The idea is to handle the multi- scale nature of real- world objects, which implies that objects may be perceived in different ways depending on the scale of observation. If one aims at developing automatic algorithms for interpreting images of unknown scenes, there is no way to know a priori what scales are relevant. Hence, the only reasonable approach is to consider representations at all scales simultaneously. From axiomatic derivations is has been shown that given the requirement that coarse- scale representations should correspond to true simplifications of fine scale structures, convolution with Gaussian kernels and Gaussian derivatives is singled out as a canonical class of image operators for the earliest stages of visual processing. These image operators can be used as basis for solving a large variety of visual tasks, including feature detection, feature classification, stereo matching, motion descriptors, shape cues and image- based recognition. By complementing scale- space representation with a module for automatic scale selection based on the maximization of normalized derivatives over scales, early visual modules can be made scale invariant. In this way, visual modules will be able to automatically adapt to the unknown scale variations that may occur due to objects and substructures of varying physical size as well as objects with varying distances to the camera. An interesting similarity to biological vision is that the scale- space operators closely resemble receptive field profiles registered in neurophysiological studies of the mammalian retina and visual cortex. Sziranyi (eds). Proc. Fundamental Structural Properties in. Image and Pattern Analysis FSPIPA'9. Budapest, Hungary). September 6- 7, 1. CERN School of Computing. Egmond aan Zee, The Netherlands, 8- -2. September, 1. 99. The idea is to handle the multi- scale nature of real- world objects, which implies that objects may be perceived in different ways depending on the scale of observation. If one aims at developing automatic algorithms for interpreting images of unknown scenes, there is no way to know a priori what scales are relevant.
Hence, the only reasonable approach is to consider representations at all scales simultaneously. From axiomatic derivations is has been shown that given the requirement that coarse- scale representations should correspond to true simplifications of fine scale structures, convolution with Gaussian kernels and Gaussian derivatives is singled out as a canonical class of image operators for the earliest stages of visual processing. Wiley Encyclopedia of Computer Science and Engineering 1st. Wiley Encyclopedia of Computer Science and. The Encyclopedia of Computer Science is the definitive reference in. An updated list of computer science and engineering research. Software Engineering Computer Science Special Topics. Encyclopedia of Cloud Computing. These image operators can be used as basis for solving a large variety of visual tasks, including feature detection, feature classification, stereo matching, motion descriptors, shape cues and image- based recognition. By complementing scale- space representation with a module for automatic scale selection based on the maximization of normalized derivatives over scales, early visual modules can be made scale invariant. In this way, visual modules will be able to automatically adapt to the unknown scale variations that may occur due to objects and substructures of varying physical size as well as objects with varying distances to the camera. An interesting similarity to biological vision is that the scale- space operators closely resemble receptive field profiles registered in neurophysiological studies of the mammalian retina and visual cortex. Sziranyi (eds). Proc. Fundamental Structural Properties in. Image and Pattern Analysis FSPIPA'9. Budapest, Hungary). September 6- 7, 1. CERN School of Computing. Egmond aan Zee, The Netherlands, 8- -2. September, 1. 99.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. Archives
October 2016
Categories |