Image classification method and system based on image salient region

Abstract

The invention discloses an image classification method and system based on an image salient region. The method includes offline training and online test. The offline training comprises: performing ultra-pixel segmentation on an image to obtain multidimensional segmentation blocks, and calculating the characteristic contrast of the segmentation blocks to obtain a target salient map; performing threshold segmentation on the target salient map to obtain a binary image, performing morphological processing on the binary image, and performing automatic segmentation extraction on the target salient map by employing a segmentation algorithm to obtain the salient region; and inputting the salient region to a convolutional neural network for training to obtain an image classifier based on the image salient region. The online test includes: performing automatic segmentation extraction of the salient region on a test image, inputting a salient region image of the test image to the trained image classifier, and performing image classification to obtain an image class mark. According to the method and system, the segmentation result is guaranteed, the workload of artificial interaction is reduced, and the accuracy of image classification is improved.

Description

technical field [0001] The invention belongs to the field of image content classification and retrieval, and more particularly relates to an image classification method and system based on image salient regions. Background technique [0002] With the continuous development of computer and digital information technology, a large number of digital images appear in people's life through various channels every day. Image is a similar or vivid description of objective things, and is the most commonly used information carrier in human social activities. As the main source of information for people, it is infiltrating people's work, study and life. In the process of image processing and analysis such as image classification and retrieval, most of the traditional methods describe and analyze the full image information of the image. However, the full image description of the image sometimes contains interference information, such as for images containing salient regions. In general...

AI Technical Summary

Problems solved by technology

At present, image classification is mostly implemented based on the whole image. When the semantic category of the image is the same but the background is different, the underlying visual features are generally not similar. Training an image classifier for this kind of image, the classification performance will be affected by the background information, thus making the image classification accuracy rate reduce

However, images acquired under different shooting conditions, such as images of smartphones and tablets, will have very similar underlying visual features but significantly different semantic categories, and it is difficult to achieve effective classification based only on the underlying visual features

Therefore, for images containing salient areas, the image category is often represented by the information of the salient area of ​​the image. Judging the image category based on the original image will cause information interference and affect the classification accuracy.

Images