Fast Interactive Superpixel Based Image Region Generation
Dinesh Naik1, Muhammed Shameem P.K2
1Dinesh Naik, Department of Information Technology, National Institute of Technology Karnataka, Surathkal Mangalore, India.
2Muhammed Shameem P.K, Department of Information Technology, National Institute of Technology Karnataka, Surathkal Mangalore, India.
Manuscript received on 02 June 2019 | Revised Manuscript received on 10 June 2019 | Manuscript published on 30 June 2019 | PP: 2963-2969 | Volume-8 Issue-8, June 2019 | Retrieval Number: H7423068819/19©BEIESP
Open Access | Ethics and 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: Image Segmentation has always been a problem of interest and the challenging task in the field of the computer-based vision system. It plays a vital role in the field of object detection and recognition. Identifying with separating a part of the interest from a complicated image is easy for the human vision system, but the same is cumbersome to automate. The proposed work is a novel combined technology for fast segmentation of foreground (area of interest) out of an image which possesses a background and other complications. This work utilizes the latest industrial class technologies with advanced algorithms. Our approach remarkably increased the performance by working on a super-pixelated image rather than a normal n x n pixel image. The proposed work is mainly focused on interactive segmentation. This could be actively used in fields like the medical analysis. Our segmentation technique is a binary segmentation where it classifies pixels into two distinct sets. The proposed scheme is experimentally shown to compare favorably with contemporary interactive image segmentation schemes when applied to colored and gray-scale images.
Keyword: Boykov-Kolmogorov algorithm, Computer Vision, CIDE2000, CIELab, Foreground Extraction, Image Segmentation, Image separation, Super-pixels, Min-cut/Max-flow algorithm.
Scope of the Article: Vision-based applications.