A General Framework for Saliency Detection Methods
This work addresses the problem of fragmented understanding in saliency detection for computer vision researchers, but it is incremental as it organizes existing methods rather than introducing new techniques.
The paper tackles the lack of an abstract framework for summarizing existing saliency detection methods in image analysis by proposing a general framework with five main steps, and it compares the performance of different models within this framework to provide a comprehensive view for researchers.
Saliency detection is one of the most challenging problems in image analysis and computer vision. Many approaches propose different architectures based on the psychological and biological properties of the human visual attention system. However, there is still no abstract framework that summarizes the existing methods. In this paper, we offered a general framework for saliency models, which consists of five main steps: pre-processing, feature extraction, saliency map generation, saliency map combination, and post-processing. Also, we study different saliency models containing each level and compare their performance. This framework helps researchers to have a comprehensive view of studying new methods.