Image identification method and device

Abstract

The embodiment of the invention relates to the image processing field, especially to an image identification method and device. The image identification method and device are configured to identify the types of the image. In the embodiment, the method comprises: obtaining an image to be identified; inputting the image to be identified into a feature extraction model, obtaining the first feature vector of the image to be identified, wherein the feature extraction model is obtained through the sample image and the deep convolutional neural network model; dividing the image to be identified into a plurality of subimages according to a preset rule; inputting the subimages into the feature extraction model, and obtaining the second feature vector of the subimages; merging the first feature vector and the second feature vector, and obtaining a third feature vector; determining the type of the image to be identified according to the similarity of the third feature vector and the a fourth feature vector of each type of sample image in the sample feature library, wherein the sample feature library is obtained for each type of sample image putting into the feature extraction model to determine the type of the image to be identified.

Description

technical field [0001] Embodiments of the present invention relate to the field of image processing, and in particular, to an image recognition method and device. Background technique [0002] ML (Machine Learning, Machine Learning) is the study of how computers simulate or implement human learning behaviors to acquire new knowledge or skills, and reorganize existing knowledge structures to continuously improve their own performance. It is the core of artificial intelligence and the fundamental way to make computers intelligent. Its application pervades all fields of artificial intelligence. It mainly uses induction and synthesis rather than deduction. [0003] Product classification of credit card pictures is a typical classification problem. Due to the large number of credit card categories, machine learning models are required to have strong feature extraction capabilities. Traditional machine learning models are difficult to achieve good classification results. For exam...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides an image recognition method and device, which is used to solve the problem that the traditional machine learning model is used to classify credit card products in the prior art, and there are deep-level features that cannot be extracted from credit card pictures, and the recognition rate is low and the misrecognition rate is also high. The problem

Images