MS-UNIQUE: Multi-model and Sharpness-weighted Unsupervised Image Quality Estimation
This work addresses image quality assessment for applications like photography and video processing, but it is incremental as it builds on existing unsupervised methods with multi-model and sharpness-weighted enhancements.
The paper tackles the problem of estimating perceived image quality by training multiple linear decoders on image patches in an unsupervised manner, achieving top performance in accuracy, consistency, linearity, and monotonic behavior compared to eleven state-of-the-art methods on the LIVE and TID 2013 databases.
In this paper, we train independent linear decoder models to estimate the perceived quality of images. More specifically, we calculate the responses of individual non-overlapping image patches to each of the decoders and scale these responses based on the sharpness characteristics of filter set. We use multiple linear decoders to capture different abstraction levels of the image patches. Training each model is carried out on 100,000 image patches from the ImageNet database in an unsupervised fashion. Color space selection and ZCA Whitening are performed over these patches to enhance the descriptiveness of the data. The proposed quality estimator is tested on the LIVE and the TID 2013 image quality assessment databases. Performance of the proposed method is compared against eleven other state of the art methods in terms of accuracy, consistency, linearity, and monotonic behavior. Based on experimental results, the proposed method is generally among the top performing quality estimators in all categories.