Studying the Effect of ROI on Image Quality Using ERPS

T246 effect of region of interest (ROI) on the overall image quality assessment was studied using subjective rating method and objective psychophysiology measurement methods (e.g., event-related potentials (ERPs) technology). Different image quality was acquired by compressing only the ROI or background area with different $\boldsymbol{\sigma}$ values of Gaussian Kernel Function. Also, the amplitude and latency of P300 (ERPs component at about 300–550ms) changed with different compressed types. The ROI compressed stimuli had earlier and higher P300 component than that of NROI compressed stimuli. The results showed that it was easier to detect the difference between original image and impaired image of ROI compressed stimuli than that of NROI compressed stimuli.

[1]  Yan Tu,et al.  A Study on the Relationship Between Event-Related Potentials and Image Quality Variation , 2016, Journal of Display Technology.

[2]  Ulrich Engelke,et al.  Visual Attention in Quality Assessment , 2011, IEEE Signal Processing Magazine.

[3]  Marcus A. Magnor,et al.  Assessing the quality of compressed images using EEG , 2011, 2011 18th IEEE International Conference on Image Processing.

[4]  Christopher Joseph Pal,et al.  Learning Conditional Random Fields for Stereo , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Lina J. Karam,et al.  A No-Reference Objective Image Sharpness Metric Based on the Notion of Just Noticeable Blur (JNB) , 2009, IEEE Transactions on Image Processing.

[6]  Marcus A. Magnor,et al.  Evaluation of video artifact perception using event-related potentials , 2011, APGV '11.