Hershey, Pennsylvania
New York, New YorkBeijing, China
Comparative Analysis of Proposed Artificial Neural Network (ANN) Algorithm With Other Techniques

Comparative Analysis of Proposed Artificial Neural Network (ANN) Algorithm With Other Techniques

Deepak Chatha (Department of Computer Science and Engineering, Panipat Institute of Engineering and Technology, Samalkha, India), Alankrita Aggarwal (Department of Computer Science and Engineering, Panipat Institute of Engineering and Technology, Samalkha, India), and Rajender Kumar (Department of Computer Science and Engineering, Panipat Institute of Engineering and Technology, Samalkha, India)
Copyright: © 2020 |Pages: 7
DOI: 10.4018/IJSPPC.2020010103
OnDemand:
(Individual Articles)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

The mortality rate among women is increasing progressively due to cancer. Generally, women around 45 years old are vulnerable from this disease. Early detection is hope for patients to survive otherwise it may reach to unrecoverable stage. Currently, there are numerous techniques available for diagnosis of such a disease out of which mammography is the most trustworthy method for detecting early cancer stage. The analysis of these mammogram images are difficult to analyze due to low contrast and nonuniform background. The mammogram images are scanned and digitized for processing that further reduces the contrast between Region of Interest and background. Presence of noise, glands and muscles leads to background contrast variations. Boundaries of suspected tumor area are fuzzy & improper. Aim of paper is to develop robust edge detection technique which works optimally on mammogram images to segment tumor area. Output results of proposed technique on different mammogram images of MIAS database are presented and compared with existing techniques in terms of both Qualitative & Quantitative parameters.
Article Preview
Top

Evaluate The Performance Of Ann With Existing Techniques

Quantitative Comparison

The Qualitative comparison is basically done by visual inspection. The few parameters which are kept in mind while declaring best technique among different edge detector are: True Edges, Thin Boundaries, Lost detail, Noise and Broken Edges.

Top

Test Image 1

The Qualitative comparison of Artificial Neural Network (ANN) technique with other existing techniques for test image 1 is shown in Figure 1. It is clear by visual inspection that Artificial Neural Network (ANN) algorithm gives best results among all other competing detectors as it is manifesting maximum accurate tumor details with minimum structural loss. Also, it is observed that there is high continuity among all edge pixels along with almost true and thin edges.

Figure 1.

Edge detection of test image1: (a) Original; (b) Sobel; (c) Robert; (d) Prewitt; (e) Canny; (f) Artificial Neural Network (ANN)

IJSPPC.2020010103.f01
Table 1.
Quantitative analysis of test image 1
ijsppc.2020010103.g01

The Quantitative results are color coded to differentiate top three performing technique among others as shown in Table 2.

Table 2.
Quantitative results
ijsppc.2020010103.g02

Complete Article List

Search this Journal:
Reset
Volume 16: 1 Issue (2025): Forthcoming, Available for Pre-Order
Volume 15: 1 Issue (2023)
Volume 14: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 13: 4 Issues (2021)
Volume 12: 4 Issues (2020)
View Complete Journal Contents Listing