Internet picture filtering method and device

Abstract

The invention provides an Internet picture filtering method and device. The Internet picture filtering method comprises the following steps: according to different preset dimensions, zooming an obtained Internet image to generate pictures of different dimensions; calculating the quick characteristics of the pictures of different dimensions; adopting preset image annotation information and the quick characteristics to train to generate a target image classifier; utilizing the target image classifier to detect the Internet image, and determining a candidate image area which contains target attributes; inputting the candidate image area into a convolutional neural network to calculate the characteristics of the convolutional neural network; and utilizing the classifier to classify whether the picture contains a target image or not according to the convolutional neural network to realize picture filtering. Internet pictures can be favorably filtered, calculation efficiency is improved, a user can carry out fine tuning on a deep neural network on line, and therefore, detection performance of the Internet picture filtering method is better than the detection performance of other methods.

Description

technical field [0001] The invention relates to pattern recognition technology, in particular to a method and device for filtering Internet pictures. Background technique [0002] According to statistics, by the end of June 2014, my country's Internet users had reached 632 million. In the process of surfing the Internet every day, countless pictures have to be browsed, but many of them are not needed by users, which not only wastes time but also wastes storage space. Therefore, an Internet picture filtering function is needed to make unnecessary The pictures are directly filtered out, leaving only the pictures needed by the user. [0003] The existing image filtering technology in the prior art has already involved the filtering of Internet images, such as the patent application titled "An Internet Image Advertising Filtering System and Its Filtering Method" (Application No. 201210004669, Publication No. 102419777A) In , the following modules are defined: content input int...

AI Technical Summary

Problems solved by technology

[0004] However, the problems in the picture filtering scheme in the prior art include: 1) filtering only for Internet advertising pictures, not for all occurring Internet pictures, and certain specific types of pictures defined by users; 2) the system requires Analyze user-generated content, extract multiple features, and calculate feature values ​​and generate feature vectors based on feature history and manual operation records. This method is not efficient in terms of time and performance.

Images