Visible to the public Perceptual blur detection and assessment in the DCT domain

TitlePerceptual blur detection and assessment in the DCT domain
Publication TypeConference Paper
Year of Publication2015
AuthorsKerouh, F., Serir, A.
Conference Name2015 4th International Conference on Electrical Engineering (ICEE)
Date Publisheddec
KeywordsBBQM metric, blind blur quality metric, blind quality metric, Blurring, Correlation, Databases, DCT domain, discrete cosine transform, discrete cosine transforms, feature extraction, Image edge detection, Image resolution, image restoration, JNB concept, just noticeable blur concept, learning (artificial intelligence), machine learning system, Measurement, perceptual blur assessment, perceptual blur degradation, perceptual blur detection, pubcrawl170111, quality score, statistical analysis, statistical features, statistical modelling, subjective scores, Support vector machines

The main emphasis of this paper is to develop an approach able to detect and assess blindly the perceptual blur degradation in images. The idea deals with a statistical modelling of perceptual blur degradation in the frequency domain using the discrete cosine transform (DCT) and the Just Noticeable Blur (JNB) concept. A machine learning system is then trained using the considered statistical features to detect perceptual blur effect in the acquired image and eventually produces a quality score denoted BBQM for Blind Blur Quality Metric. The proposed BBQM efficiency is tested objectively by evaluating it's performance against some existing metrics in terms of correlation with subjective scores.

Citation Keykerouh_perceptual_2015