Object recognition

Figure 5 The C y-normalized cross-species exposure-response continuum for 7 across multiple pharmacology models [42]. A listed value (Cx) is the C iU (nM) affecting a response in assay X. RAM(r), rat radial arm maze DSR(nhp), nonhuman primate delayed spatial response task e-phys(r), rat electrophysiology model NOR(r), rat novel object recognition cGMP(m,r), mouse/rat cerebellar cGMP trem(nhp), nonhuman primate tremor rot(m), mouse rotarod.

A PDE10A inhibitor may also have the potential to treat the cognitive symptoms of schizophrenia. The principal evidence for this claim is papaverine reversal of a PCP-induced deficit in the EDID-set shifting assay in rats [35]. This assay translates into human behavior in the form of the Wisconsin Card Sorting Test (WCST). EDID-set shifting is a test of executive function, a measure in which schizophrenics have a robust deficit. It has also been shown recently that papaverine is efficacious in the Novel Object Recognition cognition assay [36]. 

Dementia generally involves an impairment in (1) memoiy and other cogntive abilities and (2) social and occupational functioning. The Diagnostic and Statisticai Manuai ofMentai Disorders (DSM-IV) defines dementia as a persistent deficit in memory and at least one other area of cognitive function language, praxis, object recognition, or executive... 

Object recognition and bubble stats. Bubble Recognition —> Volumes and Statistics (Proussevitch and Sahagian, 2001)... 

Color processing performs a very important role in computer vision. Many tasks become much simpler if the accurate color of objects is known. Accurate color measurement is required for color-based object recognition. Many objects can be distinguished on the basis of their color. Suppose that we have a yellow book and a red folder. We can distinguish the two easily because one is yellow and the other is red. But color can also be used in other areas of computer vision such as the computation of optical flow or depth from stereo based on color and shading. In this book, we will have an in-depth look at color perception and color processing. 

In developing color constancy algorithms, there are basically two roads to follow (Finlayson et al. 1994a). One is the accurate estimation of reflectances. This is of particular importance for object recognition. Object recognition becomes much easier if the reflectances are known. Another possibility would be to compute colors as they would appear under a canonical, e.g. white, illuminant. These are two different objectives and both are justified in their own right. In the first case (computation of reflectances), color... 

The human retina contains only three types of receptors, which respond mainly to light in the red, green, and blue parts of the spectrum. Suppose that we equip a digital camera with filters that model the response characteristics of the receptors found in the retina. If the processing done by the retina and by the brain were completely understood, we could compute the same color constant descriptors as are computed by the human brain. This method could then be used for object recognition based on color. 

Note that each color is now described by a one-dimensional scalar. For display purposes or object recognition based on color, the scalar can be transformed to the range [0, 1]. 

We will be using color-based object recognition to evaluate the quality of the color constancy algorithms. Where ground truth data is available, we can also compare the output of the different algorithms to the measured ground truth data. 

Berwick and Lee (1998) suggested the use of the following chromaticity space for object recognition. They simply choose one of the color channels and divide the remaining channels by the chosen color channel. Let c = [cr,cg, C, T be the color of an image pixel. The chromaticity space is then defined as... 

Figure 13.5 Experimental setting that is used to test the performance of color constancy algorithms. Each input image from the database is processed by a color constancy algorithm. The processed images are then used for object recognition.

Berwick D and Lee SW 1998 A chromaticity space for specularity, illumination color- and illumination pose-invariant 3-d object recognition Sixth International Conference on Computer Vision. Narosa Publishing, pp. 165-170. 

Finlayson GD, Chatterjee SS and Funt B V 1995 Color angle invariants for object recognition Proceedings of the Third IS T/SID Color Imaging Conference Color Science, Systems and Applications, Nov. 7-10. The Radisson Resort, Scottsdale, Arizona, pp. 44-47. 

Schiele B and Crowley JL 1996 Object recognition using multidimensional receptive field histograms In Fourth European Conference On Computer Vision, Cambridge, UK, April 14-18 (eds. Buxton B and Cipolla R), pp. 610-619. Springer-Verlag, Berlin. 

---