A Novel Approach to Capture Salient Part from JPEG Image
Radhika P. Fuke1, M. V. Sarode2

1Ku. Radhika P. Fuke, Department of Information Technology, Amravati, University, Sipna C.O.E.T, Amravati (Maharashtra), India.
2Prof. M.V. Sarode, Department of Computer Science and Engineering, Amravati University, Sipna C.O.E.T, Amravati (Maharashtra), India.
Manuscript received on 12 March 2013 | Revised Manuscript received on 21 March 2013 | Manuscript Published on 30 March 2013 | PP: 230-232 | Volume-2 Issue-4, March 2013 | Retrieval Number: D0565032413/13©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Salient region detection in images is very useful for image processing applications like image segmentation, object detection and recognition. In this paper, an improved approach to detect salient region is presented Using saliency detection technique. Existing saliency detection models are built in the uncompressed domain. Since most images over Internet are typically stored in the compressed domain such as joint photographic experts group (JPEG), we propose a novel saliency detection model in the compressed domain in this paper. The intensity, color, and texture features of the image are extracted in the JPEG bit-stream. Detection of irregular visual patterns in images and in video sequences is useful for a variety of tasks. Detecting suspicious behaviors or unusual objects is important for surveillance and monitoring. Identifying spatial saliency in images is useful for quality control and automatic inspection.
Keywords: Compressed Domain, Image Retargeting, Joint Photographic Experts Group (JPEG), Saliency Detection, Denoising.

Scope of the Article: Image Security