如何检测主观图像质量 [英] How to detect subjective image quality

问题描述

有关一个图像上传工具欲自动检测图像的（主观）的质量，从而导致质量的评价

For a image-upload tool I want to detect the (subjective) quality of an image automatically, resulting in a rating of the quality.

我有以下想法来实现这一试探性：

I have the following idea to realize this heuristically:

• 显然将分辨率进的评级。
• 的COM preSS它为JPG（75％），DECOM preSS它与比较JPG-尺寸与DECOM pressed大小来获得的比率。该图像是较模糊，更高的比率。

显然，我的做法会占用大量周期和内存，如果大型图像评级，虽然这会做我的情况（胖服务器，没有多少上传），而我总是建立在短路围绕如果图像超过一定的分辨率更昂贵的步骤。

Obviously my approach would use up a lot of cycles and memory if large images are rated, although this would do in my scenario (fat server, not many uploads), and I could always build in a "short circuit" around the more expensive steps if the image exceeds a certain resolution.

有没有别的东西，我可以尝试，还是有办法可以更有效地做到这一点？

Is there something else I can try, or is there a way to do this more efficiently?

推荐答案

Assesing的图像（同样适用于声音或视频），质量不是一件容易的事，并且有许多出版物标本兼治。

Assesing the image (the same goes for sound or video) quality is not an easy task, and there are numerous publications tackling the problem.

这在很大程度上取决于图像的性质 - 不同组条件是适当的人工创建的图像（即图），或自然图像（即照片）。有迹象表明，必须要考虑到微妙的影响 - 般的色彩遮蔽，遮蔽亮度，对比度的感知。对于一些图像给定的COM pression比例是完全足够，而对于其他会造成显著质量损失。

Much depends on the nature of the image - different set of criteria is appropriate for artificially created images (i.e. diagrams) or natural images (i.e. photographs). There are subtle effects that have to be taken into consideration - like color masking, luminance masking, contrast perception. For some images a given compression ratio is perfectly adequate, while for other it will result in significant loss of quality.

下面是一个免费接入出版给予简要介绍了主题<一href="http://citeseerx.ist.psu.edu/viewdoc/summary;jsessionid=9BDCF27A1C101763342FB0E13B1BDC61?doi=10.1.1.30.3150">image质量评价。

Here is a free-access publication giving a brief introduction to the subject of image quality evaluation.

您提到的方法 - COM pressing的图像，并将结果与​​原来相比是远远不够完善。什么将是你计划使用的指标？ MSE？每块MSE？可以肯定这是不是太难以实现，但结果将难以跨preT（考虑与高频分量，并没有他们的图像）。

The method you mentioned - compressing the image and comparing the result with the original is far from perfect. What will be the metric that you plan to use? MSE? MSE per block? For sure it is not too difficult to implement, but the results will be difficult to interpret (consider images with high-frequency components and without them).

如果你想更深入到是图片质量评价也有大量的研究在机器学习领域完成。

And if you want to delve more into the are of image quality assessment there is also a lot of research done by the machine learning community.

这篇关于如何检测主观图像质量的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！