An Advanced Approach to Detect Edges of Digital Images for Image Segmentation

An Advanced Approach to Detect Edges of Digital Images for Image Segmentation

Shouvik Chakraborty (University of Kalyani, India)
DOI: 10.4018/978-1-7998-2736-8.ch004

Abstract

Image segmentation has been an active topic of research for many years. Edges characterize boundaries, and therefore, detection of edges is a problem of fundamental importance in image processing. Edge detection in images significantly reduces the amount of data and filters out useless information while preserving the important structural properties in an image. Edges carry significant information about the image structure and shape, which is useful in various applications related with computer vision. In many applications, the edge detection is used as a pre-processing step. Edge detection is highly beneficial in automated cell counting, structural analysis of the image, automated object detection, shape analysis, optical character recognition, etc. Different filters are developed to find the gradients and detect edges. In this chapter, a new filter (kernel) is proposed, and the compass operator is applied on it to detect edges more efficiently. The results are compared with some of the previously proposed filters both qualitatively and quantitatively.
Chapter Preview
Top

Introduction

The problem of image segmentation is well-known and addressed by many scientists because it plays an important role in the various applications based on the image analysis and the computer vision systems. But, still it is considered being one of the most difficult and challenging tasks in image processing and object recognition, and determines the quality of final results of the image analysis. In the domain of image processing (Acharya & Ray, 2005; Bhabatosh, 2011; Gonzalez & Woods, 2008; Hore et al., 2016; Hore, Chatterjee, Chakraborty, & Shaw, n.d.) and image analysis (Al-amri, Kalyankar, & D., 2010; Huang, Wu, & Fan, 2003; Mansoor et al., 2015; Rampun et al., 2019), the interpretation is frequently required and dependent on the difference between foreground and the background. When the human visual system is mimicked by the computer algorithms, several problems may arise. Segmentation is process that divides an image into its various constituent regions or separately highlight different objects. The number of segments or the depth of the hierarchical division is dependent on the subject. That is, segmentation process must stop when the desired segments are achieved or the constituting of objects are separated (Chakraborty, Roy, & Hore, 2016; Palus, n.d.). The process of segmentation must be carefully performed to avoid over or under segmentation related problems (Barnard, Duygulu, Guru, Gabbur, & Forsyth, 2003; Gao, Mas, Kerle, & Pacheco, 2011).

Edge detection is one of the most primitive tools and frequently used in many of the image processing applications to generate some useful information from the images and often used as the pre-processing step in feature extraction and object recognition (Lyu, Fu, Hu, & Liu, 2019; Madireddy et al., 2019). The edge detection have been used by different real life applications like object recognition (Shin, Goldgof, & Bowyer, 2001), target tracking (Boumediene, Ouamri, & Dahnoun, 2007; Etienne-Cummings, Spiegel, Mueller, & Zhang, 1997; Ould-Dris, Ganoun, & Canals, 2006), segmentation (Kaganami & Beiji, 2009; Xiaohan et al., 1992), structural analysis (Kanitkar, Bharti, & Hivarkar, 2011; Luo, Higgs, & Kowalik, 1996), data compression (Deepu & Lian, 2015; Hsu, 1993), biomedical image analysis (Chakraborty, Mali, Banerjee, et al., 2018; Chakraborty, Mali, Chatterjee, Anand, et al., 2018; S. Chakraborty, Mali, Chatterjee, Banerjee, Roy, et al., 2018; Chakraborty, Mali, Chatterjee, Banerjee, Sah, et al., 2018; Chakraborty, Chatterjee, Ashour, Mali, & Dey, 2017; Chakraborty et al., 2018; Chakraborty, Chatterjee, Das, & Mali, 2020; Shouvik Chakraborty & Mali, 2018; Shouvik Chakraborty, Mali, Chatterjee, Banerjee, Mazumdar, Debnath, et al., 2017; Chakraborty, Mali, Chatterjee, Banerjee, Roy, Dutta, et al., 2017; Liu et al., 2014; Pacelli, Loriga, Taccini, & Paradiso, 2006; Roy et al., 2018), cryptographic analysis (Chakraborty, Seal, Roy, & Mali, 2016; Mali, Chakraborty, & Roy, 2015; Mali, Chakraborty, Seal, & Roy, 2015; Roy, Chakraborty, et al., 2019; Roy, Mali, et al., 2019; Seal, Chakraborty, & Mali, 2017) and also help for pattern matching and reconstruction, such as image reconstruction and so on. Edge detection is an active area of research as it facilitates higher level image analysis. In image processing and computer vision, the edge detection methods are focused to find the different sharp changes in the intensity in the image so that some essence of the physical and geometrical features of objects can be extracted. In general, three broad steps associated with the Edge detection process and the steps are as follows:

Key Terms in this Chapter

Validation Measures: These are some parameters which are used to validate a segmentation procedure.

Kernel: Kernel is generally a small matrix which used to apply different types effects on the image.

Image Gradient: Image gradient represent a change in the image intensity or color in a specific direction.

Image Segmentation: Image segmentation is a method to individually identify each constituting segments in an image.

Edge Detection: Edge detection is a process to determine the contours of various objects in an image.

Image Analysis: It is the process by which useful information are extracted from an image and interpreted for further application.

Object Detection: It is a method to locate and detect different objects from digital images and digital videos.

Complete Chapter List

Search this Book:
Reset