Speech Analysis to Construct Decision Model for a Robot to End Communicating with a HumanNaoki Otsuka; Makoto MurakamiInternational Workshop on Advanced Image Technology 4 pages 2009...See More
2009 INTERNATIONAL CONFERENCE ON NETWORK-BASED INFORMATION SYSTEMS 618 - + 2009 [Refereed]
Decision Model for a System to Start Communicating with a Human using HMMMakoto Murakami; Motoi Yamagiwa; Minoru Uehara; Satoshi Ushiyama; Katsuhiko Shirai2009 INTERNATIONAL CONFERENCE ON NETWORK-BASE...See More
2009 INTERNATIONAL CONFERENCE ON NETWORK-BASED INFORMATION SYSTEMS 457 - 462 2009 [Refereed]
Applied system of the Social Life Log for Ecological lifestyle in the homeMotoi Yamagiwa; Minoru Uehara; Makoto Murakami2009 INTERNATIONAL CONFERENCE ON NETWORK-BASED INFORMATION SYSTEMS 457 - 462 200...See More
2009 INTERNATIONAL CONFERENCE ON NETWORK-BASED INFORMATION SYSTEMS 391 - 397 2009 [Refereed]
Web-Disk-Based Efficient Application Delivery Method for GridsKenichi Tanaka; Minoru Uehara; Makoto Murakami; Motoi Yamagiwa2009 INTERNATIONAL CONFERENCE ON NETWORK-BASED INFORMATION SYSTEMS 391 - 397...See More
CISIS: 2009 INTERNATIONAL CONFERENCE ON COMPLEX, INTELLIGENT AND SOFTWARE INTENSIVE SYSTEMS, VOLS 1 AND 2 144 - + 2009 [Refereed]
DECISION MODEL FOR A ROBOT TO START COMMUNICATING WITH A HUMANSatoshi Ushiyama; Kazunori Matsui; Motoi Yamagiwa; Makoto Murakami; Minoru Uehara; Katsuhiko ShiraiCISIS: 2009 INTERNATIONAL CONFERENCE ON...See More
CISIS: 2009 INTERNATIONAL CONFERENCE ON COMPLEX, INTELLIGENT AND SOFTWARE INTENSIVE SYSTEMS, VOLS 1 AND 2 427 - 432 2009 [Refereed]
Office Grid based on Windows PCsKenichi Tanaka; Minoru Uehara; Makoto Murakami; Motoi YamagiwaCISIS: 2009 INTERNATIONAL CONFERENCE ON COMPLEX, INTELLIGENT AND SOFTWARE INTENSIVE SYSTEMS, VOLS 1 AND 2 ...See More
CISIS: 2009 INTERNATIONAL CONFERENCE ON COMPLEX, INTELLIGENT AND SOFTWARE INTENSIVE SYSTEMS, VOLS 1 AND 2 512 - 517 2009 [Refereed]
Online Web Storage using Virtual Large-Scale DisksErianto Chai; Minoru Uehara; Makoto Murakami; Motoi YamagiwaCISIS: 2009 INTERNATIONAL CONFERENCE ON COMPLEX, INTELLIGENT AND SOFTWARE INTENSIVE SYSTEM...See More
Katsuyoshi Matsumoto; Minoru Uehara; Motoi Yamagiwa; Makoto Murakami; Hideki Mori
CISIS: 2009 INTERNATIONAL CONFERENCE ON COMPLEX, INTELLIGENT AND SOFTWARE INTENSIVE SYSTEMS, VOLS 1 AND 2 154 - 161 2009 [Refereed]
Evaluations of a new Visualization Tool for Internet AS Topology with Valley-free Rules
Shingo Nomoto; Kensuke Fukuda; Minoru Uehara; Makoto Murakami; Hideki Mori
GESTS International Transactions on Computer Science and Engineering 51 (1) 59 - 70 2008/12 [Refereed]
Evaluations of a new Visualization Tool for Internet AS Topology with Valley-free RulesShingo Nomoto; Kensuke Fukuda; Minoru Uehara; Makoto Murakami; Hideki MoriGESTS International Transactions on Com...See More
Evaluations of a new Visualization Tool for Internet AS Topology with Valley-free Rules
Shingo Nomoto; Kensuke Fukuda; Minoru Uehara; Makoto Murakami; Hideki Mori
GESTS International Transactions on Computer Science and Engineering 51 (1) 59 - 70 2008/12 [Refereed]
Sensing, Logging and Searching a Social Life Log
Murakami, Makoto; Ymagiwa, Motoi; Uehara, Minoru
ICPR Workshop on Sensing Web 8 pages 2008 [Refereed]
The IASTED International Conference on Internet and Multimedia Systems and Applications 1 - 6 2005 [Refereed]
Construction of the Motion Representation and Control Model for Animated Characters' Walking MotionTakehiro Morino; Daiki Osafune; Takayuki Itano; Makoto Murakami; Katsuhiko ShiraiThe IASTED Internati...See More
Electronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi) 87 (10) 35 - 43 1042-0967 2004/10 [Refereed]
Extraction of human face and transformable region by facial expression based on extended labeled graph matchingMakoto Murakami; Masahide Yoneyama; Katsuhiko ShiraiElectronics and Communications in Jap...See More
Electronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi) 87 (10) 35 - 43 1042-0967 2004/10 [Refereed]
The IEICE Transactions on Information and Systems(Japanese Edition) J85-D2 (11) 1656 - 1663 0915-1923 2002/11 [Refereed]
Extraction of Human Face and Transformable Region by Facial Expression Based on Extended Labeled Graph MatchingMakoto Murakami; Masahide Yoneyama; Katsuhiko ShiraiThe IEICE Transactions on Information...See More
International Journal of Knowledge-Based Intelligent Engineering Systems 6 (4) 178 - 185 2002/10 [Refereed]
