Method and device for detecting spot defect of face skin based on deep learning

Abstract

The invention provides a method and a device for detecting a spot defect of a face skin based on deep learning. The method comprises the steps of acquiring a training data set; constructing a convolutional neural network, and training the convolutional neural network by use of the training data set to obtain a detection model, wherein the convolutional neural network has the following characteristics: multi-layer convolutional characteristic extraction is performed on a sample to obtain different hierarchies of characteristic graphs, then, sampling is performed by use of sampling frames with multiple sizes and shapes to obtain sampling result corresponding to different hierarchies, then all of the sampling results are classified by use of a softmax loss function and a position is predictedby use of an L1 loss function, a loss value obtained by calculation is returned to a front end of the convolutional neural network, and a convolutional neural network parameter is adjusted b y use ofa gradient descent method; and segmenting a to-be-detected image into test image blocks, inputting all test image blocks into the detection model in a traversal manner to obtain corresponding image block detection results, and then splicing all of the image block test results into a complete image detection result.

Description

technical field [0001] The invention relates to the technical field of computers and software, in particular to a method and device for detecting facial skin point defects based on deep learning. Background technique [0002] With the improvement of living standards, the public began to pursue the beauty and health of facial skin. Common facial skin defects can be roughly divided into facial skin point defects and facial skin point defects according to shape, area and distribution. Among them, facial skin point defects include pigment nevus, acne, acne marks, etc., which are characterized by small area, similar point shape, and usually independent distribution. [0003] Automated detection of such point-like skin defects is generally used for batch processing or quantitative statistical analysis of skin defects. Most of the existing automatic detection algorithms for point-like skin defects are based on traditional computer vision technology, that is, according to the colo...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the present invention provides a method and device for detecting facial skin point defects based on deep learning, which can solve the technical problems in the prior art that cannot provide scientific and rigorous reference for the evaluation and treatment of skin defects

Images