No-reference Image Quality Assessment using gradient-based Structural Integrity and Naturalness (Record no. 14685)

MARC details
000 -LEADER
fixed length control field 03632nam a22001697a 4500
082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER
Classification number 616.075
Item number K963N
100 ## - MAIN ENTRY--AUTHOR NAME
Personal name Kumar, Vineet
245 ## - TITLE STATEMENT
Title No-reference Image Quality Assessment using gradient-based Structural Integrity and Naturalness
Statement of responsibility, etc by Vineet Kumar
260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT)
Place of publication IIT Jodhpur
Name of publisher Department of Electrical Engineering
Year of publication 2017
300 ## - PHYSICAL DESCRIPTION
Number of Pages ix,38p.
Other physical details HB
520 ## - SUMMARY, ETC.
Summary, etc "Human perception can distinguish between visual qualities of images through psycho-visual (subjective)<br/>assessment. However, to impart this quality to a machine is a challenging task, and therefore,<br/>objective image quality assessment plays a vital role in quantifying the visual quality of an image.<br/>Image quality assessment (IQA) aims at designing a mathematical model to gauge the overall<br/>perceptual quality of an image based on the characteristics that are consistent with the subjective<br/>evaluations. IQA plays an important role in various applications such as image compression,<br/>restoration, enhancement, and video streaming. IQA serves the purpose of monitoring image quality,<br/>benchmarking enhancement algorithms, and optimizing parameters in restoration algorithms.<br/>Early research, focused in the area of full-reference methods (where a reference image is<br/>available for comparison), presented a good understanding of characterizing visual quality in terms<br/>error sensitivity, structural similarity, contrast and luminance similarity. As a good reference image<br/>may not be available in most practical applications, this project focuses on no-reference image quality<br/>assessment (NR-IQA). This project proposes a no-reference image quality metric of naturalness<br/>based on the hypothesis that every image has latent additive white Gaussian noise (AWGN). The<br/>quality score consists of four contributing parameters: gradient-based structural integrity, contrast<br/>deviation, and Gabor-based smoothness and naturalness. The final score is a weighted summation<br/>of each of these individual quality factors. A mathematical model was developed on a dataset of<br/>about hundred test images by computing gradient-based structural similarity of corrupted images<br/>w.r.t. the original. Statistical modeling of the observations was found to fit an exponential parametric<br/>model. The standard deviation of the latent (or apparent) AWGN present in any image<br/>was estimated using an SVD-based approach. The factor of no-reference gradient-based structural<br/>integrity (NRGSI) is then computed by a simple back-projection of the estimated noise deviation<br/>on the exponential model. This serves as the first contributing factor. Other contributory factors<br/>are similarly defined based on naturalness, contrast and texture effects of degradation in an image.<br/>Mathematical modeling was performed using four hundred and fifteen natural/noisy images<br/>from standard databases. The proposed approach was further tested on a total of one hundred and<br/>sixty-two images. The overall performance of the proposed no-reference image quality metric is<br/>quantified by calculating the Spearman Rank Order Correlation Coefficient (SRCC) that denotes<br/>the accuracy of objective evaluation with respect to subjective (human visual) evaluation. The<br/>proposed IQA metric displays noteworthy performance (with an accuracy of 80% in terms of SRCC).<br/>In comparison with other state-of- the-art metrics, the proposed metric displays better, and in some<br/>cases, comparable performance.<br/>i"<br/>
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical Term Image Quality Assessment
Topical Term MTech Theses
Topical Term Department of Electrical Engineering
700 ## - ADDED ENTRY--PERSONAL NAME
Personal name Chouhan, Rajlaxmi
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Koha item type Thesis
Holdings
Withdrawn status Lost status Damaged status Not for loan Collection code Permanent Location Current Location Shelving location Date acquired Full call number Accession Number Price effective from Koha item type
      Not For Loan Reference S. R. Ranganathan Learning Hub S. R. Ranganathan Learning Hub Course Reserve 2024-01-18 616.075 K963N TM00108 2024-01-18 Thesis