Abstract
Salient region detection is useful for applications like image segmentation, adaptive compression, and object recognition. In this paper, a novel approach is proposed to detect salient region which combines image pyramid and region property. The proposed salient region detection approach contains the three principal steps, multi-scale image abstraction, salient region detection in a single scale, saliency map fusion under multiple scales. Then image reconstruction is done after removal of detected salient regions using exemplar-based image inpainting. The results of this method were evaluated on the two publicly available databases, including MSRA-1000 and CMU Cornell iCoseg datasets. The experimental results shows that our method consistently outperforms two existing salient object detection methods, yielding better precision and recall rates. Also, better structural similarity index is also obtained in our proposed exemplar-based image inpainting.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
