A picture garbage recognition method based on deep learning

Abstract

The invention discloses a picture garbage recognition method based on deep learning, and the method comprises the following steps: S1, building a large-scale picture training set, training a deep learning classifier based on a convolutional neural network in the training set, and extracting a convolutional layer in the deep learning classifier as a deep feature extractor; S2, constructing a singlenonlinear classifier, and inputting pictures in the high-quality picture library and the picture garbage library into the depth feature extractor obtained in the step S1 to obtain a feature representation vector; S3, taking the feature vector obtained in the step S2 as the input of a nonlinear classifier, and carrying out supervised learning by utilizing a corresponding tag to obtain an availablepicture garbage classifier; And S4, cutting the long image through a sliding window to obtain a plurality of pictures, extracting each segment of feature by using a depth feature extractor, classifying by using a picture garbage classifier, and comprehensively integrating each result to obtain a final result.

Description

technical field [0001] The invention relates to the technical field of computer picture processing, in particular to a method for identifying picture garbage based on deep learning. Background technique [0002] With the development of Internet technology, the amount of information stored on the network has increased tremendously, but its content composition is more complex, including a lot of low-quality and high-noise spam, and users have to spend a lot of time and energy to filter various information. class information. From the perspective of image search and classification, irrelevant or low-quality images will reduce user experience, such as food when searching for "landscape" and advertisements when searching for "architecture". If these can be automatically filtered out, it can Help users save a lot of time and effort. [0003] Existing image recognition methods are mainly aimed at the recognition of specific objects on regular data, which require a specific data s...

AI Technical Summary

Problems solved by technology

[0004] In the actual production environment, a considerable number of pictures have a very large aspect ratio. Direct scaling to 1:1 will cause high distortion of the picture content, which brings difficulties to traditional recognition methods.

Images