Computer vision theory: The lack thereof
Computer Vision, Graphics, and Image Processing
Motion Field and Optical Flow: Qualitative Properties
IEEE Transactions on Pattern Analysis and Machine Intelligence
Object-oriented analysis
Performance characterization in computer vision
CVGIP: Image Understanding
On the paper by R. M. Haralick
CVGIP: Image Understanding
Comments on performance characterization replies
CVGIP: Image Understanding
Robust Visual Method for Assessing the Relative Performance of Edge-Detection Algorithms
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Performance evaluation in content-based image retrieval: overview and proposals
Pattern Recognition Letters - Special issue on image/video indexing and retrieval
Computer Vision and Image Understanding - Special issue on empirical evaluation of computer vision algorithms
Comparison of edge detector performance through use in an object recognition task
Computer Vision and Image Understanding - Special issue on empirical evaluation of computer vision algorithms
A Goal Oriented Attention Guidance Model
BMCV '02 Proceedings of the Second International Workshop on Biologically Motivated Computer Vision
| Hi-index | 0.01 |
It is very difficult to evaluate the performance of computer vision algorithms at present. We argue that visual cognition theory can be used to challenge this task. Following are the reasons: (1) Human vision system is so far the best and the most general vision system; (2) The human eye and camera surely have the same mechanism from the perspective of optical imaging; (3) Computer vision problem is similar to human vision problem in theory; (4) The main task of visual cognition theory is to investigate the principles of human vision system. In this paper, we first illustrate why vision cognition theory can be used to characterize the performance of computer vision algorithms and discuss how to use it. Then from the perspective of computer science we summarize some of important assumptions of visual cognition theory. Finally, many cases are introduced, which show that our method can work reasonably well.