Human Face Extraction using Genetic Algorithm with Similarity of Subspace Method as a Fitness ValueMakoto Murakami; Katsuhiko Shirai; Masahide YoneyamaInternational Journal of Knowledge-Based Intellig...See More
Frontiers in Artificial Intelligence and Applications Vol. 87 SOFT COMPUTING SYSTEMS IOS Press pp. 745-754 2002/09 [Refereed]
Accurate Human Face Extraction using Genetic Algorithm and Subspace MethodMakoto Murakami; Masahide Yoneyama; Katsuhiko ShiraiFrontiers in Artificial Intelligence and Applications Vol. 87 SOFT COMPUTI...See More
ISPA 2001: PROCEEDINGS OF THE 2ND INTERNATIONAL SYMPOSIUM ON IMAGE AND SIGNAL PROCESSING AND ANALYSIS pp. 144-148 144 - 148 2001
Human face extraction using Genetic Algorithm with similarity of subspace method as a fitness valueM Murakami; K Shirai; M YoneyamaISPA 2001: PROCEEDINGS OF THE 2ND INTERNATIONAL SYMPOSIUM ON IMAGE AN...See More
SOCO2001 Soft Computing and Intelligent Systems for Industry CD-ROM 6 pages 2001 [Refereed]
Accurate Face Extraction and the Pose Detection using Subspace Method and Genetic AlgorithmMurakami, Makoto; Yoneyama, Masahide; Shirai, KatsuhikoSOCO2001 Soft Computing and Intelligent Systems for In...See More
Accurate Face Extraction and the Pose Detection using Subspace Method and Genetic Algorithm
2000 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, PROCEEDINGS VOLS I-III pp. 411-414 411 - 414 2000 [Refereed]
Accurate extraction of human face area using subspace method and Genetic AlgorithmM Murakami; M Yoneyama; K Shirai2000 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, PROCEEDINGS VOLS I-III pp. ...See More
International Workshop on Systems, Signals and Image Processing 46 - 49 1999/06 [Refereed]
A Study of Feature Extraction for Facial Pose Detection using Parametric Eigenspace MethodMakoto Murakami; Natsuko Ono; Masahide Yoneyama; Katsuhiko ShiraiInternational Workshop on Systems, Signals an...See More
Artificial Intelligence, NLP , Data Science and Cloud Computing Technology 2023/08 Academy & Industry Research Collaboration
The Aim of this paper is to explore different ways of using AI to subvert stereotypes more efficiently and effectively. It will also enumerate the advantages and disadvantages of each approach, helping creators select the most appropriate method for their specific situations. AI opens up new possibilities, enabling anyone to effortlessly generate visually stunning images without the need for artistic skills. However, it also leads to the creation of more stereotypes when using large amounts of data. Consequently, stereotypes are becoming more prevalent and serious than ever before. Our belief is that we can use this situation in reverse, aiming to summarize stereotypes with AI and then subvert them through elemental exchange. In this study, we have attempted to develop a less time-consuming method to challenge character stereotypes while embracing the concept of "exchange." We selected two character archetypes, namely the "tyrant" and the "mad scientist," and summarized their stereotypes by generating AI images or asking ChatGPT questions. Additionally, we conducted a survey of real historical tyrants to gain insights into their behavior and characteristics. This step helped us comprehend the reasons behind stereotyping in artwork depicting tyrants. Based on this understanding, we made choices about which stereotypes to retain. The intention was to empower the audience to better evaluate the identity of the character. Finally, the two remaining character stereotypes were exchanged, and the design was completed. This paper documents the last and most time-consuming method. By examining a large number of sources and examining what stereotypical influences were used, we were able to achieve a greater effect of subverting stereotypes. The other method is much less time-consuming but somewhat more random. Whether one chooses by subjective experience or by the most frequent choices, there is no guarantee of the best outcome. In other words, it is the one that best guarantees that the audience will be able to quickly identify the original character and at the same time move the two characters the furthest away from the original stereotypical image of the original. In conclusion, if the designer has sufficient time, ai portrait + research or chatGPT + research can be chosen. If there is not enough time, the remaining methods can be chosen. The remaining methods take less time and the designer can try them all to get the desired result.
