Peter Kruizinga

Comparison of texture features based on Gabor filters

Texture features that are based on the local power spectrum obtained by a bank of Gabor filters are compared. The features differ in the type of nonlinear post-processing which is applied to the local power spectrum. The following features are considered: Gabor energy, complex moments, and grating cell operator features. The capability of the corresponding operators to produce distinct feature vector clusters for different textures is compared using two methods: the Fisher (1923) criterion and the classification result comparison. Both methods give consistent results. The grating cell operator gives the best discrimination and segmentation results. The texture detection capabilities of the operators and their robustness to nontexture features are also compared. The grating cell operator is the only one that selectively responds only to texture and does not give false response to nontexture features such as object contours.

Nonlinear operator for oriented texture

Texture is an important part of the visual world of animals and humans and their visual systems successfully detect, discriminate, and segment texture. Relatively recently progress was made concerning structures in the brain that are presumably responsible for texture processing. Neurophysiologists reported on the discovery of a new type of orientation selective neuron in areas V1 and V2 of the visual cortex of monkeys which they called grating cells. Such cells respond vigorously to a grating of bars of appropriate orientation, position and periodicity. In contrast to other orientation selective cells, grating cells respond very weakly or not at all to single bars which do not make part of a grating. Elsewhere we proposed a nonlinear model of this type of cell and demonstrated the advantages of grating cells with respect to the separation of texture and form information. In this paper, we use grating cell operators to obtain features and compare these operators in texture analysis tasks with commonly used feature extracting operators such as Gabor-energy and co-occurrence matrix operators. For a quantitative comparison of the discrimination properties of the concerned operators a new method is proposed which is based on the Fisher (1923) linear discriminant and the Fisher criterion. The operators are also qualitatively compared with respect to their ability to separate texture from form information and their suitability for texture segmentation.

Computational models of visual neurons specialised in the detection of periodic and aperiodic oriented visual stimuli : Bar and grating cells

Abstract.Computational models of periodic- and aperiodic-pattern selective cells, also called grating and bar cells, respectively, are proposed. Grating cells are found in areas V1 and V2 of the visual cortex of monkeys and respond strongly to bar gratings of a given orientation and periodicity but very weakly or not at all to single bars. This non-linear behaviour, which is quite different from the spatial frequency filtering behaviour exhibited by the other types of orientation-selective neurons such as the simple cells, is incorporated in the proposed computational model by using an AND-type non-linearity to combine the responses of simple cells with symmetric receptive field profiles and opposite polarities. The functional behaviour of bar cells, which are found in the same areas of the visual cortex as grating cells, is less well explored and documented in the literature. In general, these cells respond to single bars and their responses decrease when further bars are added to form a periodic pattern. These properties of bar cells are implemented in a computational model in which the responses of bar cells are computed as thresholded differences of the responses of corresponding complex (or simple) cells and grating cells. Bar and grating cells seem to play complementary roles in resolving the ambiguity with which the responses of simple and complex cells represent oriented visual stimuli, in that bar cells are selective only for form information as present in contours and grating cells only respond to oriented texture information. The proposed model is capable of explaining the results of neurophysiological experiments as well as the psychophysical observation that the perception of texture and the perception of form are complementary processes.

Computational model of dot-pattern selective cells

Abstract. A computational model of a dot-pattern selective neuron is proposed. This type of neuron is found in the inferotemporal cortex of monkeys. It responds strongly to groups of dots and spots of light intensity variation but very weakly or not at all to single dots and spots that are not part of a pattern. This non-linear behaviour is quite different from the spatial frequency filtering behaviour exhibited by other neurons that react to spot-shaped stimuli, such as neurons with centre-surround receptive field profiles found in the lateral geniculate nuclei and layer 4Cβ of V1. It is implemented in the proposed computational model by using an AND-type non-linearity to combine the responses of centre-surround cells. The proposed model is capable of explaining the results of neurophysiological experiments as well as certain psychophysical observations.

Optical flow applied to person identification

Abstract We propose to compute a vector field, similar to the optical flow computed between successive frames of an image sequence, which maps optimally (in a certain sense) one face image onto another face image. A cost of the mapping is computed and used to quantify the dissimilarity between the two images. The technique is applied to the problem of person identification by comparing an input face image to all face images prestored in a database. The method was implemented on the Connection Machine CM-5 of the University of Groningen1 in the data-parallel programming model.

Grating cell operator features for oriented texture segmentation

The performance of two well-known texture operators (based on Gabor-energy and the cooccurrence matrix) is compared with the performance of a new, biologically motivated texture operator, the grating cell operator, previously proposed by the authors (1995, 1997). The comparison is made using a new quantitative method, based on the Fisher criterion (1923). The results show the clear superiority of the new operator in oriented texture problems.

A Computational Model of Periodic-Pattern-Selective Cells

A computational model of so-called grating cells is proposed. These cells, found in areas V1 and V2 of the visual cortex of monkeys, respond strongly to bar gratings of a given orientation and periodicity but very weakly or not at all to single bars. This non-linear behavior is quite different from the spatial frequency filtering behavior exhibited by the other types of orientation selective cells. It is incorporated in the proposed model by using an AND-like non-linearity to combine the responses of simple cells and compute the activities of so-called grating subunits which are subsequently summed up. The parameters of the model are adjusted to reproduce the results measured by neurophysiologists with different visual stimuli. The proposed computational model of a grating cell is used to compute the collective activation of sets of such cells, referred to as cortical images, induced by natural visual stimuli. On the basis of the results of such simulations we speculate about the possible role of grating cells in the visual system and demonstrate the usefulness of grating cell operators for some computer vision tasks, such as automatic face recognition and document processing.

Large scale natural vision simulations

Abstract A computationally intensive approach to pattern recognition in images is developed and applied to face recognition. Similarly to previous work, we compute functional inner products of a two-dimensional input signal (image) with a set of two-dimensional Gabor functions which fit the receptive fields of simple cells in the primary visual cortex of mammals. The proposed model includes nonlinearities, such as thresholding, orientation competition and lateral inhibition. The output of the model is a set of cortical images each of which contains only edge lines of a particular orientation in a particular light-to-dark transition direction. In this way the information of the original image is split into different channels. The cortical images are used to compute a lower-dimension space representation for object recognition. The method was implemented on the Connection Machine CM-5 1 and achieved a recognition rate of 97% when applied to a large database of face images.

Person identification based on multiscale matching of cortical images

A set of so-called cortical images, motivated by the function of simple cells in the primary visual cortex of mammals, is computed from each of two input images and an image pyramid is constructed for each cortical image. The two sets of cortical image pyramids are matched synchronously and an optimal mapping of the one image onto the other image is determined. The method was implemented on the Connection Machine CM-5 of the University of Groningen in the data-parallel programming model and applied to the problem of face recognition.

Biologically Motivated Approach to Face Recognition

A biologically motivated compute intensive approach to computer vision is developed and applied to the problem of face recognition. The approach is based on the use of two-dimensional Gabor functions that fit the receptive fields of simple cells in the primary visual cortex of mammals. A descriptor set that is robust against translations is extracted by a global reduction operation and used for a search in an image database. The method was applied on a database of 205 face images of 30 persons and a recognition rate of 94% was achieved.