Comparative Analysis of Edge Detection Methods using Deep Learning

Comparative Analysis of Edge Detection Methods using Deep Learning

© 2023 by IJETT Journal
Volume-71 Issue-2
Year of Publication : 2023
Author : Dipmala Salunke, Bhushan Dhamankar, Sairaj Chidrawar, Rohit Kangule, Shrikrushnakumar Sondge, Sumit Deshmukh
DOI : 10.14445/22315381/IJETT-V71I2P208

How to Cite?

Dipmala Salunke, Bhushan Dhamankar, Sairaj Chidrawar, Rohit Kangule, Shrikrushnakumar Sondge, Sumit Deshmukh, "Comparative Analysis of Edge Detection Methods using Deep Learning," International Journal of Engineering Trends and Technology, vol. 71, no. 2, pp. 61-70, 2023. Crossref,

Computer vision is a subset of artificial intelligence (AI), which is used to extract meaningful data from images. It provides different features such as object detection, edge detection, image classification etc. Edge detection is very useful in industries like the civil industry, agriculture industry, autonomous vehicles, facial recognition, manufacturing, etc. Using opencv, we can use different edge detection operators to get object edges and detect objects. The main problem with dimension detection is the edges. Edges are one of the important characteristics of the image, which can provide us with very useful information about the object. Though edge detection is a very old topic, there is still no solid study to explain which edge detection method will work best for dimension detection. So here is a comparative analysis to find which edge detection algorithm performs best for dimension detection to locate excellent edges that will generate decent contours. All edge detection systems' effectiveness needs to be evaluated. The edges of the image may be extracted using a variety of edge detection algorithms, and the performance can be judged using metrics like signal-to-noise ratio (SNR), structural similarity index measure (SSIM), entropy, peak signal-to-noise ratio (PSNR), mean squared error (MSE). In this paper, in addition to first derivative operators like sobel, robert, and prewitt, gaussian-based algorithms, the laplacian of gaussian, and the canny edge detector have also been taken into consideration. It is experimentally observed that the sobel operator is performing better than others, with an average SNR value of 1.1730.

Opencv, Edge detection, Dimension detection, Image segmentation, Prewitt, Sobel, Laplacian of gaussian, Canny, Robert.

