No abstract

No abstract

This paper describes a newly-created image database termed as the NITS-IQA database for image quality assessment (IQA). In spite of recently developed IQA databases, which contain a collection of a huge number of images and type of distortions, there is still a lack of new distortion and use of real natural images taken by the camera. The NITS-IQA database contains total 414 images, including 405 distorted images (nine types of distortion with five levels in each of the distortion type) and nine original images. In this paper, a detailed step by step description of the database development along with the procedure of the subjective test experiment is explained. The subjective test experiment is carried out in order to obtain the individual opinion score of the quality of the images presented before them. The mean opinion score (MOS) is obtained from the individual opinion score. In this paper, the Pearson, Spearman and Kendall rank correlation between a state-of-the-art IQA technique and the MOS are analyzed and presented.

Abstract-In literature, oriented filters are used for low-level vision tasks. In this paper, we propose use of steerable Gaussian filter in image quality assessment. Human visual system is more sensitive to multidirectional edges present in natural images. The most degradation in image quality is caused due to its edges. In this work, an edge based metric termed as steerable Gaussian filtering (SGF) quality index is proposed as objective measure for image quality assessment. The performance of the proposed technique is evaluated over multiple databases. The experimental result shows that proposed method is more reliable and outperform the conventional image quality assessment method.

Wavelet transform is one of the most active areas of research in the image processing. This paper gives analysis of a very well known objective image quality metric, so called Structural similarity, MSE and PSNR which measures visual quality between two images. This paper presents the joint scheme of wavelet transform with structural similarity for evaluating the quality of image automatically. In the first part of algorithm, each distorted as well as original image are decomposed into three levels and in second part, these coefficient are used to calculate the structural similarity index, MSE and PSNR. The predictive performance of image quality based on the wavelet families like db5, haar (db1), coif1 with one, two and three level of decomposition is figured out. The algorithm performance includes the correlation measurement like Pearson, Kendall, and Spearman correlation between the objective evaluations with subjective one.