Method for performing non-reference image quality prediction by using multilayer depth characterization

Abstract

The invention discloses a method for performing non-reference image quality prediction by using multilayer depth characterization. The method comprises the following steps: step (1) data preprocessing: zooming all images to a unified size, subtracting a draw value, and converting binary data into a data format that can be identified by a deep neural network; step (2) feature extracting and processing: performing feature extraction by using a 37-layer VGGnet model that is trained on ImageNet, extracting each layer of features, and processing the same to obtain a column vector; and step (3) score predicting: inputting the column vector obtained by fusing each layer of features in a support vector regression model to obtain a predicted score of each layer of features, and using an average value of the scores of the layers as a quality evaluation score of the whole image. The invention provides a simple and efficient new method for image quality evaluation. The best effect in the existingimage quality evaluation field is obtained.

Description

Technical field [0001] The present invention mentions a method for using multi-level depth representation to perform BLind Imagequality predictioN via multi-level DEep Representations (BLINDER), which mainly involves a method of pre-training using a deep network and extracting and processing each The method for predicting scores by layer features, and the modeling expression for constructing a highly accurate score prediction model. Background technique [0002] Image quality is an important indicator for comparing the performance of various image processing algorithms and optimizing system parameters. Therefore, it is of great significance to establish an effective image quality evaluation mechanism in the fields of image acquisition, coding and compression, and network transmission. Image quality evaluation can be divided into subjective evaluation methods and objective evaluation methods. The former relies on the subjective perception of experimenters to evaluate the quality o...

AI Technical Summary

Problems solved by technology

[0006] (2) In the existing methods for image quality rating based on deep neural networks, most of the network outputs of the last layer of the network model are used as the key to predicting image quality scores. However, for image quality evaluation, the last layer of network may not the best choice

Images