A no reference perceptual blur quality metric in the DCT domain
Title | A no reference perceptual blur quality metric in the DCT domain |
Publication Type | Conference Paper |
Year of Publication | 2015 |
Authors | Kerouh, F., Serir, A. |
Conference Name | 2015 3rd International Conference on Control, Engineering Information Technology (CEIT) |
Date Published | May 2015 |
Publisher | IEEE |
ISBN Number | 978-1-4799-8212-7 |
Keywords | blind blur quality measures, blind objective metrics, blind quality metric, blind source separation, blur distortion, Blurring, blurring affects, Databases, DCT domain, digital imaging systems, discrete cosine transform, Discrete Cosine Transform (DCT), discrete cosine transforms, edges, fine image details, frequency domain, frequency-domain analysis, human visual system, Image edge detection, image high frequency components, image restoration, JNB, just noticeable blur concept, Just Noticeable Blur threshold (JNB), no reference perceptual blur quality metric, PBBQM, perceived image quality degradation, perceptual blind blur quality metric, perceptual no reference blur assessment metric, pubcrawl170111, subjective quality scores, Visual systems, wavelet transforms |
Abstract | Blind objective metrics to automatically quantify perceived image quality degradation introduced by blur, is highly beneficial for current digital imaging systems. We present, in this paper, a perceptual no reference blur assessment metric developed in the frequency domain. As blurring affects specially edges and fine image details, that represent high frequency components of an image, the main idea turns on analysing, perceptually, the impact of blur distortion on high frequencies using the Discrete Cosine Transform DCT and the Just noticeable blur concept JNB relying on the Human Visual System. Comprehensive testing demonstrates the proposed Perceptual Blind Blur Quality Metric (PBBQM) good consistency with subjective quality scores as well as satisfactory performance in comparison with both the representative non perceptual and perceptual state-of-the-art blind blur quality measures. |
URL | https://ieeexplore.ieee.org/document/7233043 |
DOI | 10.1109/CEIT.2015.7233043 |
Citation Key | kerouh_no_2015 |
- PBBQM
- human visual system
- Image edge detection
- image high frequency components
- image restoration
- JNB
- just noticeable blur concept
- Just Noticeable Blur threshold (JNB)
- no reference perceptual blur quality metric
- frequency-domain analysis
- perceived image quality degradation
- perceptual blind blur quality metric
- perceptual no reference blur assessment metric
- pubcrawl170111
- subjective quality scores
- Visual systems
- wavelet transforms
- blind blur quality measures
- frequency domain
- fine image details
- edges
- discrete cosine transforms
- Discrete Cosine Transform (DCT)
- discrete cosine transform
- digital imaging systems
- DCT domain
- Databases
- blurring affects
- Blurring
- blur distortion
- blind source separation
- blind quality metric
- blind objective metrics