This paper is devoted to image quality problem. We analyze advantages and disadvantages of existing methods. Classification of quality metrics into some groups has been done. Based on this classification, we formed proposition about prospects of using this methods in solving image quality The problem of quality assessment arises in many different subjects. From computer graphics, where rendering of complex scenes may had a lot of time. To bioinformatics and computer security, where quality and accuracy of images may safe human lives. Although, count of image editors, which must define image quality and may improve this, significantly increases.
Let there be two digital images: X – original, Y – test (distorted image – with possible defects). The challenge is to build algorithm, which have these two images and define quality assessment of test image.
Digital image may be represent with brightness matrix = ( , ) ×
, where , ∈ [ , ] ⋂ ℤ, ly. Although, in some cases, we will consider image as one-dimensional signal – height and width of image, respective = ( ∙ + ) ∙ Basic metrics error ( , ) = 1
(∑ =1 | − | ) .
( , ) = √
1
At the beginning, we consider classic metrics that came to computer vision from mathematical statistics. Mean squared error of images and presented as ∑ =1( − )2. Sometimes researchers considered root mean squared
( , ), which may be generalize on : ( , ) =
Peak signal-to-noise ratio is calculated based on MSE and often apply for measure of distortion when image was compressed. ) − is the dynamic range of allowable image pixel intensities (e.g., for image that have allocations of 8 b/pixel of gray-scale, = 255).
However, these metrics are not best instruments for quality assessment of images
[
In paper [
The first result in this approach was metric SSIM (Structural SIMilarity), which computing as composition of: illumination ( ( , ) = 2+ 2+ 1 2 + 1 ), contrast ( ( , ) = 2+ 2+ 2 2 + 2 ) and structural comparison ( ( , ) = + 3 + 3 ); where – expected value of brightness, – standard deviation, – covariance of and , and 1, 2, 3 – some constants, that obtained experimentally. .
For improve this metric we can compute weighted mean value of SSIM on local
features (local feature is small part of image, which focuses people’s attention; it is
known, that using local features allow to discard noise and improve quality of metric
[
MS-SSIM (Multi-scale SSIM) [
SCSSIM [
First this metric was developed by Scott Daly in his paper [
VDP receives 2 input images and generates output differences map (each pixel has
value, which describes how different the pixels of corresponding input images).
Schema of work VDP presents on Fig. 1. One of the advantages of this model is
possibility to get prediction of local differences between images (on the pixel level),
while methods described previously provided a single value for the entire image.
Although, the basis of this metric are components that are already recognized in the
computer vision: CSF [
For analyze image fidelity metrics we collect set of images, which has been obtained by various deformations of original image. Then these images were sorted by decrease quality in terms of human perception (this sort was done using quality image assessment by three independent people). Result set of images in the sort order present on Fig. 2 (presented reduced copies, real images have a size 256х256 pixels). Names of the images correspond to deformation types: 1) shift( ) – shift brightness of all pixels by (i.e. image becomes lighter); 2) noise( ) – add Gaussian noise (the more – the more noise); 3) jpeg( ) – image after compression by JPEG for different sizes of block (the less – the more defects); 4) blur( ) – Gaussian blur (the more , the more blur). Then testing of 4 metrics (PSNR, LMQ, variation of SSIM, VDP) was conducted. Each metric returns evaluation image deformation – i.e. result that inverse to quality and takes values from 0 (quality image) to 1 (deformed image). The resulting graph of the image deformation (vertical axis) of the image (horizontal axis) presented on Fig. 3. Highline that main criteria for correctness of metric is not absolute deformation value but result graph has been directed upwards (i.e. for any pair of images, deformation value of left image must be greater than deformation value of right image). 0,80 0,60 0,40 0,20 0,00 As can be seen from the graph, the most correct results were obtained by metrics VDP and SCSSIM. Metric LMQ also gave a good result, but poorly handled with images, which are compressed using JPEG.
LMQ
In this paper we considered principal image fidelity metrics, from basic that came to computer vision from mathematical statistics, to hybrid models that use modern knowledge of computer vision and information quality assessment. Described metrics split into the following groups: statistics (MSE, norm, PSNR); structural similarity (SSIM, MSSIM, MS-SSIM, IW-SSIM, SCSSIM); human perception (VDP); anisotropy (LMQ). Advantages and disadvantages of these methods were considered. In the result of this work we determine that the presence of the original image should be use VDP metric. If we don’t have original image for quality assessment, then should be use LMQ, which is very costly from a computational point of view. Аннотация. Рассматривается задача оценки качества цифрового изображения. Проанализированы преимущества и недостатки существующих методов. Проведена классификация метрик качества в некоторые группы. На основе анализа и тестирования методов на выбранных изображениях, сформировано утверждение о перспективности использования выбранных методов в решении поставленной задачи.