Edge detection filter optimization method based on deep learning

Abstract

The invention discloses an edge detection filter optimization method based on deep learning, and the method comprises the steps: collecting a plurality of to-be-detected object images, and recording the to-be-detected object images as a training image set; selecting to-be-detected features in each image in a framing manner and labeling the to-be-detected features to obtain labeled images; taking the first training image as an input image; carrying out the convolution on the input image, calculating the gradient of each pixel point and inputting the gradient into a Sigmid function for activation processing, and acquiring an output result graph; recording the output result image as a new input image, and repeating; obtaining a normalized result graph by utilizing a softmax function, and calculating loss matrixes MLoss and LOSS values of the normalized result graph and the annotated image; performing back propagation by using the loss matrix MLoss to obtain corrected edge detection filters of each layer; taking the next training image as an input image, and continuing repeating by using the corrected edge detection filters until the LOSS value converges. The method is better in edge detection stability, high in robustness and small in calculated amount.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an edge detection filter optimization method based on deep learning. Background technique [0002] Image segmentation is an important branch in the field of computer vision, among which edge detection methods such as Sobel and Prewitt are classic detection algorithms for image segmentation. As the requirements for image segmentation tasks are getting higher and higher, when the simple Sobel operator performs image segmentation, it is prone to incomplete segmentation and wrong segmentation, which cannot meet the detection needs in the actual production process; and then appeared: based on deep learning Although the image segmentation algorithm has greatly improved the pixel classification accuracy, the deep network model brings a huge amount of calculation, so the algorithm is very dependent on hardware facilities, such as GPU. Contents of the invention [0003] In order to solv...

AI Technical Summary

Problems solved by technology

As the requirements for image segmentation tasks are getting higher and higher, when the simple Sobel operator performs image segmentation, it is prone to incomplete segmentation and wrong segmentation, which cannot meet the detection needs in the actual production process; and then appeared: based on deep learning Although the image segmentation algorithm has greatly improved the pixel classification accuracy, the deep network model brings a huge amount of calculation, so the algorithm will be very dependent on hardware facilities, such as GPU, etc.

Images