Computer Vision System for Expressing Texture Using Sound-Symbolic Words
The major goals of texture research in computer vision are to understand, model, and process texture and ultimately simulate human visual information processing using computer technologies. The field of computer vision has witnessed remarkable advancements in material recognition using deep convolut...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-10-01
|
| Series: | Frontiers in Psychology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyg.2021.654779/full |
| _version_ | 1818722033840685056 |
|---|---|
| author | Koichi Yamagata Jinhwan Kwon Takuya Kawashima Wataru Shimoda Maki Sakamoto |
| author_facet | Koichi Yamagata Jinhwan Kwon Takuya Kawashima Wataru Shimoda Maki Sakamoto |
| author_sort | Koichi Yamagata |
| collection | DOAJ |
| description | The major goals of texture research in computer vision are to understand, model, and process texture and ultimately simulate human visual information processing using computer technologies. The field of computer vision has witnessed remarkable advancements in material recognition using deep convolutional neural networks (DCNNs), which have enabled various computer vision applications, such as self-driving cars, facial and gesture recognition, and automatic number plate recognition. However, for computer vision to “express” texture like human beings is still difficult because texture description has no correct or incorrect answer and is ambiguous. In this paper, we develop a computer vision method using DCNN that expresses texture of materials. To achieve this goal, we focus on Japanese “sound-symbolic” words, which can describe differences in texture sensation at a fine resolution and are known to have strong and systematic sensory-sound associations. Because the phonemes of Japanese sound-symbolic words characterize categories of texture sensations, we develop a computer vision method to generate the phonemes and structure comprising sound-symbolic words that probabilistically correspond to the input images. It was confirmed that the sound-symbolic words output by our system had about 80% accuracy rate in our evaluation. |
| first_indexed | 2024-12-17T20:48:12Z |
| format | Article |
| id | doaj.art-24056ec7e4484c40a24ce806f999cf4b |
| institution | Directory Open Access Journal |
| issn | 1664-1078 |
| language | English |
| last_indexed | 2024-12-17T20:48:12Z |
| publishDate | 2021-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychology |
| spelling | doaj.art-24056ec7e4484c40a24ce806f999cf4b2022-12-21T21:33:06ZengFrontiers Media S.A.Frontiers in Psychology1664-10782021-10-011210.3389/fpsyg.2021.654779654779Computer Vision System for Expressing Texture Using Sound-Symbolic WordsKoichi Yamagata0Jinhwan Kwon1Takuya Kawashima2Wataru Shimoda3Maki Sakamoto4Graduate School of Informatics and Engineering, The University of Electro Communications, Chofu, JapanDepartment of Education, Kyoto University of Education, Kyoto, JapanGraduate School of Informatics and Engineering, The University of Electro Communications, Chofu, JapanGraduate School of Informatics and Engineering, The University of Electro Communications, Chofu, JapanGraduate School of Informatics and Engineering, The University of Electro Communications, Chofu, JapanThe major goals of texture research in computer vision are to understand, model, and process texture and ultimately simulate human visual information processing using computer technologies. The field of computer vision has witnessed remarkable advancements in material recognition using deep convolutional neural networks (DCNNs), which have enabled various computer vision applications, such as self-driving cars, facial and gesture recognition, and automatic number plate recognition. However, for computer vision to “express” texture like human beings is still difficult because texture description has no correct or incorrect answer and is ambiguous. In this paper, we develop a computer vision method using DCNN that expresses texture of materials. To achieve this goal, we focus on Japanese “sound-symbolic” words, which can describe differences in texture sensation at a fine resolution and are known to have strong and systematic sensory-sound associations. Because the phonemes of Japanese sound-symbolic words characterize categories of texture sensations, we develop a computer vision method to generate the phonemes and structure comprising sound-symbolic words that probabilistically correspond to the input images. It was confirmed that the sound-symbolic words output by our system had about 80% accuracy rate in our evaluation.https://www.frontiersin.org/articles/10.3389/fpsyg.2021.654779/fulltexturesound-symbolic wordstactile sensationonomatopoeiaimage databases |
| spellingShingle | Koichi Yamagata Jinhwan Kwon Takuya Kawashima Wataru Shimoda Maki Sakamoto Computer Vision System for Expressing Texture Using Sound-Symbolic Words Frontiers in Psychology texture sound-symbolic words tactile sensation onomatopoeia image databases |
| title | Computer Vision System for Expressing Texture Using Sound-Symbolic Words |
| title_full | Computer Vision System for Expressing Texture Using Sound-Symbolic Words |
| title_fullStr | Computer Vision System for Expressing Texture Using Sound-Symbolic Words |
| title_full_unstemmed | Computer Vision System for Expressing Texture Using Sound-Symbolic Words |
| title_short | Computer Vision System for Expressing Texture Using Sound-Symbolic Words |
| title_sort | computer vision system for expressing texture using sound symbolic words |
| topic | texture sound-symbolic words tactile sensation onomatopoeia image databases |
| url | https://www.frontiersin.org/articles/10.3389/fpsyg.2021.654779/full |
| work_keys_str_mv | AT koichiyamagata computervisionsystemforexpressingtextureusingsoundsymbolicwords AT jinhwankwon computervisionsystemforexpressingtextureusingsoundsymbolicwords AT takuyakawashima computervisionsystemforexpressingtextureusingsoundsymbolicwords AT watarushimoda computervisionsystemforexpressingtextureusingsoundsymbolicwords AT makisakamoto computervisionsystemforexpressingtextureusingsoundsymbolicwords |