An improved salient object detection algorithm combining background and foreground connectivity for brain image analysis. (October 2018)

• Record Type: Journal Article
• Authors: Kaur, Bhavneet; Sharma, Meenakshi; Mittal, Mamta; Verma, Amit; Goyal, Lalit Mohan; Hemanth, D. Jude
• Is Part Of: Computers & electrical engineering. Volume 71(2018)
• Page Start: 692
• Page End: 703
• Publication Date: 2018-10
• Subjects: Salient object detection -- Super-pixels -- Background connectivity -- Foreground connectivity -- Image segmentation -- Brain images; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2018.08.018
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Salient object detection has always been a valuable tool in the field of image processing. However, there are many challenges associated with the salient object detection algorithms. A new conceptually clear and robust algorithm for salient object detection has been proposed in this paper that has reconsidered some design varieties of the existing methods. Recent developments in the state-of-the-art have exploited either background information or estimation of foreground information. Therefore, an algorithm that covers both the boundary connectivity from background cues and foreground connectivity has been proposed in this paper. This proposed algorithm handles the limitations of existing object detection algorithms effectively and accurately by working on the edges of the objects or images. A thorough analysis has been carried out on the segmentation of brain Magnetic Resonance (MR) Images. Experimental results reveal that the proposed approach, Beaming Edge SALient (BE-SAL) has rendered the promising direction in the field of image analysis.