Fly face recognition method based on deep convolutional neural network

Abstract

The invention provides a fly face recognition method based on a deep convolutional neural network. The method comprises the steps of optimizing a multi-task convolutional neural network MTCNN to perform face positioning and feature point detection on a fly image; obtaininig a fly face feature point image through positioning and detection, and carrying out fly face alignment; making the aligned flyface images into a data set; building a fly face deep convolutional neural network model; connecting two groups of feature vectors extracted from the thickness in the fly face deep convolutional neural network in series to form a group of feature vectors; and testing the fly face deep convolutional neural network model through the test set, and verifying the fly recognition effect. According to the method, a fly face deep convolutional neural network is adopted, contour features of an image are roughly extracted by using a large number of convolution pooling, and then specific part features such as small eyes in fly compound eyes are extracted by using Inception-ResNet and Reduction networks. According to the network, the learning target and difficulty can be simplified, and richer feature vectors can be extracted while gradient loss is prevented.

Description

technical field [0001] The present invention relates to the technical field of biological feature recognition, in particular, to a method of fly face recognition based on a deep convolutional neural network. Background technique [0002] In recent years, the field of biometric identification technology has developed rapidly. Especially with the increasingly frequent trade exchanges between countries in the world, the probability of foreign fly insects carried by passengers being introduced into our country is increasing, and it may even cause problems such as the destruction of the ecological environment. Therefore, research on efficient identification of fly insect species is urgent. At present, there are mainly methods for fly recognition: 1) Fly insect recognition based on color features, collecting image color histogram information and merging all color histograms into feature vectors as color features of fly insects. The color feature is not affected by image rotation...

AI Technical Summary

Problems solved by technology

But because it does not pay enough attention to the information difference between categories, the classification ability is limited

4) Fly image recognition based on deep learning, which uses a convolutional neural network to identify flies as a whole, but the similarity of flies is high, the extracted features of the whole body of flies have limitations, and the accuracy of insect recognition is low

Images