A unified framework for exploiting color coefficients for salient object detection

With many applications in high level scene understanding, salient object detection is an important objective. In addition, this topic has received significant attention recently. This work proposes techniques that exploit the role of color spaces for addressing two important challenges in relation to salient object detection. The autonomous identification of a color space by which to carry out the processing has always been of prime importance to most image analysis tasks and this is equally so in relation to saliency detection. To address this challenge, a new adaptive color space selection method is proposed, here, which autonomously identifies the color space that is locally the most appropriate for saliency detection on an image by image basis. The color channels within this identified local color space are aggregated using joint l2, 1-norm minimization in order to determine feature importance and also to achieve feature selection leaning. A process relevant to saliency detection is multi-modality feature fusion, in which multiple features and color spaces are used in combination to capture the saliency aspects of an image/region. To implement this second process, a new technique for the region based optimal combination of feature modalities is introduced. The results of the rigorous experimental evaluations demonstrate the effectiveness of the adaptive color space selection and also for the region based optimal combination methods in comparison to 13 other state-of-the-art saliency methods and all in relation to three benchmark datasets. The efficacy of the proposed color space selection and region based combination methods is further validated by examining their ability to select appropriate color spaces for, and successfully aggregate the results of, up to five benchmark methods.