Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00017
Ryota Onishi, Kaito Tanaka, Hiroaki Sawano, Yuri Suzuki, S. Hotta
Motion comics, which are used to advertise printed comics, are created by adding video effects and a sound source to panels from the original (printed) comics. We propose a method for creating a motion comic which consists of the following steps: extracting a panel from a printed page, adding video effects, and switching the panel in time with sound effects. Because it is difficult for beginners in video production to perform these steps, we have devised a method that automatically creates a motion comic using the printed comic pages and sound. In our experimental evaluations, the precision of our proposed panel extraction was greater than 0.75, and we successfully implemented our proposed video effects and panel switching method.
{"title":"Method for Creating Motion Comic from Printed Comic","authors":"Ryota Onishi, Kaito Tanaka, Hiroaki Sawano, Yuri Suzuki, S. Hotta","doi":"10.1109/NicoInt50878.2020.00017","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00017","url":null,"abstract":"Motion comics, which are used to advertise printed comics, are created by adding video effects and a sound source to panels from the original (printed) comics. We propose a method for creating a motion comic which consists of the following steps: extracting a panel from a printed page, adding video effects, and switching the panel in time with sound effects. Because it is difficult for beginners in video production to perform these steps, we have devised a method that automatically creates a motion comic using the printed comic pages and sound. In our experimental evaluations, the precision of our proposed panel extraction was greater than 0.75, and we successfully implemented our proposed video effects and panel switching method.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126326419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00034
Meina Tawaki, I. Kanaya, Keiko Yamamoto
research, the authors surveyed emotional impressions of simplified face. Elements of the simplified face are two eyes and a mouth, which are transformed to make facial expressions geometrically. The facial expression patterns made by the geometric elements and transformations were composed employing three dimensions of visual information that had been suggested by many previous researches, slantedness of the mouth, openness of the face, and slantedness of the eyes. The authors found that facial expressions can be classified into 10 emotions: happy, angry, sad, disgust, fear, surprised, angry*, fear*, neutral (positive), and neutral (negative). These emotions were portrayed by different geometric transformations.
{"title":"Cross-cultural design of facial expressions for humanoid robots","authors":"Meina Tawaki, I. Kanaya, Keiko Yamamoto","doi":"10.1109/NicoInt50878.2020.00034","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00034","url":null,"abstract":"research, the authors surveyed emotional impressions of simplified face. Elements of the simplified face are two eyes and a mouth, which are transformed to make facial expressions geometrically. The facial expression patterns made by the geometric elements and transformations were composed employing three dimensions of visual information that had been suggested by many previous researches, slantedness of the mouth, openness of the face, and slantedness of the eyes. The authors found that facial expressions can be classified into 10 emotions: happy, angry, sad, disgust, fear, surprised, angry*, fear*, neutral (positive), and neutral (negative). These emotions were portrayed by different geometric transformations.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132525787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00025
Benjamin Santerre, Masaki Abe, Taichi Watanabe
This paper proposes a terrain tessellation technique using the new GPU mesh pipeline, and compares it to the classically used tessellation pipeline. We explain how we can use it to greatly increase the tessellation capability within the draw call while keeping similar performances. We then show how it can be used to limit the CPU load as well as the data transfer to the GPU for rendering wide terrains.
{"title":"Improving GPU Real-Time Wide Terrain Tessellation Using the New Mesh Shader Pipeline","authors":"Benjamin Santerre, Masaki Abe, Taichi Watanabe","doi":"10.1109/NicoInt50878.2020.00025","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00025","url":null,"abstract":"This paper proposes a terrain tessellation technique using the new GPU mesh pipeline, and compares it to the classically used tessellation pipeline. We explain how we can use it to greatly increase the tessellation capability within the draw call while keeping similar performances. We then show how it can be used to limit the CPU load as well as the data transfer to the GPU for rendering wide terrains.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126652471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00031
Kouta Kikuchi, Toshitaka Amaoka
We have proposed "Kage User Interface(KUI)" which uses the real shadow in the real world as an interface. In this research, we propose a "KUI Based Puppet" to provide an intuitive manipulation and edit shadow pictures in direct contact, alternative way of a conventional shadow puppet. A conventional shadow puppet is changed it's shape by manipulating poles attached to the limbs of puppet. The KUI Based Puppet enables users to manipulate a puppet shadow in direct contact.
