An image classification and identification method based on twin networks

Abstract

The invention discloses an image classification and recognition method based on a twin network. According to the method, repeated inspection is carried out through Hash coding; preprocessing such as boundary frame prediction and affine transformation is simplified, and the data set quality is improved; Then, the test set and the training set are traversed through Hash coding, matched picture pairsand unmatched picture pairs are formed through combination in sequence, the matched picture pairs and the unmatched picture pairs are alternately input into a twin classification network for trainingfitting, and finally the classification effect that pictures of the same type are classified into the same type and different types can be effectively distinguished is achieved. According to the method, the defect of low prediction accuracy of an early-stage deep learning classification method when the test set is more than the training set and the category data is unbalanced is overcome, and theproblems that the classification data is unbalanced, the test set is more than the training set and the overall scale is small in an actual scene are solved. Besides, by encoding the picture data, the matching picture pair and the mismatching picture pair are analyzed, so that the accuracy of the twin classification network is improved, and a good example is provided for picture classification inan actual scene.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to an image classification and recognition method based on twin networks. Background technique [0002] With the development of deep learning, computer vision has become one of the hottest research directions in the field of deep learning; as a key component of computer vision, the latest progress in image classification, localization and detection has greatly promoted the progress of visual recognition systems. However, the image classification problem often needs to face the following challenges: viewpoint change, scale change, intra-class change, image deformation, image occlusion, lighting conditions and background noise. [0003] The general process of the currently commonly used image classification and recognition method is to read pictures, generate batches and scramble the sample data, then construct the image classification and recognition model, then t...

AI Technical Summary

Problems solved by technology

Another example is that the Chinese patent with the publication number CN108647723A proposes an image classification method based on a deep learning network, using the ResNext model and Softmax training, and using the existing public data sets for pre-training, but when faced with actual complex data sets, it is difficult to Carry out special data preprocessing, only use the fine-tuning method for training, and rely heavily on the model trained by the public standard data set, the effect is still not good

It can be seen that the purely supervised method has a heavy dependence on the size of the data set and has a large impact on the test results.

Images