Aesthetics image quality evaluation method based on EEG signals

Abstract

The invention discloses an aesthetics image quality evaluation method based on EEG (electroencephalogram) signals. The aesthetics image quality evaluation method based on EEG signals overcomes the problems that in the prior art, the aesthetics image quality evaluation method does not consider the subjectivity of aesthetic perception of human, so that objective aesthetics image quality evaluation is separated from the evaluation main body; and the deep learning network cannot completely simulate the evaluation thinking and result of human, and cannot be preferably combined with subjective evaluation. The aesthetics image quality evaluation method based on EEG signals includes the steps: 1) selecting an image to be evaluated; 2) acquiring EEG signals; 3) extract single time of EEG signals; 4) classifying the single time of EEG signals; and 5) evaluating the image quality. The aesthetics image quality evaluation method based on EEG signals relatively more accord with subjective evaluationof human while objectively evaluating the aesthetics image quality, and the evaluation result is relatively more accurate.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to an aesthetic image quality evaluation method based on electroencephalogram signals in the technical field of image and video quality evaluation. The present invention can be applied to the fields of psychological behavior research, image quality evaluation, image compression, image detection, etc., extracting EEG signals according to the influence of images with different aesthetic sensibility on the human brain, and considering the spatiotemporal characteristics of EEG signals. Images were assessed for objective quality. Background technique [0002] There are many measurement methods for image aesthetics. Objectively extracting low-level features such as wavelet transform, DCT transform and histogram has achieved relatively good measurement performance. A high-aesthetic image should be simple and use basic photography techniques, such as highlighting the subject...

AI Technical Summary

Problems solved by technology

[0007] The specific idea for realizing the purpose of the present invention is to aim at the limitations and uncertainties existing in the existing aesthetic image quality evaluation methods, which cause the inaccurate results of the aesthetic image quality evaluation, and extract the subject's EEG signals, using linear classifiers to sort and classify, study the changes of human EEG signals with changes in aesthetic image quality, and obtain a more objective aesthetic image quality evaluation method

Images