Modeling Bottom-Up Visual Attention Using Dihedral Group D4

Abstract

Abstract:In this paper, first, we briefly describe the dihedral group D 4 that serves as the basis for calculating saliency in our proposed model. Second, our saliency model makes two major changes in a latest state-of-the-art model known as group-based asymmetry. First, based on the properties of the dihedral group D 4 , we simplify the asymmetry calculations associated with the measurement of saliency. This results is an algorithm that reduces the number of calculations by at least half that makes it the fastest among the six best algorithms used in this research article. Second, in order to maximize the information across different chromatic and multi-resolution features, the color image space is de-correlated. We evaluate our algorithm against 10 state-of-the-art saliency models. Our results show that by using optimal parameters for a given dataset, our proposed model can outperform the best saliency algorithm in the literature. However, as the differences among the (few) best saliency models are small, we would like to suggest that our proposed model is among the best and the fastest among the best. Finally, as a part of future work, we suggest that our proposed approach on saliency can be extended to include three-dimensional image data.

Rail surface spalling detection based on visual saliency

“…As the edge positioning accuracy of the DTA algorithm is poor under complex illumination, we introduce another comparing algorithm, called MDTA, which applies DTA spalling detection after the rail surface positioning step of our algorithm. We also introduce a state‐of‐the‐art saliency‐based algorithm , called GBA. Since the GBA algorithm does not have the rail surface positioning step, we use our rail surface positioning result instead.…”

“…The establishment of the saliency map is the core part of the detection. Traditional visual saliency algorithms based on pixel contrast or group asymmetry are either sensitive to point targets or specific groups. Thus they are easily affected by grain noises or nonuniform illumination.…”

“…Chen et al . introduced a highly efficient local contrast measure algorithm in this model to improve the precision for finding small targets, and Sharma introduced a group‐based asymmetry algorithm to improve the computation speed of the saliency map. But these algorithms still have difficulty in distinguishing grain noises or nonuniform illumination from real spalling spots.…”

Dihedral Group D4—A New Feature Extraction Algorithm

“…As a first step, to reduce redundant information across the color channels, the input RGB color image I is de-correlated. In line with the study by Sharma [17], the color channels are de-correlated as follows: First, the matrix entries of I are reorganized to create a two-dimensional matrix M of size w × n, where n is the number of channels and w is the length of vector, i.e., the product of the length of matrix rows and columns. In the case of an RGB image, n = 3.…”

“…We investigate if the inherent properties of the complete set of elements pertaining to the D 4 group can form a natural basis for calculating a feature vector suitable for image discrimination. The D 4 group has shown promising results in various computer vision applications [12][13][14][15][16][17], which motivated us to use this group for our proposed algorithm.…”