一种目标识别调查仿生的图像处理外文原文.pdfVIP

International Journal of Image and Graphics Vol. 9, No. 4 (2009) 495–510 c World Scientific Publishing Company A SURVEY OF BIOLOGICALLY INSPIRED IMAGE PROCESSING FOR OBJECTS RECOGNITION WEIREN SHI∗ , ZUOJIN LI† and XIN SHI‡ College of Automation, Chongqing University No. 174, Shazheng Street, Shapingba District Chongqing, People’s Republic of China, 400044 ∗ wrs@ †lizuojin110@ ‡ meetshixin@ ZHI ZHONG The Smartech Institute, Room 1808, Anhui Building No. 6007, Shennan Road, Futian District Shenzhen, People’s Republic of China, 518040 zzhong@.hk Received 17 September 2008 Revised 21 January 2009 Accepted 16 May 2009 The human vision system is a very sophisticated image processing and objects recog- nition mechanism. However, it is a challenge to simulate the human or animal vision system to automate visual function in machines, because it is difficult to account for the view-invariant perception of universals such as environmental objects or processes and the explicit perception of featural parts and wholes in visual scenes. In this paper, we first present an introduction to the importance of biologically inspired computer vision and review general and key