Learning and surface boundary feedbacks for colour natural scene perception |
| |
| Affiliation: | 1. Department of Computer Science and Engineering, Faculty of Electronic Engineering, Menoufia University, Menouf 32952, Egypt;2. Department of Information Technology, College of Computers and Information Technology, Taif University, Al-Hawiya 21974, Kingdom of Saudi Arabia;1. School of Data and Computer Science, Sun Yat-sen University, Guangzhou 510006, China;2. Collaborative Innovation Center of High Performance Computing, Sun Yat-sen University, Guangzhou 510006, China;1. Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Malaysia;2. Department of Cyber Security Science, Federal University of Technology, Minna, Nigeria;1. Federal College of Education (Technical), Department of Computer Science, Gombe, Nigeria;2. University of Malaya, Faculty of Computer Science and IT, Kuala Lumpur, Malaysia;3. University of Maribor, Faculty of Electrical Engineering and Computer Science, Smetanova, Maribor, Slovenia;4. Bayero University Kano, Faculty of Engineering, Kano, Nigeria;5. International Islamic University, Malaysia |
| |
| Abstract: | Boundary detection and segmentation are essential stages in object recognition and scene understanding. In this paper, we present a bio-inspired neural model of the ventral pathway for colour contour and surface perception, called LPREEN (Learning and Perceptual boundaRy rEcurrent dEtection Neural architecture). LPREEN models colour opponent processes and feedback interactions between cortical areas V1, V2, V4, and IT, which produce top-down and bottom-up information fusion. We suggest three feedback interactions that enhance and complete boundaries. Our proposed neural model contains a contour learning feedback that enhances the most probable contour positions in V1 according to a previous experience, and generates a surface perception in V4 through diffusion processes. We compared the proposed model with another bio-inspired model and two well-known contour extraction methods, using the Berkeley Segmentation Benchmark. LPREEN showed better performance than two methods and slightly worse performance than another one. |
| |
| Keywords: | Computer vision Contour learning Boundary detection Neural networks Colour image processing Bio-inspired models |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
