Method for training convolutional neural network classifier and image processing device

Abstract

The invention provides a method for training a convolutional neural network classifier and an image processing device. According to the method for training the convolutional neural network classifier, global features and local features are extracted from an image for used training. The global features and local features are mapped to a feature map according to a predetermined mode as an input sample of the classifier. According to the predetermined mode, the global features are mapped to at least one first region, the local features are mapped to a second region, and each first region is connected with the second region. According to the training method provided by the invention, the speed and accuracy of detection are improved to a large extent.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a method for training a convolutional neural network classifier and an image processing device for classifying images. Background technique [0002] Due to the characteristics of simple structure, few training parameters and strong adaptability, convolutional neural network is more and more widely used in pattern recognition, image processing and other fields. [0003] For example, figure 1 It is a schematic diagram showing the structure of a conventional classifier 100 using a convolutional neural network (Convolutional Neural Network, CNN for short). It consists of the following parts: input layer, convolutional layer, spatial sampling layer, fully connected layer and output layer. [0004] In the process of using the traditional CNN classifier for recognition, take handwritten digits as an example, input an image, and after repeated convolution, spatial maximum sampling and ...

AI Technical Summary

Problems solved by technology

This leads to the least adjustment of the weights near the input layer that should be adjusted the most, which greatly slows down the learning speed of the entire CNN.

[0007] In addition, traditional training methods for CNN classifiers only focus on the training process of a single CNN, or train a batch of CNNs in parallel in a high-performance computing environment.

Images