[1] Chen Feng et al., "Image Edge Detection Based on Improved Local Fractal Dimension," Fourth International Conference on Natural Computation, pp. 640-643, 2008. Crossref,
[2] Sheetal Israni, and Swapnil Jain, "Edge Detection of License Plate Using Sobel Operator," International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT), pp. 3561-3563, 2016. Crossref,
[3] Hanmin Ye, Bin Shen, and Shili Yan, "Prewitt Edge Detection Based on BM3D Image Denoising," IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), pp. 1593-1597, 2018. Crossref,
[4] Miftahul Jannah, and Adli Abdillah Nababan, “Harfu Jar Detection System in Al-Quran Using Pierce Similarity Algorithm as a Basic Learning Media of Arabic Language,” 3rd International Conference on Mechanical, Electronics, Computer, and Industrial Technology (MECnIT), pp. 349-354, 2020. Crossref,
[5] Shweta Pardeshi, Pranali Pawar, and Nikhil Raj, “Real Time Object Measurement,” International Journal of Engineering Science and Computing, vol. 11, no. 2, 2021.
[6] Geng Xin, Chen Ke, and Hu Xiaoguang, "An Improved Canny Edge Detection Algorithm for Color Image," IEEE 10th International Conference on Industrial Informatics, pp. 113-117, 2012. Crossref,
[7] Theodora Sanida, Argyrios Sideris, and Minas Dasygenis, "A Heterogeneous Implementation of the Sobel Edge Detection Filter Using OpenCL," 2020 9th International Conference on Modern Circuits and Systems Technologies (MOCAST), pp. 1-4, 2020 Crossref,
[8] Li Cao, Yi Jiang, and Mingfeng Jiang, "Automatic Measurement of Garment Dimensions Using Machine Vision," International Conference on Computer Application and System Modeling (ICCASM), pp. V9-30-V9-33, 2010. Crossref,
[9] Yi Zhang, "Edge Detection Algorithm of Image Fusion Based on Improved Sobel Operator," IEEE 3rd Information Technology and Mechatronics Engineering Conference (ITOEC), pp. 457-461, 2017. Crossref,
[10] Shaveta Malik, and Tapas Kumar, “Various Edge Detection Techniques on Different Categories of Fish,” International Journal of Computer Applications, vol. 135, no. 7, pp. 6-11, 2016. Crossref,
[11] Yolanda Gabyriela Ferandji, Diaraya, and Armin Lawi, "Performance Comparison of Image Edge Detection Operators for Lontara Sanskrit Scripts," 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT), pp. 241-244, 2018. Crossref,
[12] P. Prathusha, S. Jyothi, and D. M. Mamatha, "Enhanced Image Edge Detection Methods for Crab Species Identification," International Conference on Soft-computing and Network Security (ICSNS), pp. 1-7, 2018. Crossref,
[13] Akansha Jain et al., "Comparison of Edge Detectors," International Conference on Medical Imaging, m-Health and Emerging Communication Systems (MedCom), pp. 289-294, 2014. Crossref,
[14] Md Khurram Monir Rabby, Brinta Chowdhury, and Jung H. Kim, "A Modified Canny Edge Detection Algorithm for Fruit Detection & Classification," 10th International Conference on Electrical and Computer Engineering (ICECE), pp. 237-240, 2018. Crossref,
[15] Hongli Lu, and Juan Yan, "Window Frame Obstacle Edge Detection Based on Improved Canny Operator," 3rd International Conference on Electronic Information Technology and Computer Engineering (EITCE), pp. 493-496, 2019, Crossref,
[16] Mohd. Aquib Ansari, Diksha Kurchaniya, and Manish Dixit, “A Comprehensive Analysis of Image Edge Detection Techniques,” International Journal of Multimedia and Ubiquitous Engineering, vol. 12, no. 11, pp. 1-12, 2017. Crossref,
[17] Hui Zhang, Quanyin Zhu, and Xiang-feng Guan, "Probe into Image Segmentation Based on Sobel Operator and Maximum Entropy Algorithm," International Conference on Computer Science and Service System, pp. 238-241, 2012. Crossref,
[18] Pinaki Pratim Acharjya, Ritaban Das, and Dibyendu Ghoshal, “Study and Comparison of Different Edge Detectors for Image Segmentation,” Global Journal of Computer Science and Technology, vol. 12, no. 13, 2012.
[19] Manasa R, K Karibasappa, and J. Rajeshwari, "Autonomous Path Finder and Object Detection using an Intelligent Edge Detection Approach," SSRG International Journal of Electrical and Electronics Engineering, vol. 9, no. 8, pp. 1-7, 2022. Crossref,
[20] Tasnuva Tasneem, and Zeenat Afroze, "A New Method of Improving Performance of Canny Edge Detection," 2nd International Conference on Innovation in Engineering and Technology (ICIET), pp. 1-5, 2019, Crossref,
[21] Manish Yewange et al., “IJReal-Time Object Detection by Using Deep Learning: A Survey,” International Journal of Innovative Science And Research Technology, vol. 7, no. 4, 2022. Crossref,
[22] Deepak T. Mane et al., “Pattern Classification using Supervised Hypersphere Neural Network,” International Journal of Emerging Technology and Advanced Engineering, vol. 12, no. 8, 2022. Crossref,
[23] Liying Yuan, and Xue Xu, "Adaptive Image Edge Detection Algorithm Based on Canny Operator," 4th International Conference on Advanced Information Technology and Sensor Application (AITS), pp. 28-31, 2015, Crossref,
[24] Ashish Anand, Sanjaya Shankar Tripathy, and Sukesh Kumar, "An Improved Edge Detection Using Morphological Laplacian of Gaussian Operator," 2nd International Conference on Signal Processing and Integrated Networks (SPIN), pp. 532-536, 2015. Crossref,
[25] Beixin Xia, Jianbin Cao, and Chen Wang, “SSIM-NET: Real-Time PCB Defect Detection Based on SSIM and MobileNet-V3," 2nd World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM), pp. 756-759, 2019, Crossref,
[26] Sunil Kumar et al., "Comparative Analysis for Edge Detection Techniques," International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), pp. 675-681, 2021. Crossref,