Method for constructing dermatoglyph classification prediction model by introducing ResNet deep learning network

Abstract

The invention relates to a method for constructing a dermatoglyph classification prediction model by introducing a ResNet deep learning network. The method comprises steps of using an intelligent terminal device for fully collecting a sample dermatoglyph original image and sequentially carrying out normalization, Wiener filtering denoising, Sobel operator algorithm sharpening, binarization algorithm processing and OPTA pixel skeletonization processing; repairing and enhancing by adopting a GAN generative adversarial network model algorithm, and manually labeling each sample dermatoglyph image;and finally, establishing a dermatoglyph classification prediction model, optimizing a loss function, iteratively training the model, and verifying to obtain a dermatoglyph classification model. According to the method, a CNN-based ResNet deep learning network is introduced to construct a dermatoglyph classification prediction model; when the constructed model is applied, different dermatoglyph feature images can be learned and analyzed from the aspects of multiple dimensions and multiple features, more features are extracted from dermatoglyph image information, and high accuracy is achievedin dermatoglyph recognition and classification.

Description

technical field [0001] The present invention relates to the field of dermatoglyphia classification and recognition, in particular to a method of introducing a ResNet deep learning network to construct a dermatoglyphia classification prediction model. Background technique [0002] From a conceptual point of view, fingerprints belong to a type of dermatoglyphs, which refer to raised lines on fingers, palms, toes, and soles of feet. Our common name "fingerprint" is a texture born on fingers. The textures on the palms and soles of the feet are called palm prints and foot prints, respectively. Once the skin pattern is developed, it will remain unchanged throughout life. Its uniqueness is reflected in the uniqueness that distinguishes it from other fingerprints. The height, density, quantity and position of the trifurcation point of the skin are not the same. [0003] Most of the dermatoglyphs that are not understood in this technical field are limited to the technology of using...

AI Technical Summary

Problems solved by technology

[0006] First of all, in the past, shallow structure models were generally used for data processing in dermatoglyphic recognition and classification, and the structure models had at most one or two layers of nonlinear features. Shallow structure models have been used to solve some simple practical problems, but when When encountering complex multi-dimensional and multi-feature situations, it is difficult for shallow models to achieve good expressions. Therefore, it is difficult to achieve classification goals if established using shallow structure models as in the past;

[0007] Secondly, the establishment of the dermatoglyph prediction model needs to search and collect a large number of samples, and the collection of dermatoglyph images needs to be captured by smart terminals. Any damage will lead to the possibility of repeated collection, which will have a great impact on the early data processing of the establishment of the dermatoglyph classification prediction model

Images