An Effective feature set in Quality Estimation of Natural Scene Statistics Images
Gopika S1, Malathi D2, K.Kalaiselvi3

1Gopika S*, Department of Computer Science, Kristu Jayanti College, Karnataka, India.
2Malathi D, Department of Computer Science & Engineering, SRM IST, Chennai, India
3K Kalaiselvi, Department of Computer Science, Kristu Jayanti College, Karnataka, India. 

Manuscript received on November 15, 2019. | Revised Manuscript received on 20 November, 2019. | Manuscript published on December 10, 2019. | PP: 2881-2888 | Volume-9 Issue-2, December 2019. | Retrieval Number: B7899129219/2019©BEIESP | DOI: 10.35940/ijitee.B7899.129219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Quality estimation in images is an area which demands high attention of researchers. Many recent algorithms in Image quality assessment relies on the computation of definite values from the image or comparison with the original pristine image. Here, we propose the extraction of a set of specific features from image and processing is done on these extracted features to obtain the objective quality score. The detailed inspection of behaviour of this set of highly specific image features extracted through less complex mathematical procedure from a collection good quality and low quality set of Natural Scene Statistics images available in LIVE dataset is elaborated in this work. Our studies and results are compared with the subjective opinion value and is proven to be accurate. The obtained results are demonstrated using statistical and graphical manner for promptness in understanding the nature of quality of the image. Thus the proposed feature set is proven to be complete in assessing the quantitative quality value of any Natural image. 
Keywords: Distortion, Generalized Gaussian Derivative, Natural Scene Statistics, Normalized Luminance Coefficients.
Scope of the Article: Signal and Image Processing