{"title":"KUI Based Puppet","authors":"Kouta Kikuchi, Toshitaka Amaoka","doi":"10.1109/NicoInt50878.2020.00031","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00031","url":null,"abstract":"We have proposed \"Kage User Interface(KUI)\" which uses the real shadow in the real world as an interface. In this research, we propose a \"KUI Based Puppet\" to provide an intuitive manipulation and edit shadow pictures in direct contact, alternative way of a conventional shadow puppet. A conventional shadow puppet is changed it's shape by manipulating poles attached to the limbs of puppet. The KUI Based Puppet enables users to manipulate a puppet shadow in direct contact.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128315986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00010
Naoya Tsuruta, Sawa Hiraiwa, Ryuta Motegi, K. Kondo
In this paper, we propose a support method for 3D modeling of architectural decor, which used in the Corinthian order of ancient Greek and Roman. Since this architectural style is characterized by decoration with acanthus leaves and scrolls, we classified 1291 parts obtained from 200 pictures of architecture with acanthus patterns by their shapes and positions. We then extracted 34 representative parts necessary for decor design and build a 3D model library of them. The user can use desired parts by importing them from existing 3D modeling tool. Experimental results show that the user can greatly reduce the time for modeling decor using our library.
{"title":"Classification of Acanthus Pattern for 3D Architectural Decor Modeling","authors":"Naoya Tsuruta, Sawa Hiraiwa, Ryuta Motegi, K. Kondo","doi":"10.1109/NicoInt50878.2020.00010","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00010","url":null,"abstract":"In this paper, we propose a support method for 3D modeling of architectural decor, which used in the Corinthian order of ancient Greek and Roman. Since this architectural style is characterized by decoration with acanthus leaves and scrolls, we classified 1291 parts obtained from 200 pictures of architecture with acanthus patterns by their shapes and positions. We then extracted 34 representative parts necessary for decor design and build a 3D model library of them. The user can use desired parts by importing them from existing 3D modeling tool. Experimental results show that the user can greatly reduce the time for modeling decor using our library.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131060820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00021
Yuriho Higuchi, Mitsunori Matsushita
The objective of this study is to aid visually impaired people by presenting them with nonverbal information regarding aspects such as the atmosphere, object state, and facial expressions through the incorporation of tactile sensations of real objects. Such information is often helpful in stimulating one’s imagination and in comprehending or predicting a situation without using words, and it comprises multiple elements such as emotions, motions, and relationships among objects. Furthermore, it is difficult to express such information by employing a single scale, and it is thus necessary to present multiple elements. In this context, the sense of touch can be employed for simultaneously presenting multiple elements and reading tactile sensations. In this study, tactile sensations of objects were utilized for presenting nonverbal information. A prototype system was developed for combining tactile sensations associated with softness, smoothness, and flatness. This study also investigated the number and variety of tactile sensations presented by the proposed system that could be recognized by sighted people. The obtained results indicate that approximately 80% of the people can recognize the sensation of smoothness presented by the system, and more than 50% of the people can recognize the sensations of softness and flatness.
{"title":"Investigation of Method Presented Nonverbal Information Using Tactile Sensations of Real Objects","authors":"Yuriho Higuchi, Mitsunori Matsushita","doi":"10.1109/NicoInt50878.2020.00021","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00021","url":null,"abstract":"The objective of this study is to aid visually impaired people by presenting them with nonverbal information regarding aspects such as the atmosphere, object state, and facial expressions through the incorporation of tactile sensations of real objects. Such information is often helpful in stimulating one’s imagination and in comprehending or predicting a situation without using words, and it comprises multiple elements such as emotions, motions, and relationships among objects. Furthermore, it is difficult to express such information by employing a single scale, and it is thus necessary to present multiple elements. In this context, the sense of touch can be employed for simultaneously presenting multiple elements and reading tactile sensations. In this study, tactile sensations of objects were utilized for presenting nonverbal information. A prototype system was developed for combining tactile sensations associated with softness, smoothness, and flatness. This study also investigated the number and variety of tactile sensations presented by the proposed system that could be recognized by sighted people. The obtained results indicate that approximately 80% of the people can recognize the sensation of smoothness presented by the system, and more than 50% of the people can recognize the sensations of softness and flatness.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125327432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00016
Fernanda Miyuki Yamada, Hiroki Takahashi, H. C. Batagelo, João Paulo Gois
The Tangram is a geometric puzzle composed of seven polygonal pieces that can be combined to form different patterns. In combinatorial optimization, the task of solving Tangram puzzles is known to be NP-hard. In this paper, we present an extension of a recent computational method for the automatic solution of Tangram puzzles. The original work considers the largest-first heuristic, in which the pieces are positioned inside the puzzle region following a sequence from the largest to the smallest in area size. We present three additional permutation heuristics that generate different sequences to guide the pieces positioning inside the puzzle region. The effectiveness of the proposed heuristics is indicated by the application of the extended method on the solution of different Tangram puzzles. Combining the executed experiments, the extended method solved 93.33% of the patterns included in a dataset in an average time of 53.0s, while the original implementation solved 86.67% of the same dataset in an average time of 51.4s.
