Quantum Behaved Swarm Intelligent Techniques for Image Analysis: A Detailed Survey

Quantum Behaved Swarm Intelligent Techniques for Image Analysis: A Detailed Survey

Sandip Dey (Camellia Institute of Technology, India), Siddhartha Bhattacharyya (RCC Institute of Information Technology, India) and Ujjwal Maulik (Jadavpur University, India)
DOI: 10.4018/978-1-5225-0788-8.ch034
OnDemand PDF Download:
$37.50

Abstract

In this chapter, an exhaustive survey of quantum behaved techniques on swarm intelligent is presented. The techniques have been categorized into different classes, and in conclusion, a comparison is made according to the benefits of the approaches taken for review. The above-mentioned techniques are classified based on the information they exploit, for instance, neural network related, meta-heuristic and evolutionary algorithm related, and other distinguished approaches are considered. Neural Network-Based Approaches exhibit a few brain-like activities, which are programmatically complicated, for instance, learning, optimization, etc. Meta-Heuristic Approaches update solution generation-wise for optimization, and the approaches differ based on the problem definition.
Chapter Preview
Top

Introduction

Image segmentation (Jahne, 1993; Jain, 1989) is a fundamental and significant technique in image processing. This technique is used to segregate an image into several non-overlapping consequential and homogeneous regions. The basic property of image segmentation is that each segmented region must share some common features of image, such as, texture, color or pixel intensity. Occasionally, the analogous grouping is known as clusters. A basic prior knowledge or even a presupposition about the image may be very useful for successful classification. This knowledge may help ones to find the appropriate features for this classification. Mathematically, let an image is separated into p number of homogeneous, non-overlapping sub-regions viz., . Each pixel in image must be allocated to only one for . According to the rule of image segmentation, each must satisfy the following properties:

(1)
(2)
(3)

In many occasions, segmentation was proved to be a useful and significant stair in image analysis. A good segmentation can reduce the computational overhead for the subsequent phases in image analysis. Segmentation is very useful for detecting and extracting the specific features of object from both graphic and nonnumeric data set. Segmentation has been successfully employed in different fields of application, such as, pattern recognition, surveillance, machine learning, medical sciences, artificial intelligence, economics, defense remote sensing to name a few. Segmentation techniques are generally classified into two classes viz., feature space based and image domain based (Lucchese & Mitra, 2001). Thresholding acts as a popular tool in image segmentation (Hammouche et al., 2008). One popular example of the former technique may be histogram thresholding whereas, region growing and merging, splitting and merging, edge detection based techniques may be some popular examples for later category (Lucchese & Mitra, 2001). Based on the characteristics of image pixel in its neighboring areas like discontinuity and resemblance, some segmentation techniques have been presented in (Freixenet et al., 2002). A review in this literature has been presented in (Gonzalez & Woods, 2002). Later, Bhattacharyya presented a detailed survey on different image thresholding and segmentation techniques based on classical and non-classical approaches (Bhattacharyya, 2011a).

Complete Chapter List

Search this Book:
Reset