A multi-attribute image aesthetics evaluation system based on attention mechanism

Abstract

The invention provides a multi-attribute image aesthetics evaluation system based on attention mechanism. Using machine learning methods, A composite neural network model is trained by using large-scale photograph dataset and corresponding comment information, this model can extract the multi-attribute aesthetic features of image effectively by convolution operation, the image features are extracted from the multi-attribute feature extraction network of the model, Features are further processed in the channel and spatial attention network, and finally the final comments are generated in the language generation network through the long-short memory network unit. The model can automatically output comments of different attributes according to the image characteristics. When an image is inputted, the generated model considers the characteristics of the image from different attributes and evaluates the aesthetic quality of the image in natural language. The method is easily realized by software, and the invention can be widely applied to computer vision, image evaluation and the like.

Description

technical field [0001] The invention belongs to the fields of image analysis and computer vision, in particular to image aesthetic quality evaluation, in particular to a multi-attribute image aesthetic evaluation system based on attention mechanism. Background technique [0002] With the popularity of multimedia data such as image data and video data in the era of big data and the increasingly frequent processing and transmission, how to process multimedia data has become a hot spot and focus of academic and applied research. The quality evaluation of image aesthetics is a field formed by the intersection of computer vision, image processing, image aesthetics and other disciplines. [0003] Image Aesthetic Quality Assessment (Image Aesthetic Quality Assessment) aims to use computers to simulate human perception and understanding of beauty, and automatically evaluate the "beauty" of images, that is, the objective evaluation of image aesthetic quality. The aesthetic stimulati...

AI Technical Summary

Problems solved by technology

However, its method has the following disadvantages and deficiencies: the amount of data is too small (4307 images), it is difficult to meet the scale requirements of large-scale deep neural networks for training samples; only one type of evaluation information can be output, multi-attribute evaluation cannot be realized, and the content is not enough Comprehensive and objective; the attention mechanism is not used to strengthen the task objectives, and the pertinence of the generated evaluation is not strong

Images