Subverting Two Character Stereotypes at Once: Exploring AI's Role in Subverting StereotypesXiaohan Feng; Makoto MurakamiArtificial Intelligence, NLP , Data Science and Cloud Computing Technology 2023...See More
Artificial Intelligence, NLP , Data Science and Cloud Computing Technology 2023/08 Academy & Industry Research Collaboration
The Aim of this paper is to explore different ways of using AI to subvert stereotypes more efficiently and effectively. It will also enumerate the advantages and disadvantages of each approach, helping creators select the most appropriate method for their specific situations. AI opens up new possibilities, enabling anyone to effortlessly generate visually stunning images without the need for artistic skills. However, it also leads to the creation of more stereotypes when using large amounts of data. Consequently, stereotypes are becoming more prevalent and serious than ever before. Our belief is that we can use this situation in reverse, aiming to summarize stereotypes with AI and then subvert them through elemental exchange. In this study, we have attempted to develop a less time-consuming method to challenge character stereotypes while embracing the concept of "exchange." We selected two character archetypes, namely the "tyrant" and the "mad scientist," and summarized their stereotypes by generating AI images or asking ChatGPT questions. Additionally, we conducted a survey of real historical tyrants to gain insights into their behavior and characteristics. This step helped us comprehend the reasons behind stereotyping in artwork depicting tyrants. Based on this understanding, we made choices about which stereotypes to retain. The intention was to empower the audience to better evaluate the identity of the character. Finally, the two remaining character stereotypes were exchanged, and the design was completed. This paper documents the last and most time-consuming method. By examining a large number of sources and examining what stereotypical influences were used, we were able to achieve a greater effect of subverting stereotypes. The other method is much less time-consuming but somewhat more random. Whether one chooses by subjective experience or by the most frequent choices, there is no guarantee of the best outcome. In other words, it is the one that best guarantees that the audience will be able to quickly identify the original character and at the same time move the two characters the furthest away from the original stereotypical image of the original. In conclusion, if the designer has sufficient time, ai portrait + research or chatGPT + research can be chosen. If there is not enough time, the remaining methods can be chosen. The remaining methods take less time and the designer can try them all to get the desired result.
Natural Language Processing, Information Retrieval and AI 2023/02 Academy and Industry Research Collaboration Center (AIRCC)
The Witch is a typical stereotype-busting character because its description has changed many times in a long history. This paper is an attempt to understand the visual interpretations and character positioning of the Watch by many creators in different eras, AI is being used to help summarize current stereotypes in witch design, and to propose a way to subvert the Witch stereotype in current popular culture. This study aims to understand the visual interpretations of witches and character positioning by many creators in different eras, and to subvert the stereotype of witches in current popular culture. This study provides material for future research on character design stereotypes, and an attempt is proposed to use artificial intelligence to break the stereotypes in design and is being documented as an experiment in how to subvert current stereotypes from various periods in history. The method begins by using AI to compile stereotypical images of contemporary witches. Then, the two major components of the stereotype, "accessories" and "appearance," are analyzed from historical and social perspectives and attributed to the reasons for the formation and transformation of the Witch image. These past stereotypes are designed using the design approach of "extraction" "retention" and "conversion.", and finally the advantages and disadvantages of this approach are summarized from a practical perspective. Research has shown that it is feasible to use AI to summarize the design elements and use them as clues to trace history. This is especially true for characters such as the Witch, who have undergone many historical transitions. The more changes there are, the more elements can be gathered, and the advantage of this method increases. Stereotypes change over time, and even when the current stereotype has become history, this method is still effective for newly created stereotypes.
Design that uses AI to Subvert Stereotypes: Make Witches Wicked AgainXiaohan Feng; Makoto MurakamiNatural Language Processing, Information Retrieval and AI 2023/02 Academy and Industry Research Coll...See More
Natural Language Processing, Information Retrieval and AI 2023/02 Academy and Industry Research Collaboration Center (AIRCC)
The Witch is a typical stereotype-busting character because its description has changed many times in a long history. This paper is an attempt to understand the visual interpretations and character positioning of the Watch by many creators in different eras, AI is being used to help summarize current stereotypes in witch design, and to propose a way to subvert the Witch stereotype in current popular culture. This study aims to understand the visual interpretations of witches and character positioning by many creators in different eras, and to subvert the stereotype of witches in current popular culture. This study provides material for future research on character design stereotypes, and an attempt is proposed to use artificial intelligence to break the stereotypes in design and is being documented as an experiment in how to subvert current stereotypes from various periods in history. The method begins by using AI to compile stereotypical images of contemporary witches. Then, the two major components of the stereotype, "accessories" and "appearance," are analyzed from historical and social perspectives and attributed to the reasons for the formation and transformation of the Witch image. These past stereotypes are designed using the design approach of "extraction" "retention" and "conversion.", and finally the advantages and disadvantages of this approach are summarized from a practical perspective. Research has shown that it is feasible to use AI to summarize the design elements and use them as clues to trace history. This is especially true for characters such as the Witch, who have undergone many historical transitions. The more changes there are, the more elements can be gathered, and the advantage of this method increases. Stereotypes change over time, and even when the current stereotype has become history, this method is still effective for newly created stereotypes.
Development of an AI model to calculate dietary composition that can induce specific blood amino acids-Toward application to the control of physiological states by diet.
