Comparative Analysis of Edge Detectors Applying on the Noisy Image Using Edge-Preserving Filter

Abstract

AbstractIn computer vision, edge detection is a fundamental technique. It is used as a pre-processing technique to make image segmentation, pattern recognition, and feature extraction more comfortable. Digital images are often corrupted by the noise that causes the detection of spurious edges during edge detection. Thus, we’d like to suppress the maximum amount of noise as potential while retaining important image features such as edges, corners, and other sharp structures. This research compares multiple edge detection methods applied to a filtered image by adding speckle noise. In this paper, four edge detection operators have been applied to an image denoised by various edge-preserving filters, and their performance is evaluated based on the performance metrics peak signal-to-noise ratio (PSNR) and mean squared error (MSE). Images from the Barcelona Images for Perceptual Edge Detection Dataset (BIPED) are used for performance evaluation of filters and edge detection techniques. The experimental results show that a bilateral filter with a Canny edge detection operator is the most optimized method for edge detection of speckle-noise-affected images.KeywordsImage processingEdge detectionNoiseEdge-preserving filtersPSNRMSEBIPED