Convolutional neural network-based human hand image region detection method

Abstract

The invention discloses a convolutional neural network-based human hand image region detection method. The method comprises the following steps of: carrying out feature extraction on an image by utilizing a convolutional neural network, and training a weak classifier; for the image, angles of which are marked, segmenting the image on the basis of the classifier to obtain a plurality of candidate regions; modeling each candidate region by utilizing the convolutional neural network so as to obtain an angle estimation model, and carrying out angle marking to rotate the candidate area to a positive definite attitude; modeling each candidate region again by utilizing the convolutional neural network so as to obtain a classification model; for a test image, firstly segmenting the test image by using the weak classifier so as to obtain candidate regions, and for each candidate region, estimating angle of the candidate region through the angle estimation model and rotating the candidate region to a positive definite attitude; and inputting the candidate region under the positive definite attitude into the classification model to obtain a position and an angle of a human hand in the image. According to the method, the classification precision is improved by adopting convolutional neural network-based coding classification, and by utilizing the angle model, the method has rotation variance and very high human hand region detection precision.

Description

technical field [0001] The invention belongs to the fields of pattern recognition and computer vision, and in particular relates to a method for detecting regions of hand images based on convolutional neural networks. Background technique [0002] In recent years, with the development of computer vision and pattern recognition, the detection and positioning of hands has made significant progress, but there are still many deficiencies. Due to the influence of the external environment, such as illumination changes, hand shadows, hand deformation, hand Self-occlusion, mutual occlusion, etc. of hand movement have brought great challenges to hand detection and positioning. Convolutional Neural Networks (CNN) is a type of artificial neural network. Its weight sharing network structure makes it more similar to biological neural networks, which reduces the complexity of the network model and the number of weights. It has achieved the best results in almost all current object classi...

AI Technical Summary

Problems solved by technology

[0003] The traditional convolutional neural network has strong discrimination in the field of object recognition, but it requires the input to be invariant to rotation. In many tasks, such as human hand image area detection, the input image has a large number of rotation changes. The traditional convolution Neural networks perform poorly on these tasks

In addition, in the traditional detection method, the candidate region extraction is completely based on the gray value Unicom region, which is difficult to deal with objects such as hands with large deformation and serious occlusion.

Images