Development of an AI model to calculate dietary composition that can induce specific blood amino acids-Toward application to the control of physiological states by diet.山中大介; 西村武謙; 増田正人; 西宏起; 合田祐貴; 沖野...See More
Development of an AI model to calculate dietary composition that can induce specific blood amino acids-Toward application to the control of physiological states by diet.
Generation of Training Data for Scene Labeling using Neural Network [Not invited]
Yuichiro Motegi; Takahiro Suzuki; Yuta Matsuda; Makoto Murakami
13th World Congress on Computational Mechanics 2018/07
Some researchers have proposed neural networks for scene labeling which assigns class label to each pixel of an image. The class accuracy for objects included enough in a training set such as sky or road is high, but the accuracy for objects included less in the training set tends to be low. To improve the average per-class accuracy, we need to increase variations of training images in each class, and reduce the difference in the number of training images/pixels in each class. But it takes time to annotate a lot of images at the pixel level manually to make training set. There are some researches to generate many pixel-level annotated images using computer graphics. We propose the method to generate large training set for scene labeling. In our system users register 3D models and the corresponding class labels. And the users input some constraints of the object positions such as "tables must be on the floor" or "cups must be on tables or desks". And the users input some hyper parameters for training neural network, such as the structure of the network, loss function, etc. The system put some objects in the virtual space based on the constraints, and generates a large set of images labeled at each pixel, to increase the variations of images in each class and to flatten the number of pixels in each class. The neural network is trained using the large set of generated labeled images. And the system repeats training and evaluating while increasing the variations of training images, and output the network parameters which minimize the generalization error measured with the average per-class accuracy. We captured some real images of indoor environment, and labeled each pixel of them using the neural network trained with our system. To evaluate our system we changed some settings of the system and compared the obtained results.
Generation of Training Data for Scene Labeling using Neural Network [Not invited]Yuichiro Motegi; Takahiro Suzuki; Yuta Matsuda; Makoto Murakami13th World Congress on Computational Mechanics 2018/07...See More
Generation of Training Data for Scene Labeling using Neural Network [Not invited]
Yuichiro Motegi; Takahiro Suzuki; Yuta Matsuda; Makoto Murakami
13th World Congress on Computational Mechanics 2018/07
Some researchers have proposed neural networks for scene labeling which assigns class label to each pixel of an image. The class accuracy for objects included enough in a training set such as sky or road is high, but the accuracy for objects included less in the training set tends to be low. To improve the average per-class accuracy, we need to increase variations of training images in each class, and reduce the difference in the number of training images/pixels in each class. But it takes time to annotate a lot of images at the pixel level manually to make training set. There are some researches to generate many pixel-level annotated images using computer graphics. We propose the method to generate large training set for scene labeling. In our system users register 3D models and the corresponding class labels. And the users input some constraints of the object positions such as "tables must be on the floor" or "cups must be on tables or desks". And the users input some hyper parameters for training neural network, such as the structure of the network, loss function, etc. The system put some objects in the virtual space based on the constraints, and generates a large set of images labeled at each pixel, to increase the variations of images in each class and to flatten the number of pixels in each class. The neural network is trained using the large set of generated labeled images. And the system repeats training and evaluating while increasing the variations of training images, and output the network parameters which minimize the generalization error measured with the average per-class accuracy. We captured some real images of indoor environment, and labeled each pixel of them using the neural network trained with our system. To evaluate our system we changed some settings of the system and compared the obtained results.
Object Shape Feature Extraction from Motion Parallax using Convolutional Neural Network [Not invited]
ChengJun Shao; Makoto Murakami
13th World Congress on Computational Mechanics 2018/07 Oral presentation
We propose a neural network which can recognize objects from a sequence of RGB images captured with a single camera through two different convolutional neural networks. The learning process is divided into two steps: learning of CNN for spatial feature extraction and learning of CNN for spatiotemporal feature extraction. The spatial feature extraction CNN extracts spatial feature vectors with position invariance. And they are input to the following spatiotemporal feature extraction CNN, which convolutes them temporally to achieve depth information based on motion parallax. In the spatial feature extraction CNN, each frame of image sequence is convoluted with some spatial filters, the convoluted values are passed through an activation function, and some spatial features are extracted in the convolutional layer. The features are input to the local contrast normalization layer, and the following pooling layer for downsampling. With these three layers as a set, three sets of layers are concatenated to extract low, medium, and high level spatial features. Then, the high level features are converted to a one-dimensional vector, and weighted sums of elements of it are passed through an activation function in the fully connected layer. We may use dropout to reduce the degree of freedom of the network, and to prevent overfitting. In the spatiotemporal feature extraction CNN, a sequence of the low and medium spatial features extracted in the spatial feature extraction CNN with a frame length T is input to the convolutional layer. The sequence of the same spatial features is convoluted with some temporal filters, the convoluted values are passed through an activation function, and some temporal features including depth information from motion parallax can be extracted. The features are input to the local contrast normalization layer, the pooling layer, and the fully connected layer. And the high level spatial features extracted in the spatial feature extraction CNN are also input to the fully connected layer. And these different kinds of features are integrated in the output layer. To evaluate our proposed method we conducted an experiment using some objects with simple shapes, and extracted the shape information from motion parallax.
