Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Haralick, R.M.: Computer Vision Theory: The Lack Thereof. Computer Vision Graphics and Image Processing 36(2), 272–286 (1986)
Haralick, R.M.: Performance Characterization in Computer Vision. Computer Vision, Graphics and Image Processing: Image Understanding 60(2), 245–249 (1994)
Haralick, R.M.: Comments on Performance Characterization Replies. Computer Vision, Graphics, and Image Processing: Image Understanding 60(2), 264–265 (1994)
Foerstner, W.: 10 Pros and Cons Against Performance Characterization of Vision Algorithms. In: Proc. ECCV Workshop on Performance Characteristics of Vision Algorithms (April 1996)
Thacker, N.A.: Using Quantitative Statistics for the Construction of Machine Vision Systems. In: Keynote presentation given to Optoelectronics, Photonics and Imaging (September 2002)
Heath, M., Sarkar, S., et al.: A Robust Visual Method for Assessing the Relative Performance of Edge Detection Algorithms. IEEE Trans. PAMI 19(12), 1338–1359 (1997)
Müller, H., Müller, W., et al.: Performance Evaluation in Content–Based Image Retrieval: Overview and Proposals. Pattern Recognition Letters 22(5), 593–601 (2001)
Shin, M.C., Goldgolf, D.B., Bowyer, K.W.: Comparison of Edge Detector Performance Through Use in an Object Recognition Task. Computer Vision and Image Understanding 84, 160–178 (2001)
McCane, B.: On Benchmarking Optical Flow. Computer Vision and Image Understanding 84, 126–143 (2001)
Cinque, L., Guerra, C., Levialdi, S.: Reply On the Paper by R.M. Haralick. Computer Vision, Graphics, and Image Processing: Image Understanding 60(2), 250–252 (1994)
Bowyer, K.W., Phillips, P.J.: Overview of Work in Empirical Evaluation of Computer Vision Algorithms. In: Empirical Evaluation Techniques in Computer Vision, IEEE Computer Press, Los Alamitos (1998)
Poggio, T., et al.: Computational Vision and Regularization Theory. Nature 317(26), 314–319 (1985)
Marr, D.: Vision. Freeman, New York (1982)
Rock: Perception. Scientific American Books, Inc. (1984)
Gregory, R.L.: Eye and Brain. Princeton University Press, Princeton (1997)
Biederman: Recognition-by-Components: A Theory of Human Image Understanding. Psychological Review 94, 115–147 (1987)
Koffka, K.: Principle of Gestalt Psychology. Harcourt Brace Jovanovich Company, New York (1935)
Zhang, M.: Psychology of Visual Cognition. East China Normal University Press (1991)
Rock: The Logic of Perception. MIT Press, Cambridge (1983)
Sobel, D.M., et al.: Children’s causal inferences from indirect evidence: Backwards blocking and Bayesian reasoning in preschoolers. Cognitive Science 28, 303–333 (2004)
Coad, P., Yourdon, E.: Object-Oriented Analysis. Yourdon Press, New York (1990)
Horn, B.K.P., et al.: Determining Optical Flow. Artificial Intelligence 17, 185–203 (1981)
Verr, et al.: Motion Field and Optical Flow: Qualitative Properties. IEEE Trans. PAMI 11, 490–498 (1989)
Itti, L., Koch, C., Neibur, E.: A Model of Saliency-based Visual Attention for Rapid Scene Analysis. IEEE Trans. PAMIÂ 20(11) (1998)
Navalpakkam, V., Itti, L.: A Goal Oriented Attention Guidance Model. In: Bülthoff, H.H., Lee, S.-W., Poggio, T.A., Wallraven, C. (eds.) BMCV 2002. LNCS, vol. 2525, pp. 453–461. Springer, Heidelberg (2002)
Oliva, A., Torralba, M.: Top-down Control of Visual Attention in Object Detection. In: International Conference on Image Processing (2003)
Zhang, Y.J.: Content-based Visual Information Retrieval. Science Press, Beijing (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wu, A., Xu, D., Yang, X., Zheng, J. (2005). Performance Characterization in Computer Vision: The Role of Visual Cognition Theory. In: Wang, L., Jin, Y. (eds) Fuzzy Systems and Knowledge Discovery. FSKD 2005. Lecture Notes in Computer Science(), vol 3614. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11540007_165
Download citation
DOI: https://doi.org/10.1007/11540007_165
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28331-7
Online ISBN: 978-3-540-31828-6
eBook Packages: Computer ScienceComputer Science (R0)