Salient Region Detection and Segmentation

Abstract

Abstract. Detection of salient image regions is useful for applications like image segmentation, adaptive compression, and region-based image retrieval. In this paper we present a novel method to determine salient regions in images using low-level features of luminance and color. The method is fast, easy to implement and generates high quality saliency maps of the same size and resolution as the input image. We demonstrate the use of the algorithm in the segmentation of semantically meaningful whole objects from digital images.

Fusing generic objectness and visual saliency for salient object detection

“…Most saliency detection methods [1,2,5,7,8,9,11,15] consider only the low-level features. They basically compute the saliency values by a center-surround approach [2].…”

“…In [7], Harel et al further consider the appearance difference and the geometric distance of each pixel pair, and then use a graph-based method to estimate the saliency. In methods of the second group [1,2,5,8,9], the saliency estimation would require comparing each pixel with a large area or even the whole image. The technique by Hou and Zhang [8] analyzes the frequency domain of an image.…”

“…Instead of computing so many differences, Achanta et al [1,2] use an average operation to summarize the information of the surrounding area of a pixel so that its saliency value can be determined based on the summarized information. Among the aforementioned techniques [1,2,5,7,8,9,11,15], pixels are essentially processed independently. Since pixels near the edges are quite distinct with respect to those in other areas of an image, methods of this kind often assign higher saliency values to them.…”

Visual Saliency Weighting and Cross-Domain Manifold Ranking for Sketch-Based Image Retrieval

“…A visual saliency map, which approximates visual attention of human, is used for image segmentation [16], object detection [17], and other applications. Recently, Yang et al [8] proposed a graph-based saliency detection method called Manifold Ranking-based Saliency Detection (MRSD).…”

Fast and Efficient Saliency Detection Using Sparse Sampling and Kernel Density Estimation

“…shows this concept. Achanta et al [2] provides us such a sample. They measured the color difference of a center pixel and average color in its immediate surrounding.…”