Object Shape Feature Extraction from Motion Parallax using Convolutional Neural Network [Not invited]ChengJun Shao; Makoto Murakami13th World Congress on Computational Mechanics 2018/07 Oral presen...See More
Object Shape Feature Extraction from Motion Parallax using Convolutional Neural Network [Not invited]
ChengJun Shao; Makoto Murakami
13th World Congress on Computational Mechanics 2018/07 Oral presentation
We propose a neural network which can recognize objects from a sequence of RGB images captured with a single camera through two different convolutional neural networks. The learning process is divided into two steps: learning of CNN for spatial feature extraction and learning of CNN for spatiotemporal feature extraction. The spatial feature extraction CNN extracts spatial feature vectors with position invariance. And they are input to the following spatiotemporal feature extraction CNN, which convolutes them temporally to achieve depth information based on motion parallax. In the spatial feature extraction CNN, each frame of image sequence is convoluted with some spatial filters, the convoluted values are passed through an activation function, and some spatial features are extracted in the convolutional layer. The features are input to the local contrast normalization layer, and the following pooling layer for downsampling. With these three layers as a set, three sets of layers are concatenated to extract low, medium, and high level spatial features. Then, the high level features are converted to a one-dimensional vector, and weighted sums of elements of it are passed through an activation function in the fully connected layer. We may use dropout to reduce the degree of freedom of the network, and to prevent overfitting. In the spatiotemporal feature extraction CNN, a sequence of the low and medium spatial features extracted in the spatial feature extraction CNN with a frame length T is input to the convolutional layer. The sequence of the same spatial features is convoluted with some temporal filters, the convoluted values are passed through an activation function, and some temporal features including depth information from motion parallax can be extracted. The features are input to the local contrast normalization layer, the pooling layer, and the fully connected layer. And the high level spatial features extracted in the spatial feature extraction CNN are also input to the fully connected layer. And these different kinds of features are integrated in the output layer. To evaluate our proposed method we conducted an experiment using some objects with simple shapes, and extracted the shape information from motion parallax.
Feature extraction of object shape from motion parallax using convolutional neural networ [Not invited]
能動的情報収集対話システムを目的とした対話終了判断モデルの構築 [Not invited]2011/03 我々はユーザと能動的にコミュニケーションを取り,感想情報のような再利用する価値のある情報を言語情報として所得するシステムの実現を目指している.このようなシステムにおいては,システムがしつこく情報収集を続けてしまうと次回からの情報収集に支障をきたす恐れがあるため,ユーザが対話したくないことを...See More
J-014 Effective feature analysis to construct decision model for a system to end communicating with a human [Not invited]OTSUKA Naoki; MURAKAMI Makoto; YAMAGIWA Motoi; UEHARA Minoru情報科学技術フォーラム講演論文集 ...See More
Recently, according to increases hardware performance, the resources of each PC are enlarged. But, those resources are not used entirely. There are many free or idle parts in those resources. We are studying on controlling full grid on Windows PC by using Virtual Machine. This study aims to utilize idle resources of Windows PC using Linux Grid on Virtual Machine (Virtual Grid). And we have developed Meta Grid that controls Virtual Grid. In this paper, we propose a method of using Web Storage for Meta Grid. IN this method, Virtual Grid can use massive Web Storage through NBD. As this result,...
The Evaluations of Meta Grid using WebDisk [Not invited]Tanaka Kenichi; Uehara Minoru; Murakami Makoto; Yamagiwa MotoiIPSJ SIG Notes 2008/11 Recently, according to increases hardware performance, t...See More
Recently, according to increases hardware performance, the resources of each PC are enlarged. But, those resources are not used entirely. There are many free or idle parts in those resources. We are studying on controlling full grid on Windows PC by using Virtual Machine. This study aims to utilize idle resources of Windows PC using Linux Grid on Virtual Machine (Virtual Grid). And we have developed Meta Grid that controls Virtual Grid. In this paper, we propose a method of using Web Storage for Meta Grid. IN this method, Virtual Grid can use massive Web Storage through NBD. As this result,...
Proceedings of the IEICE General Conference 2006/03
D-15-33 Human motion analysis in different concentration levels for user-oriented e-learning system [Not invited]Gomi Mariko; Murakami Makoto; Yoneyama MasahideProceedings of the IEICE General Confer...See More
ONO Yukimasa; MARUYAMA Sachiko; MURAKAMI Makoto; YONEYAMA Masahide
電子情報通信学会技術研究報告. PRMU, パターン認識・メディア理解 2003/11
Optimization of Control Parameter for Extraction of Human Face based on Extended Labeled Graph Matching [Not invited]ONO Yukimasa; MARUYAMA Sachiko; MURAKAMI Makoto; YONEYAMA Masahide電子情報通信学会技術研究報告. ...See More
ONO Yukimasa; MARUYAMA Sachiko; MURAKAMI Makoto; YONEYAMA Masahide
Technical report of IEICE. PRMU 2003/11
W e applied Labeled Graph Matching used for object recognition of still picture to the moving image. It became possible that the process sequentially dealt with until now by this technique was integratedly processed. However, it is necessary that the recognition accuracy and processing time consider the control method, since it is affected in feature quantity control parameter. In this paper, we carried out the analysis on the parametric control method for optimizing the extraction accuracy by applying the proposal technique to the problem of the head region extraction.
