Multi-visual-field convolutional neural network-based image feature identification method

Abstract

The invention discloses a multi-visual-field convolutional neural network-based image feature identification method. The method comprises the steps of collecting CT images with positive and negative tags in a historical database, and establishing a data set; judging a position region of a specified feature in each CT image of the data set by utilizing an image segmentation algorithm, and extracting sensitive regions of different pixel sizes; constructing a multi-visual-field convolutional neural network; inputting the extracted sensitive regions of different pixel sizes as samples to the multi-visual-field convolutional neural network, and training the multi-visual-field convolutional neural network to obtain a trained multi-visual-field convolutional neural network; and processing the to-be-identified CT images, inputting the extracted sensitive regions of different pixel sizes to the trained multi-visual-field convolutional neural network for performing feature identification, and determining the positive and negative tags of the to-be-identified images according to an identification result. According to the scheme, the end-to-end image identification is realized and the identification accuracy is ensured.

Description

technical field [0001] The invention relates to the technical field of CT image matching and recognition, in particular to an image feature recognition method based on a multi-view convolutional neural network. Background technique [0002] At present, most methods for automatic image classification are not end-to-end, which means that before matching and recognition, it is necessary to extract features with predefined filters (such as histograms of oriented gradients, local binary patterns, etc.) or manually extract images characteristics (such as geometry, texture, appearance, etc.). Feature learning is a high-order representation learned directly from training data. Artificial neural network (ANN) learns features from the original data. However, due to the full connection and shallow network structure of the traditional artificial neural network, it is impossible to extract high-level features with strong independence, which severely limits the application of actual imag...

AI Technical Summary

Problems solved by technology

[0004] However, there is no relatively complete CNN technology for CT image recognition at present.

Images