Title :
A method of image quality assessment based on imaging system parameters
Author :
Zhang, Wei ; Zhi, