A Review of Gradient-Based and Edge-Based Feature Extraction Methods for Object Detection

Abstract

In computer vision research, object detection based on image processing is the task of identifying a designated object on a static image or a sequence of video frames. Projects based on such research works have been widely adopted to various industrial and social applications. The fields to which those applications applies includes but not limited to, security surveillance, intelligent transportation system, automated manufactoring, quality control and supply chain management. In this paper, we are going to review a few most popular computer vision methods based on image processing and pattern recognition. Those methods have been extensively studied in various research papers and their significance to computer vision research have been proven by subsequent research works. In general, we categorize those methods into to gradient-based and edge-based feature extraction methods, depending on the low level features they use. In this paper, the definitions for gradient and edge are extended. Because an image can also be considered as a grid of image patches, it is therefore reasonable to incorporate the concept of granules to gradient for a review. The definition for granules can be found in [1].

Detection of moving objects in roundabouts based on a monocular system

“…It could be a blob, an edge, a corner, etc. There are different feature detectors like Canny, Sobel, Shi & Tomasi, and Laplacian of Gaussian (Wang, 2011). Each application needs to decide what are its proper features and feature-detectors.…”

Methods Used in Computer-Aided Diagnosis for Breast Cancer Detection Using Mammograms: A Review

“…Gradient-based methods are widely used in analyzing mammograms [107][108][109]. e basic idea of the gradient is as follows: let Y be an R-valued random variable, and then…”

Pengenalan Plat Kendaraan Bermotor Menggunakan Metode Gradien Karakter dan BPNN (Backpropagation Neural Network)

“…Berdasarkan penelitian sebelumnya tentang pengenalan karakter alpabet dari tulisan tangan berdasarkan fitur geometri [1], maka paper ini merupakan implementasi dari penelitian tersebut dengan menambahkan karakter numerik dengan studi kasus plat kendaraan. Penelitian ini bertujuan untuk mengetahui hasil pengenalan karakter yang didapatkan menggunakan metode klasifikasi BPNN dengan ekstraksi fitur gradien karakter berdasarkan fitur tepi dan gradiennya [2]pada plat kendaraan.…”

“…Kedua, walaupun fitur berbasis tepi telah terbukti sebagai pendekatan yang sangat baik, akan tetapi komponen gradien dibutuhkan untuk meningkatkan ketahanan pada suatu permasalahan atau tugas yang lebih kompleks. Penelitian selanjutnya akan menyelidiki lebih dalam kedua pendekatan ini dan menelusuri perbaikan yang potensial dari suatu pengenalan objek [2].…”