An Algorithmic Approach Based on CMS Edge Detection Technique for the Processing of Digital Images

An Algorithmic Approach Based on CMS Edge Detection Technique for the Processing of Digital Images

Kalyan Kumar Jena (Parala Maharaja Engineering College, India), Sasmita Mishra (Indira Gandhi Institute of Technology, India) and Sarojananda Mishra (Indira Gandhi Institute of Technology, India)
Copyright: © 2020 |Pages: 21
DOI: 10.4018/978-1-7998-0066-8.ch013

Abstract

Research in the field of digital image processing (DIP) has increased in the current scenario. Edge detection of digital images is considered as an important area of research in DIP. Detecting edges in different digital images accurately is a challenging work in DIP. Different methods have been introduced by different researchers to detect the edges of images. However, no method works well under all conditions. In this chapter, an edge detection method is proposed to detect the edges of gray scale and color images. This method focuses on the combination of Canny, mathematical morphological, and Sobel (CMS) edge detection operators. The output of the proposed method is produced using matrix laboratory (MATLAB) R2015b and compared with Sobel, Prewitt, Roberts, Laplacian of Gaussian (LoG), Canny, and mathematical morphological edge detection operators. The experimental results show that the proposed method works better as compared to other existing methods in detecting the edges of images.
Chapter Preview
Top

Introduction

DIP is an eminent area of research for different researchers. It is widely applied in many fields and can be considered as one of the rapidly growing technologies in the current scenario. Several concepts, techniques as well as applications of image processing are provided by Niblack (1986), Gonzalez et al. (1987), Green (1989), Jain (1989), Baxes (1994), Klette et al. (1996), Pitas (2000), Gonzalez et al. (2004), Annadurai (2007), Gonzalez et al.(2007), Petrou et al. (2010), Bhabatosh (2011), Solomon et al. (2011), Ekstrom (2012), Nayak et al. (2015), Burger et al. (2016), Nayak et al. (2016), Joshi (2018), Vyas et al.(2018), Majumder et al.(2018) and Bechtel et al.(2018), Nayak et al. (2018a), Nayak et al. (2018b), Nayak et al. (2018c), Nayak et al. (2018d), Nayak et al. (2018e), Nayak et al. (2018f), Nayak et al. (2018g), Nayak et al. (2019). In DIP, computer algorithms are used to perform processing on images (digital). Digital image is an image or picture which is represented digitally that means in group of combination of bits (0 or 1) or specifically called pixels. The digital image can be classified as gray scale, color and multispectral. JPEG, GIF, TIFF, PNG, BMP, etc. are the file types of digital image. DIP technologies can be used for manipulating the pixels in order to improve the quality of image, to draw out information digitally from the image, using computer algorithms. Pictorial information can be improved for human interpretation and the image data can be processed for storage, transmission as well as representation for autonomous machine perception by using DIP mechanism. Different techniques such as image edge detection, image preprocessing, image classification, image enhancement, image segmentation, feature extraction, pattern recognition, image projection, anisotropic diffusion, image editing, image filtering, image compression, etc. are used in DIP. Different applications of DIP includes image sharpening, image restoration, remote sensing, machine vision, color processing, pattern recognition, video processing, computer graphics arts, image encoding, forensic studies, etc. DIP can be applied in medical field, military applications, textiles industry, printing industry, film industry, etc. for several purposes. It can also be applied in radar and sonar. Different issues and challenges such as image edge detection, image segmentation, object recognition, image steganography, image enhancement, image restoration, image acquisition, image enhancement, image compression, image security, etc. are associated with DIP. This chapter is focused on the edge detection of digital images as it plays an important role in real world scenario. Edge detection is considered as an important technique of DIP to detect the edges of digital images. It is used to identify the sudden modification in pixels values relating to the adjacent pixels values in an image. Different concepts or techniques are provided by Scharcanski et al. (1997), Giannarou et al. (2005), Yu-qian et al. (2006), Xin et al. (2012), Goel et al. (2013), Gupta et al. (2013), Katiyar et al. (2014), Shanmugavadivu et al. (2014), Chaple et al. (2014), Wang et al. (2016), Othman et al. (2017), Kumar et al. (2017), Avots et al. (2018), Lahani et al. (2018), Alshorman et al. (2018), Hemalatha et al. (2018), Agrawal et al. (2018), Podder et al. (2018) and Halder et al. (2019) related to edge detection and processing of several images. It is a very challenging work for the DIP researchers to detect the edges in several images (digital) accurately. Different edge detection methods or operators such as Sobel, Prewitt, Roberts, LoG, Canny, etc. are used for detecting the edges in different images. However, no method works well under all conditions. In this chapter, an algorithmic approach is proposed to process the gray scale as well as color images for detecting the edges.

The main contribution in this chapter is stated as follows:

  • 1.

    A hybrid edge detection scheme is proposed in order to detect the edges of color and gray scale digital images using the quantitative combination of Canny, Morphological and Sobel edge detection operators.

  • 2.

    At first, Canny edge detection operator is applied in the original image. Afterwards, Morphological operator is applied and then Sobel edge detection operator is used to obtain the resultant image.

  • 3.

    The results of the proposed edge detection method are produced using MATLAB R2015b and compared with Sobel, Prewitt, Roberts, LoG, Canny and Mathematical Morphological edge detection methods.

Key Terms in this Chapter

Prewitt Operator: An edge detection operator that focuses on the computation of gradient approximation of the image intensity function.

CMS: Canny, mathematical morphological, and Sobel.

Roberts Operator: An edge detection operator that focuses on approximation of image gradient using discrete differentiation operation.

Canny Operator: An edge detection operator that focuses on multistage algorithm for detecting edges in several images.

Edge Detection: An image processing technique to find the objects boundaries within images.

Sobel Operator: An edge detection operator that focuses on two dimensional gradient measurements on several images and highlights the high spatial frequency regions which correspond to edges.

Digital Image Processing: Application of computer algorithms for performing image processing on several digital images.

Mathematical Morphology: A technique to analyze and process geometrical structures.

LoG Operator: An edge detection operator that focuses on zero crossings points in several images.

Complete Chapter List

Search this Book:
Reset