Salient Region Detection based on Frequency-tuning and Region Contrast

Abstract

Abstract-Frequency-tuned saliency detection analyzes image saliency from the perspective of frequency domain and fully combines image segmentation method, which outputs welldefined boundaries of salient objects. However, the method ignores spatial relationships across image parts. This paper proposes an improved saliency detection method on the basis of the frequency-tuned method. In this method, we first segment the input image into regions and then analyze the image from the frequency domain. After that, we preprocess it using Gaussian filter to eliminate noise and coding artifacts. For each region, we can get saliency map in region-level based on region contrast. Finally, salient regions are selected by "winner-take-all" (WTA) neural network and Inhibition of Return(IOR) mechanism. The proposed salient region detection algorithm combines the virtues of frequency-tuning and region contrast. The experimental results show the feasibility and validity of this algorithm.

Robustness Improvement of Visual Templates Matching Based on Frequency-Tuned Model in RatSLAM

“…Existing attention mechanism models can be divided into bottom-up models and top-down models. The method of extracting salient regions used in this paper is a bottom-up visual attention model, known as the saliency model (Marques et al, 2006 ; Fu et al, 2014 ). The saliency model is data-driven, such that the influence of human judgement is not considered during image selection.…”