UNIQUE: Unsupervised Image Quality Estimation

Abstract

In this paper, we estimate perceived image quality using sparse representations obtained from generic image databases through an unsupervised learning approach. A color space transformation, a mean subtraction, and a whitening operation are used to enhance descriptiveness of images by reducing spatial redundancy; a linear decoder is used to obtain sparse representations; and a thresholding stage is used to formulate suppression mechanisms in a visual system. A linear decoder is trained with 7 GB worth of data, which corresponds to 100,000 8x8 image patches randomly obtained from nearly 1,000 images in the ImageNet 2013 database. A patch-wise training approach is preferred to maintain local information. The proposed quality estimator UNIQUE is tested on the LIVE, the Multiply Distorted LIVE, and the TID 2013 databases and compared with thirteen quality estimators. Experimental results show that UNIQUE is generally a top performing quality estimator in terms of accuracy, consistency, linearity, and monotonic behavior.

12 pages, 5 figures, 2 tables

References in corpus (1)

• PerSIM: Multi-resolution Image Quality Assessment in the Perceptually Uniform Color Domain

Cited by in corpus (5)

• Perceptual Image Quality Assessment through Spectral Analysis of Error Representations
• On the Space-Time Statistics of Motion Pictures
• Probing the Purview of Neural Networks via Gradient Analysis
• Generating Adaptive and Robust Filter Sets Using an Unsupervised Learning Framework
• Boosting in Image Quality Assessment