Optimization of Control Parameter for Extraction of Human Face based on Extended Labeled Graph Matching [Not invited]ONO Yukimasa; MARUYAMA Sachiko; MURAKAMI Makoto; YONEYAMA MasahideTechnical report...See More
ONO Yukimasa; MARUYAMA Sachiko; MURAKAMI Makoto; YONEYAMA Masahide
Technical report of IEICE. PRMU 2003/11
W e applied Labeled Graph Matching used for object recognition of still picture to the moving image. It became possible that the process sequentially dealt with until now by this technique was integratedly processed. However, it is necessary that the recognition accuracy and processing time consider the control method, since it is affected in feature quantity control parameter. In this paper, we carried out the analysis on the parametric control method for optimizing the extraction accuracy by applying the proposal technique to the problem of the head region extraction.
ONO Yukimasa; MARUYAMA Sachiko; MURAKAMI Makoto; YONEYAMA Masahide
Technical report of IEICE. HIP 2003/11
W e applied Labeled Graph Matching used for object recognition of still picture to the moving image. It became possible that the process sequentially dealt with until now by this technique was integratedly processed. However, it is necessary that the recognition accuracy and processing time consider the control method, since it is affected in feature quantity control parameter. In this paper, we carried out the analysis on the parametric control method for optimizing the extraction accuracy by applying the proposal technique to the problem of the head region extraction.
Optimization of Control Parameter for Extraction of Human Face based on Extended Labeled Graph Matching [Not invited]ONO Yukimasa; MARUYAMA Sachiko; MURAKAMI Makoto; YONEYAMA MasahideTechnical report...See More
ONO Yukimasa; MARUYAMA Sachiko; MURAKAMI Makoto; YONEYAMA Masahide
Technical report of IEICE. HIP 2003/11
W e applied Labeled Graph Matching used for object recognition of still picture to the moving image. It became possible that the process sequentially dealt with until now by this technique was integratedly processed. However, it is necessary that the recognition accuracy and processing time consider the control method, since it is affected in feature quantity control parameter. In this paper, we carried out the analysis on the parametric control method for optimizing the extraction accuracy by applying the proposal technique to the problem of the head region extraction.
Proceedings of the Society Conference of IEICE 2003/09
Reconstruction of Ultrasonic Image using CSG by Genetic Algorithm [Not invited]Aoki Koushirou; Yamagiwa Motoi; Murakami Makoto; Yoneyama MasahideProceedings of the Society Conference of IEICE 2003/0...See More
Proceedings of the Society Conference of IEICE 2003/09
Extraction of Characteristic Features from Letter Images for Personal Font Creation [Not invited]Tamaru Masazumi; Murakami Makoto; Sugimoto Futoshi; Yoneyama MasahideProceedings of the Society Confer...See More
Analysis of Appropriate Distance and Direction of User and AR Character for Communication Using AR WoZ SystemARAMAKI Reina; MURAKAMI Makoto Technical report of IEICE. HCS 112- (412) 31 -36 2013/...See More
A Method to Synthesize Three Dimensional Face Models by Mapping from a Word Space to a Physical Model Space and the Inspection of the Mapping FunctionFutoshi Sugimoto; Makoto Murakami; Chieko Kato 情報...See More
A Method to Synthesize Three Dimensional Face Models by Mapping from a Word Space to a Physical Model Space and the Inspection of the Mapping Function (Special Issue on Theory and Application of Intel...See More
J-014 Effective feature analysis to construct decision model for a system to end communicating with a humanOTSUKA Naoki; MURAKAMI Makoto; YAMAGIWA Motoi; UEHARA Minoru 情報科学技術フォーラム講演論文集 9- (3) 497 ...See More
山際 基; 上原 稔; 村上 真 マルチメディア通信と分散処理ワークショップ論文集 = Multimedia Communication and Distributed Processing System Workshop 2009- (9) 189 -194 2009/09
The application of Social Life Log for Ecological lifestyle in the home山際 基; 上原 稔; 村上 真 マルチメディア通信と分散処理ワークショップ論文集 = Multimedia Communication and Distributed Processing System Workshop 2009- (9) 189...See More
J-046 Effective feature analysis to construct decision model for a system to end communicating with a humanOTSUKA Naoki; MURAKAMI Makoto; YAMAGIWA Motoi; UEHARA Minoru 情報科学技術フォーラム講演論文集 8- (3) 499 ...See More
Reconstruction for two dimentional artificially degraded image using constructive solid geometry and genetic programmingMotoi Yamagiwa; Minoru Uehara; Makoto Murakami; Masahide Yoneyama Industrial te...See More
Gomi Mariko; Murakami Makoto; Yoneyama Masahide Proceedings of the IEICE General Conference 185 -185 2006
D-15-33 Human motion analysis in different concentration levels for user-oriented e-learning systemGomi Mariko; Murakami Makoto; Yoneyama Masahide Proceedings of the IEICE General Conference 185 -1...See More
ONO Yukimasa; MARUYAMA Sachiko; MURAKAMI Makoto; YONEYAMA Masahide Technical report of IEICE. HIP 103- (455) 19 -24 2003/11
Optimization of Control Parameter for Extraction of Human Face based on Extended Labeled Graph MatchingONO Yukimasa; MARUYAMA Sachiko; MURAKAMI Makoto; YONEYAMA Masahide Technical report of IEICE. HI...See More
Tamaru Masazumi; Murakami Makoto; Sugimoto Futoshi; Yoneyama Masahide Proceedings of the Society Conference of IEICE 2003- 85 -85 2003/09
