An Image Edge Detection Algorithm Based on Multi-Feature Fusion

Abstract

Edge detection is one of the core steps of image processing and computer vision. Accurate and fine image edge will make further target detection and semantic segmentation more effective. Holistically-Nested edge detection (HED) edge detection network has been proved to be a deep-learning network with better performance for edge detection. However, it is found that when the HED network is used in overlapping complex multi-edge scenarios for automatic object identification. There will be detected edge incomplete, not smooth and other problems. To solve these problems, an image edge detection algorithm based on improved HED and feature fusion is proposed. On the one hand, features are extracted using the improved HED network: the HED convolution layer is improved. The residual variable convolution block is used to replace the normal convolution enhancement model to extract features from edges of different sizes and shapes. Meanwhile, the empty convolution is used to replace the original pooling layer to expand the receptive field and retain more global information to obtain comprehensive feature information. On the other hand, edges are extracted using Otsu algorithm: Otsu-Canny algorithm is used to adaptively adjust the threshold value in the global scene to achieve the edge detection under the optimal threshold value. Finally, the edge extracted by improved HED network and Otsu-Canny algorithm is fused to obtain the final edge. Experimental results show that on the Berkeley University Data Set (BSDS500) the optimal data set size (ODS) F-measure of the proposed algorithm is 0.793; the average precision (AP) of the algorithm is 0.849; detection speed can reach more than 25 frames per second (FPS), which confirms the effectiveness of the proposed method.

Edge Detection via Fusion Difference Convolution

“…Xie et al introduced the pioneering end-to-end edge deep model called HED [ 13 ], which utilized side branches and fusion branches to compute losses and generate the final edge maps. Subsequent studies [ 33 , 34 ] made improvements to this model to obtain more accurate edge maps. The second type is based on the Transformer network architecture, which captures the complete image context and detailed local clues to extract meaningful and clear edge maps.…”

An Active Image Forgery Detection Approach Based on Edge Detection

“…The methods that connect these points and localize the edges are called edge detection methods. An edge detection algorithm is based on the original image and locates the edge by obtaining the differentiation of the obvious gray changes in the image and it uses the gradient changes between the light and the shade [12]. Edge detection is frequently used in image processing applications to separate objects on the image from each other [13].…”

“…The Canny operator is proposed by J. F. Canny [17] and is mentioned in the literature as a multiscale optimal edge detector [12,18]. The main goals of the Canny algorithm are a low error rate, a minimal difference between real edge pixels and calculated edge pixels, and a single response to an edge.…”

Belt Rotation in the Pipe Conveyor: Research on a Detection Method Based on Image Processing

“…At this stage, the conveyor system is developing in the direction of large-scale [6] , intelligent [7] and energy-saving [8] , and the traditional comprehensive safeguard system of the pipe belt conveyor based on multiple types of sensors is not enough to meet the current needs of highly visualized, and integrated and intelligent development. In view of the above problems this paper investigates the research of conveyor belt rotation detection method of the pipe belt conveyor based on image processing, puts forward a detection method based on OUST-Canny operator [9,10] , and extracts the edge straight line features by using Hough [11] transform and analyzes and processes them, and ultimately realizes the detection of conveyor belt rotation faults.…”