Image classifier establishing method and image classifier establishing device

Abstract

The invention discloses an image classifier establishing method and an image classifier establishing device. The image classifier establishing method comprises steps that a sample image set is acquired, and the sample image set comprises a positive sample comprising a target image and a negative sample without the target image; the deformation processing of the sample images in the sample image set is carried out to acquire the expanded sample image set; according to the expanded sample image set and a deep convolutional neural network model, a classifier aiming at the target image is acquired; the normalization processing of the output of the convolutional layer of the deep convolutional neural network is carried out. By adopting the above mentioned method, the limited sample image sets are identified artificially, and then the limited sample image sets are expanded, and therefore a sample amount is expanded, and the accuracy of the classifier is improved. The identification accuracy of the classifier is further improved by adopting the deep convolutional neural network, and therefore the classifier aiming at the target image and having the higher identification accuracy is provided.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for establishing an image classifier. Background technique [0002] Logo (LOGO) recognition is a kind of image recognition. It is a very important aspect for enterprise commodity management to judge whether the target LOGO is contained in the image through feature comparison. Use, through LOGO identification to judge the type of goods and many other aspects. [0003] At present, the method of manually extracting features and then training classifiers is mostly used for LOGO recognition. However, the manual extraction method is artificially specified for the features extracted by the LOGO, and there may be insufficient coverage for machine recognition. In addition, because the LOGO features need to be manually extracted, it is impossible to obtain a large enough sample library when training the classifier. Therefore, the accuracy of the obtained classifier ...

AI Technical Summary

Problems solved by technology

However, the manual extraction method is artificially specified for the features extracted by the LOGO, and there may be insufficient coverage for machine recognition. In addition, because the LOGO features need to be manually extracted, it is impossible to obtain a large enough sample library when training the classifier. Therefore, the accuracy of the obtained classifier for image recognition is not high, and there is no way to achieve practical purposes.

[0004] In summary, there is still a lack of a high-accuracy image classifier based on LOGO recognition

Images