Extraction of Characteristic Features from Letter Images for Personal Font CreationTamaru Masazumi; Murakami Makoto; Sugimoto Futoshi; Yoneyama Masahide Proceedings of the Society Conference of IEICE...See More
MURAKAMI Makoto; YONEYAMA Masahide; SHIRAI Katsuhiko IEICE transactions on information and systems 85- (11) 1889 -1889 2002/11
Extraction of Human Face and Transformable Region by Facial Expression Based on Extended Labeled Graph MatchingMURAKAMI Makoto; YONEYAMA Masahide; SHIRAI Katsuhiko IEICE transactions on information a...See More
OHTAKE Akira; SHINMOTO Takashi; MURAKAMI Makoto; YONEYAMA Masahide; SHIRAI Katsuhiko Proceedings of the IEICE General Conference 1999- (2) 266 -266 1999/03
Recognition of Human faces Having Facial Expressions Using Discrete Hopfield Neural NetworkOHTAKE Akira; SHINMOTO Takashi; MURAKAMI Makoto; YONEYAMA Masahide; SHIRAI Katsuhiko Proceedings of the IEIC...See More
Japan Society for the Promotion of Science:Grants-in-Aid for Scientific Research
Date (from‐to) : 2019/04 -2022/03
Author : Murakami Makoto
We consider that the process that people create various human motions in their minds and the process that people recognize various human motions are complicated and non-linear. And we modeled them using two different kinds of deep neural networks: generative adversarial networks and variational autoencoders. We trained the proposed models using human motion dataset captured with optical motion capture system. And we confirmed that the trained models can generate various natural human motions.
Human Motion Manifold using Deep Neural NetworksJapan Society for the Promotion of Science:Grants-in-Aid for Scientific ResearchDate (from‐to) : 2019/04 -2022/03 Author : Murakami Makoto We consider ...See More
Japan Society for the Promotion of Science:Grants-in-Aid for Scientific Research
Date (from‐to) : 2019/04 -2022/03
Author : Murakami Makoto
We consider that the process that people create various human motions in their minds and the process that people recognize various human motions are complicated and non-linear. And we modeled them using two different kinds of deep neural networks: generative adversarial networks and variational autoencoders. We trained the proposed models using human motion dataset captured with optical motion capture system. And we confirmed that the trained models can generate various natural human motions.
Japan Society for the Promotion of Science:Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)
Date (from‐to) : 2008 -2011
Author : YUBUNE Eiichi; MURAKAMI Makoto
In order for Japanese learners of English to acquire native-like sounding natural speech, we attempted to develop a computer program which recognizes and evaluates the extent to which learners' phonetic realization is either close or distant against the teacher speech. We used a DP matching method to make the evaluation program of coalescent assimilation and linking of English sounds embedded in the sample sentences. As the result of comparing the program's evaluations with the human evaluations, considerably high validity and correlation were found, suggesting our automatic recognition and evaluation system will be of use. We also conducted a research on which feedback modality will best help the learner to realize the important aspects of pronunciation in producing better English rhythm. We tested three different modalities against experimental subjects : visual, auditory, and linguistic. As the result, the auditory feedback tended to be best recognized among the three.
Development research on e-learning material helping acquiring English rhythm and sound changesJapan Society for the Promotion of Science:Grants-in-Aid for Scientific Research Grant-in-Aid for Scientif...See More
Japan Society for the Promotion of Science:Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)
Date (from‐to) : 2008 -2011
Author : YUBUNE Eiichi; MURAKAMI Makoto
In order for Japanese learners of English to acquire native-like sounding natural speech, we attempted to develop a computer program which recognizes and evaluates the extent to which learners' phonetic realization is either close or distant against the teacher speech. We used a DP matching method to make the evaluation program of coalescent assimilation and linking of English sounds embedded in the sample sentences. As the result of comparing the program's evaluations with the human evaluations, considerably high validity and correlation were found, suggesting our automatic recognition and evaluation system will be of use. We also conducted a research on which feedback modality will best help the learner to realize the important aspects of pronunciation in producing better English rhythm. We tested three different modalities against experimental subjects : visual, auditory, and linguistic. As the result, the auditory feedback tended to be best recognized among the three.
To clarify how emotion appears in speech sound, we analyzed it using rakugo comic stories speech data, which is a kind of the most natural and emotional speech data. As a result the variance in speech sound with emotion mainly appears at the end of utterance. Then we focused on laughing voice as an emotion representation in physiological function. As a result of its analysis f0 frequency and phoneme timing are the fundamental features to perceive the voice as laughing.