{"title":"An Extended Approach for the Automatic Solution of Tangram Puzzles Using Permutation Heuristics","authors":"Fernanda Miyuki Yamada, Hiroki Takahashi, H. C. Batagelo, João Paulo Gois","doi":"10.1109/NicoInt50878.2020.00016","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00016","url":null,"abstract":"The Tangram is a geometric puzzle composed of seven polygonal pieces that can be combined to form different patterns. In combinatorial optimization, the task of solving Tangram puzzles is known to be NP-hard. In this paper, we present an extension of a recent computational method for the automatic solution of Tangram puzzles. The original work considers the largest-first heuristic, in which the pieces are positioned inside the puzzle region following a sequence from the largest to the smallest in area size. We present three additional permutation heuristics that generate different sequences to guide the pieces positioning inside the puzzle region. The effectiveness of the proposed heuristics is indicated by the application of the extended method on the solution of different Tangram puzzles. Combining the executed experiments, the extended method solved 93.33% of the patterns included in a dataset in an average time of 53.0s, while the original implementation solved 86.67% of the same dataset in an average time of 51.4s.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125281513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00020
Daisuke Chiba, Katsutsugu Matsuyama
We examine a system that supports creating shadow box art works. The creators of shadow box art carefully determine the number of layers and their shapes to cut out, considering how shadows fall and the thickness of the frame. We investigate the crafting process and design our prototype functions: (1) a user interface for designing shadow box art, (2) a simple viewer considering shadows using 3DCG, and, (3) reducing paper footprint by rearranging cut-out parts. Through creating actual artworks, we confirm that our system enables the user to make layer design smoothly and the creation of shadow box art relatively easily.
{"title":"An Examination of a Support Tool for Designing Shadow Box Art","authors":"Daisuke Chiba, Katsutsugu Matsuyama","doi":"10.1109/NicoInt50878.2020.00020","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00020","url":null,"abstract":"We examine a system that supports creating shadow box art works. The creators of shadow box art carefully determine the number of layers and their shapes to cut out, considering how shadows fall and the thickness of the frame. We investigate the crafting process and design our prototype functions: (1) a user interface for designing shadow box art, (2) a simple viewer considering shadows using 3DCG, and, (3) reducing paper footprint by rearranging cut-out parts. Through creating actual artworks, we confirm that our system enables the user to make layer design smoothly and the creation of shadow box art relatively easily.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126515871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00035
Tomohiro Hibino, Haoran Xie, K. Miyata
Choosing the most desirable image from many images can be a hard task for a user. In this study, we developed an image selection system based on 4 ways of calculating similarity. We conducted an experiment to validate the usability of the system and decide the best method for recommendation. It was confirmed that our system significantly helps users and Principal Component Analysis is a good way to calculate characteristics from many images.
{"title":"Benchmark on Face Image Retrieval From Learning Attributes","authors":"Tomohiro Hibino, Haoran Xie, K. Miyata","doi":"10.1109/NicoInt50878.2020.00035","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00035","url":null,"abstract":"Choosing the most desirable image from many images can be a hard task for a user. In this study, we developed an image selection system based on 4 ways of calculating similarity. We conducted an experiment to validate the usability of the system and decide the best method for recommendation. It was confirmed that our system significantly helps users and Principal Component Analysis is a good way to calculate characteristics from many images.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133242730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00030
Louis. Schmidt, Taichi Watanabe, Koji Mikami
The main purpose of this research is to adjust the game difficulty with Reinforcement Learning. We aim to adjust the AI behavior according to the player skill. The developed game looks like a 2D fighting game. The goal of the paper is to create an AI which learns from the player, but not in order to become stronger, but to adapt it behavior in order to give a good game experience to the player.
{"title":"Adjusting the game difficulty by changing AI behaviors with Reinforcement Learning","authors":"Louis. Schmidt, Taichi Watanabe, Koji Mikami","doi":"10.1109/NicoInt50878.2020.00030","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00030","url":null,"abstract":"The main purpose of this research is to adjust the game difficulty with Reinforcement Learning. We aim to adjust the AI behavior according to the player skill. The developed game looks like a 2D fighting game. The goal of the paper is to create an AI which learns from the player, but not in order to become stronger, but to adapt it behavior in order to give a good game experience to the player.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133607279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：