Efficient No-Reference Quality Assessment and Classification Model for Contrast Distorted Images

Abstract

In this paper, an efficient Minkowski Distance based Metric (MDM) for no-reference (NR) quality assessment of contrast distorted images is proposed. It is shown that higher orders of Minkowski distance and entropy provide accurate quality prediction for the contrast distorted images. The proposed metric performs predictions by extracting only three features from the distorted images followed by a regression analysis. Furthermore, the proposed features are able to classify type of the contrast distorted images with a high accuracy. Experimental results on four datasets CSIQ, TID2013, CCID2014, and SIQAD show that the proposed metric with a very low complexity provides better quality predictions than the state-of-the-art NR metrics. The MATLAB source code of the proposed metric is available to public at http://www.synchromedia.ca/system/files/MDM.zip.

arXiv comment6 pages, 4 figures, 4 tables

References in corpus (2)

• Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index
• Mean Deviation Similarity Index: Efficient and Reliable Full-Reference Image Quality Evaluator

Cited by in corpus (5)

• Light Field Image Quality Assessment With Auxiliary Learning Based on Depthwise and Anglewise Separable Convolutions
• Enhancement of Underwater Images with Statistical Model of Background Light and Optimization of Transmission Map
• Echocardiographic Image Quality Assessment Using Deep Neural Networks
• Robust Gesture-Based Communication for Underwater Human-Robot Interaction in the context of Search and Rescue Diver Missions
• Adaptive Navigation Scheme for Optimal Deep-Sea Localization Using Multimodal Perception Cues