A Method of Objects Classification Based on Learning and Visual Perception
Objects classification is one of the most significant problems in computer vision. For improving the accuracy of objects classification, we put forward a new classification method enlightened the whole process that human distinguish different types of objects. Our method mixed visual saliency model...
Format: | Article |
---|---|
Language: | zho |
Published: |
EDP Sciences
2018-04-01
|
Series: | Xibei Gongye Daxue Xuebao |
Subjects: | |
Online Access: | https://www.jnwpu.org/articles/jnwpu/pdf/2018/02/jnwpu2018362p359.pdf |
_version_ | 1797423041231192064 |
---|---|
collection | DOAJ |
description | Objects classification is one of the most significant problems in computer vision. For improving the accuracy of objects classification, we put forward a new classification method enlightened the whole process that human distinguish different types of objects. Our method mixed visual saliency model and CNN, is more close to human and has apparently biological advantages. Firstly, we built an eye-tracking database to learn people visual behaviors when they classify various objects and recorded the eye-tracking data. Secondly, this database is used to train a learning-based visual attention model, which is based on low-level (e.g., orientation, color, intensity, etc.) and high-level (e.g., faces, people, cars, etc.) image features to analyze and predict the human's classification RoIs. Finally, we established a CNN framework to classify RoIs. The results of the experiment showed our attention model can determine saliency regions and predict human's classification RoIs more precisely and our classification method improved the efficiency of classification markedly. |
first_indexed | 2024-03-09T07:41:40Z |
format | Article |
id | doaj.art-dcea3abda6134500b4cc9df60a63bb3a |
institution | Directory Open Access Journal |
issn | 1000-2758 2609-7125 |
language | zho |
last_indexed | 2024-03-09T07:41:40Z |
publishDate | 2018-04-01 |
publisher | EDP Sciences |
record_format | Article |
series | Xibei Gongye Daxue Xuebao |
spelling | doaj.art-dcea3abda6134500b4cc9df60a63bb3a2023-12-03T04:38:28ZzhoEDP SciencesXibei Gongye Daxue Xuebao1000-27582609-71252018-04-0136235936710.1051/jnwpu/20183620359jnwpu2018362p359A Method of Objects Classification Based on Learning and Visual Perception0123School of Computer Science, Northwestern Polytechnical UniversitySchool of Computer Science, Northwestern Polytechnical UniversitySchool of Computer Science, Northwestern Polytechnical UniversitySchool of Electronics and Information, Northwestern Polytechnical UniversityObjects classification is one of the most significant problems in computer vision. For improving the accuracy of objects classification, we put forward a new classification method enlightened the whole process that human distinguish different types of objects. Our method mixed visual saliency model and CNN, is more close to human and has apparently biological advantages. Firstly, we built an eye-tracking database to learn people visual behaviors when they classify various objects and recorded the eye-tracking data. Secondly, this database is used to train a learning-based visual attention model, which is based on low-level (e.g., orientation, color, intensity, etc.) and high-level (e.g., faces, people, cars, etc.) image features to analyze and predict the human's classification RoIs. Finally, we established a CNN framework to classify RoIs. The results of the experiment showed our attention model can determine saliency regions and predict human's classification RoIs more precisely and our classification method improved the efficiency of classification markedly.https://www.jnwpu.org/articles/jnwpu/pdf/2018/02/jnwpu2018362p359.pdfvisual attention modelcnnobjects classificationsvm |
spellingShingle | A Method of Objects Classification Based on Learning and Visual Perception Xibei Gongye Daxue Xuebao visual attention model cnn objects classification svm |
title | A Method of Objects Classification Based on Learning and Visual Perception |
title_full | A Method of Objects Classification Based on Learning and Visual Perception |
title_fullStr | A Method of Objects Classification Based on Learning and Visual Perception |
title_full_unstemmed | A Method of Objects Classification Based on Learning and Visual Perception |
title_short | A Method of Objects Classification Based on Learning and Visual Perception |
title_sort | method of objects classification based on learning and visual perception |
topic | visual attention model cnn objects classification svm |
url | https://www.jnwpu.org/articles/jnwpu/pdf/2018/02/jnwpu2018362p359.pdf |