Human-shaped image segmentation method

Abstract

The invention relates to a human-shaped image segmentation method. The method includes: for all first pixel points for training a human-shaped image, extracting multi-scale context information; putting image of all scales of all the first pixel points into the same convolutional neutral network, and forming a multichannel convolutional neural network group, each channel corresponding to an image block of a scale; adopting a back propagation algorithm to train the neural network group, and obtaining human-shaped image segmentation training model data; for all second pixel points for training the human-shaped image, extracting multi-scale context information; putting image block of different scales of each second pixel point into a neural network channel corresponding to the human-shaped image segmentation training model, if a first probability is larger than a second probability, the second pixel pints belonging to a human-shaped region, and otherwise, the second pixel points belongs to outside the human-shaped region. The human-shaped image segmentation method in the invention is fast in image segmentation speed and high in accuracy.

Description

technical field [0001] The invention relates to the field of pattern recognition, in particular to a humanoid image segmentation method based on multi-scale context deep learning. Background technique [0002] In the image target segmentation method, the existing segmentation method is to establish the relationship between each pixel and its adjacent pixels, and use a graph model to model the relationship. When the number of adjacent pixels is too small (for example, the method based on the graphical model considers several or a dozen adjacent pixels), it is impossible to form a semantic segmentation; and when the number of adjacent pixels considered is large, the computational complexity is very high, and it is likely that the model will struggle to converge. Contents of the invention [0003] The purpose of the present invention is to address the defects of the prior art and provide a humanoid image segmentation method, which uses multi-scale context information of pixe...

AI Technical Summary

Problems solved by technology

When the number of adjacent pixels is too small (for example, the method based on the graphical model considers several or a dozen adjacent pixels), it is impossible to form a semantic segmentation; and when the number of adjacent pixels considered is large, the computational complexity Very high, and it is likely that the model will struggle to converge

Images