Salient Region Detection via Super Pixel, Histogram of Gradients

Abstract

Automatic salient object regions detection across images, without any prior information or knowledge of the contents of the corresponding images, enhances many computer vision and computer graphics applications. In the existing paper consider feature based on global and local features, which complement each other to compute a saliency map. The proposed approach automatically detects salient regions in an image dataset. The proposed algorithm based on applies super pixel segmentation appearance model. To improve the performance of saliency map estimation based on super pixels as features algorithm to resolve the saliency estimation from a trimap via a learning-based algorithm. Introduce a novel technique to automatically detect salient regions of an image via high-dimensional color transform. Our main idea is to represent a saliency map of an image as a linear combination of high-dimensional color space where salient regions and backgrounds can be distinctively separated. This is based on an observation that salient regions often have distinctive colors compared to the background in human perception, but human perception is often complicated and highly nonlinear. By mapping a low dimensional RGB color to a feature vector in a high-dimensional color space, we show that we can linearly separate the salient regions from the background by finding an optimal linear combination of color coefficients in the high-dimensional color space. Our high dimensional color space incorporates multiple color representations including RGB, CIELab, HSV and with gamma corrections to enrich its representative power. The experimental results on different benchmark datasets show that proposed approach is effective in comparison with the previous state-of-the-art saliency estimation methods.