A computational feature binding model of human texture perception

Abstract

We present a computational model for human texture perception which assigns functional principles to the Gestalt laws of similarity and proximity. Motivated by early vision mechanisms, in a first step local texture features are extracted by utilizing multi-scale filtering and non-linear spatial pooling. In the second stage, features are grouped according to the spatial feature binding model of the Competitive Layer Model (CLM) (Wersing, Steil, & Ritter, 2001). The CLM uses cooperative and competitive interactions in a recurrent network, where binding is expressed by the layer-wise coactivation of feature-representing neurons. The Gestalt law of similarity is expressed by a non-euclidean distance measure in the abstract feature space with proximity being taken into account by a spatial component. To choose the stimulus dimensions which allow the most salient similarity-based texture segmentation, the feature similarity metrics is reduced to the directions of maximum variance. We show that our combined texture feature extraction and binding model performs segmentation in strong conformity with human perception. The examples range from classical microtextures and Brodatz textures to other classical Gestalt stimuli, which offer a new perspective on the role of texture for more abstract similarity grouping.

Heading Homing Simulation System Based on Image Intelligent Recognition

“…Figure 3 is a schematic diagram of window, where I, i1…represent the regions in the window. The initial position of each window is located at the right end of each line's pixel, which moves to the left after algorithm and turns into Window' until the left end [13][14][15][16]. The algorithm procedures are as follows:…”

Engineering Cost Evaluation Model Based on Multi Dimension Entropy and Intelligent Algorithm

“…G is also a rough variable after calculation and its mean value and dispersion are respectively ( 1 3 ) It can be learned from interval reliability analysis model [9][10][11][12][13] that, in case of…”

Performance Evaluation Model of Park Based on Intelligent Algorithm

“…Commonly used evaluation standards lay one-sided emphasis on importance, quantifiability, procurability and understandability while connotation of relevance similar to strategy and relevance and levels of value enhancement and other principles as important as enterprise performance evaluation implementation are not accurately decided [4][5][6][7]. Even if these principles are considered in evaluation process to some extent, they are not implemented in position resulting in accuracy decrease in performance evaluation result [8][9][10].…”