Then to generate motion with emotion from language instructions we constructed emotion representation model, in which the relation between the emotional words and the motion is described as a binary tree. Then we implemented the virtual actor system, which consists of the emotion representation component to generate target motion from language instructions using the emotion representation model, and the emotion learning component to update the emotion representation model when an unknown word is given. As a result of the evaluation experiment our system generates the appropriate motion with emotion.
Finally, in order to clarify the relation between the signals of video and sound and the emotion which we perceive from them, we analyzed it using the visual and speech data with emotion. As a result speakers represent emotional level by the change of not facial expression but voice. At the same time listeners recognize the kind of emotion from the speakers' facial expression, and perceive the level of the emotion from the speakers' voice.
Construction of Multimodal Emotion Representation Model for Computer AnimationJapan Society for the Promotion of Science:Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (A)D...See More
To clarify how emotion appears in speech sound, we analyzed it using rakugo comic stories speech data, which is a kind of the most natural and emotional speech data. As a result the variance in speech sound with emotion mainly appears at the end of utterance. Then we focused on laughing voice as an emotion representation in physiological function. As a result of its analysis f0 frequency and phoneme timing are the fundamental features to perceive the voice as laughing.
Then to generate motion with emotion from language instructions we constructed emotion representation model, in which the relation between the emotional words and the motion is described as a binary tree. Then we implemented the virtual actor system, which consists of the emotion representation component to generate target motion from language instructions using the emotion representation model, and the emotion learning component to update the emotion representation model when an unknown word is given. As a result of the evaluation experiment our system generates the appropriate motion with emotion.
Finally, in order to clarify the relation between the signals of video and sound and the emotion which we perceive from them, we analyzed it using the visual and speech data with emotion. As a result speakers represent emotional level by the change of not facial expression but voice. At the same time listeners recognize the kind of emotion from the speakers' facial expression, and perceive the level of the emotion from the speakers' voice.
Since broadband Internet connections have become widely available, multimedia educational software is estimated to be of great importance for the immediate future. PDAs and mobile phones owned by many young people are considered to be as effective as PCs in near-future language learning.
We made a comparative study of PCs, PDAs, and mobile phones in terms of usability, effectiveness, and interactivity in language learning. PDAs were judged to be more useful than mobile phones in the 2001-2 experiment. Students studied in a multimedia English program using the three different environments (eight students per PC, PDA, and mobile phone) and afterwards took exams. PCs turned out to be very dependable, but PDAs showed a great potential for language learning because of their portability and unique functions.
Our research also focused on how to develop learning materials using the Internet. We made three different movies for our collaborative experiment in creating educational software on the web. The traditional way of making educational software is for programmers to design, produce, and edit learning materials in one place together with authors and editors, but in this research each team member could occupy a different site on the web and still collaborate simultaneously in the production of software. Commuting time was saved because the participants in this collaboration did not have to meet physically at one place.
In order to decide whether the text used for educational software is appropriate for students, we used text-analyzing programs and the English text database : the levels of the texts were decided by the number of their vocabulary words. We added another one thousand texts (700 megabytes) to the present English Text Database to extract more sample sentences in textual analysis. We also came to the conclusion that at least 4000 vocabulary words were necessary for college students to understand the average English newspaper and its equivalents, although Japanese high-school graduates learn only two thousand words at high school.
We also collected and analyzed TOEFL and various English tests to make a prototype of CBT (Computer-Based Testing). This program was designed to evaluate students' English language abilities automatically pointing out their strengths and weaknesses based on grammar and usage data stored in the databases.
English Education and Making of Educational Materials in the Information SocietyJapan Society for the Promotion of Science:Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (B...See More
Since broadband Internet connections have become widely available, multimedia educational software is estimated to be of great importance for the immediate future. PDAs and mobile phones owned by many young people are considered to be as effective as PCs in near-future language learning.
We made a comparative study of PCs, PDAs, and mobile phones in terms of usability, effectiveness, and interactivity in language learning. PDAs were judged to be more useful than mobile phones in the 2001-2 experiment. Students studied in a multimedia English program using the three different environments (eight students per PC, PDA, and mobile phone) and afterwards took exams. PCs turned out to be very dependable, but PDAs showed a great potential for language learning because of their portability and unique functions.
Our research also focused on how to develop learning materials using the Internet. We made three different movies for our collaborative experiment in creating educational software on the web. The traditional way of making educational software is for programmers to design, produce, and edit learning materials in one place together with authors and editors, but in this research each team member could occupy a different site on the web and still collaborate simultaneously in the production of software. Commuting time was saved because the participants in this collaboration did not have to meet physically at one place.
In order to decide whether the text used for educational software is appropriate for students, we used text-analyzing programs and the English text database : the levels of the texts were decided by the number of their vocabulary words. We added another one thousand texts (700 megabytes) to the present English Text Database to extract more sample sentences in textual analysis. We also came to the conclusion that at least 4000 vocabulary words were necessary for college students to understand the average English newspaper and its equivalents, although Japanese high-school graduates learn only two thousand words at high school.
We also collected and analyzed TOEFL and various English tests to make a prototype of CBT (Computer-Based Testing). This program was designed to evaluate students' English language abilities automatically pointing out their strengths and weaknesses based on grammar and usage data stored in the databases.