作者: Peter Durlak , Stefan Boehm , Tong Fang , Michelle Xiao-Hong Yan , Markus Lendl
DOI:
关键词: Image quality 、 Enhanced Data Rates for GSM Evolution 、 Computer science 、 Luminance 、 Quality (business) 、 Artificial intelligence 、 Region of interest 、 Contrast (vision) 、 Image compression 、 Computer vision 、 Block (programming)
摘要: A method and system for image quality assessment is disclosed. The a no-reference objectively assessing the of medical images. This guided by human vision model in order to accurately reflect perception. region interest (ROI) divided into non-overlapping blocks equal size. Each categorized as smooth block, texture or an edge block. perceptual sharpness measure, which weighted local contrast, calculated each blocks. noise level background luminance, index determined based on measures all blocks, An overall can be using task specific machine learning samples annotated used applications, such video/image compression storage healthcare homeland security, band-width limited wireless communication.