Face image quality evaluation method, computer device and computer readable storage medium

Abstract

The invention provides a face image quality evaluation method, a computer device and a computer readable storage medium, and the method comprises the steps: obtaining an initial image, dividing the initial image into a plurality of sub-images, calculating the gray mean value and variance of each sub-image, and carrying out the normalization calculation of each sub-image; performing discrete cosinetransform on each normalized sub-image, extracting a low-frequency coefficient, and calculating the weighted features of the sub-image by using the gray average value and the low-frequency coefficient of each sub-image; and calculating a similarity probability score of each sub-image relative to the standard face sub-image, and calculating a final score of the initial image. The invention furtherprovides a computer device and a computer readable storage medium for realizing the human face image quality evaluation method. According to the method, the influence of various conditions such as illumination, postures and shielding on the face images is considered, and the quality of each image can be evaluated more accurately.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

This technology allows us to extract high frequency coefficient values (focal point) or other characteristic properties during an image transformation before performing analysis by comparing them against standard data. By taking these extra details about how lighting, shading, expressions, and poses affects human faces, we aim to make better use of those specific attributes when analyzing facial appearance. Additionally, it suggests modifying certain areas within every single frame of video frames based upon their importance in determining overall visual performance. Overall, our technical effect includes improved understanding of person's skin texture and recognizing patterns through image analysis techniques.

Problems solved by technology

The technical problem addressed in this patented text relates to improving facial recognition (FID) techniques while considering their effectiveness under varying environmental conditions or challenging situations like crowdsourcing scenarios. Current approaches are either limited in terms of identifying higher-level attributes than lower levels, resulting in poorer overall FID outcomes despite being able to identify both upper and lower quality ones simultanously.

Images