Conference Paper

Object segmentation based on split and merge algorithm

Dept. of Comput. Sci. & Eng., Mil. Inst. of Sci. & Technol., Dhaka
DOI: 10.1109/TENCON.2008.4766802 Conference: TENCON 2008 - 2008 IEEE Region 10 Conference
Source: IEEE Xplore


Image segmentation is a feverish issue as it is a challenging job and most digital imaging applications require it as a preprocessing step. Among various algorithms, although split and merge (SM) algorithm is highly lucrative because of its simplicity and effectiveness in segmenting homogeneous regions, however, it is unable to segment all types of objects in an image using a general framework due to not most natural objects being homogeneous. Addressing this issue, a new algorithm namely object segmentation based on split and merge algorithm (OSSM) is proposed in this paper considering image feature stability, inter- and intra-object variability, and human visual perception. The qualitative analysis has been conducted and the segmentation results are compared with the basic SM algorithm and a shape-based fuzzy clustering algorithm namely object based image segmentation using fuzzy clustering (OSF). The OSSM algorithm outperforms both the SM and the OSF algorithms and hence increases the application area of segmentation algorithms.

  • [Show abstract] [Hide abstract]
    ABSTRACT: Segmenting homogeneous regions or objects in an image are very much demanding but challenging. Pattern based object segmentation using split and merge (PSM) was proposed to overcome the problems of basic split and merge (SM) algorithm, which is unable to segment properly all types of objects in an image due to huge variations among the objects in size, shape, intensity and orientation. Though the PSM algorithm has better performance than some other image segmentation algorithms, it is completely unable to segment the connected regions in an image and also has higher rate of shape distortion. Addressing these issues, a new algorithm namely object segmentation using block based patterns (OSP) is proposed in this paper considering multi stage merging technique. Experimental results show that the OSP algorithm is not only capable of segmenting connected regions in an image but also yield quite low shape distortion of the regions.
    No preview · Conference Paper · Feb 2009
  • [Show abstract] [Hide abstract]
    ABSTRACT: In order to split the image region which is interested in, a new split and merge algorithm is presented based on grey theory. This method uses grey correlation theory to make grey relational analysis for the split image. According to the inter-regional comprehensive correlation degree, it can guide whether the region should be merged. Just to analyze data of the borderline of the combined region. Compared to other methods, it is based on grey relational analysis of grey system, and does not require large amounts of data statistics, which is more simple and efficient. The experimental results prove that the algorithm can effectively extract the target area, and has a strong anti-noise capability. It is an effective new method for image segmentation.
    No preview · Article · Sep 2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: Uterine fibroids are benign tumors that can affect female patients during reproductive years. Magnetic resonance-guided focused ultrasound (MRgFUS) represents a noninvasive approach that uses thermal ablation principles to treat symptomatic fibroids. During traditional treatment planning, uterus, fibroids, and surrounding organs at risk must be manually marked on MR images by an operator. After treatment, an operator must segment, again manually, treated areas to evaluate the non-perfused volume (NPV) inside the fibroids. Both pre- and post-treatment procedures are time-consuming and operator-dependent. This paper presents a novel method, based on an advanced direct region detection model, for fibroid segmentation in MR images to address MRgFUS post-treatment segmentation issues. An incremental procedure is proposed: split-and-merge algorithm results are employed as multiple seed-region selections by an adaptive region growing procedure. The proposed approach segments multiple fibroids with different pixel intensity, even in the same MR image. The method was evaluated using area-based and distance-based metrics and was compared with other similar works in the literature. Segmentation results, performed on 14 patients, demonstrated the effectiveness of the proposed approach showing a sensitivity of 84.05 %, a specificity of 92.84 %, and a speedup factor of 1.56× with respect to classic region growing implementations (average values).
    No preview · Article · Nov 2015 · Medical & Biological Engineering