Salient contour detection on the basis of the mechanism of bilateral asymmetric receptive fields
- PDF / 2,261,664 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 11 Downloads / 201 Views
ORIGINAL PAPER
Salient contour detection on the basis of the mechanism of bilateral asymmetric receptive fields Tao Fang1 · Yingle Fan1 · Wei Wu1 Received: 9 October 2019 / Revised: 30 March 2020 / Accepted: 2 April 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Salient contour detection is the key step of visual perception and is very important for visual detection and object recognition. In this paper, a new contour detection method, which is based on the bilateral asymmetric receptive field mechanism of the visual pathway, is proposed. First, the classical receptive field of primary visual cortex neurons was simulated, and the 2D Gaussian derivative was used to detect the primary contour response of the input image. Then, the asymmetric receptive field structure was introduced to enhance the contrast difference in local regions. Assuming that unilateral asymmetric receptive fields will suppress the intensity imbalance of the primary contour in the image, the strategy of weight information fusion, which is based on the bilateral asymmetric receptive field multi-scale inhibition, was proposed. Finally, texture suppression was performed with varying intensity in the local regions of the primary contour in the image, and the salient contour was detected. The salient contour detection method, which is based on bilateral asymmetric receptive fields proposed in this study, provides new ideas for the subsequent image understanding and analysis that are on the basis of the visual mechanism. Keywords Visual mechanism · Asymmetric receptive fields · Contour detection · Multi-scale
1 Introduction Contour mainly refers to the contour information that can reflect the main object, including the boundary between the main object and the background, and the boundary between planes. Contour is the basis of many visual perception tasks, and it is essential in visual perception. In addition, contour is critical for object recognition, surface reconstruction, and image understanding [1]. In recent decades, many scholars have proposed various contour detection methods that are based on the local spatial feature analysis, global context analysis, and multi-resolution analysis [2–4] and that effectively improve the accuracy and efficiency of contour detection. However, compared with the ability of the human visual system to detect the contour of major object in extremely complex scenes, the intelligent performance of these methods in distinguishing texture, edge, and major contour is insufficient. This challenging task has attracted
B 1
Yingle Fan [email protected] Laboratory of Pattern Recognition and Image Processing, Hangzhou Dianzi University, Hangzhou 310018, China
considerable attention from visual science and computer science researchers [5, 6]. Contours perception is a fundamental function of humans to recognize the world through vision. With the deepening of the research on visual mechanisms, many researchers have been inspired by biological visual mechanisms and established various mathematical mo
Data Loading...
