Contour detection method based on rod cell dark adaptation

Abstract

The invention aims to provide a contour detection method based on rod cell dark adaptation. The contour detection method comprises the following steps: A, transferring an image to be detected from an RGB color space to an HSV color space; b, performing brightness dark adaptation simulation on the brightness of the HSV image to obtain n images with the actually maximum brightness at different adaptation moments; c, respectively transferring the n images with the actually maximum brightness back to the RGB color space to obtain n adaptive process images at different adaptive moments; d, carrying out weighted fusion on the obtained n adaptation process images at different time stress moments to obtain a color image after dark adaptation, and solving the contour of the color image to obtain an unrefined contour output; and E, carrying out edge refinement on the obtained non-refined contour image by utilizing the optimal direction through non-maximum suppression to obtain a final contour image and outputting the final contour image. According to the invention, the image information of different adaptation periods is integrated to obtain a retina output with more complete target information, so that the accuracy of target contour detection is improved.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a contour detection method based on the dark adaptation of rod cells. Background technique [0002] The contour defines the shape of the target, and the contour is one of the important tasks in target recognition, and obtaining the target contour from the cluttered scene is an important and quite difficult task, mainly because there are usually a large number of textured background edges around the contour, so This work mainly needs to exclude nonsensical edges due to textured regions while preserving object contours. The key to improving the detection rate is to optimize the integration of local information into consistent global features based on context. The human visual system has the ability to quickly and effectively extract contour features from complex scenes, which effectively promotes the development of contour detection algorithms inspired by biological characteristics...

AI Technical Summary

Problems solved by technology

In the process of contour information extraction, they did not simulate the visual adaptation mechanism, which caused a certain degree of target contour information problems, resulting in positioning deviation of the target contour

Images