Colour image segmentation with histogram and homogeneity histogram difference using evolutionary algorithms
- PDF / 4,991,021 Bytes
- 21 Pages / 595.276 x 790.866 pts Page_size
- 112 Downloads / 216 Views
ORIGINAL ARTICLE
Colour image segmentation with histogram and homogeneity histogram difference using evolutionary algorithms Sushil Kumar1 • Millie Pant2 • Manoj Kumar1 • Aditya Dutt3
Received: 30 April 2014 / Accepted: 3 April 2015 Springer-Verlag Berlin Heidelberg 2015
Abstract Due to the complexity of underlying data in a color image, retrieval of specific object features and relevant information becomes a complex task. Colour images have different color components and a variety of colour intensity which makes segmentation very challenging. In this paper we suggest a fitness function based on pixel-by-pixel values and optimize these values through evolutionary algorithms like differential evolution (DE), particle swarm optimization (PSO) and genetic algorithms (GA). The corresponding variants are termed GA-SA, PSO-SA and DE-SA; where SA stands for Segmentation Algorithm. Experimental results show that DE performed better in comparison of PSO and GA on the basis of computational time and quality of segmented image. Keywords Segmentation Evolutionary algorithms Colour image Homogeneity
1 Introduction Colour image segmentation is a complex but crucial task having application in several areas. Two most popular techniques for colour image segmentation include & Sushil Kumar [email protected] Millie Pant [email protected] 1
Department of Computer Science and Engineering, Amity School of Engineering and Technology, Amity University, Noida, India
2
Department of Applied Science and Engineering, Indian Institute of Technology Roorkee, Roorkee, India
3
JIIT, Noida, India
histogram-based methods [5] and neighbourhood based segmentation [6, 7]. Wen-Bing Tao et al. [26] proposed a GA based three level thresholding method for image segmentation. They partitioned the image in three basic parts dark, grey and white then implemented fuzzy region as Z-function, P-function and S-function respectively. GA’s are used to find an optimal solution for the fuzzy parameters avoiding the extra chromosomes resulting in a better feasibility. Hammouche et al. [27] proposed a wavelet transform method combined with genetic algorithm. This method reduced the original length of histogram using wavelet transform; GA selects the number of thresholds and values of thresholds in this reduced histogram. Multilevel thresholds are used for image segmentation with better performance. Minimum cross entropy thresholding (MCET) is a widely used simple and accurate method for image segmentation. In bi-level thresholding MCET works efficiently but for multi-level thresholding it encounters a very expensive computation. So Tang et al. [28] proposed a GA based fastening threshold selection in multilevel MCET. To reduce computational complexity a recursive programming is used for objective function. These values are used as a chromosome representation for GA which search several optimal multilevel threshold values. These values are very close to exhaustive search methods and show a better performance in terms of computational comp
Data Loading...
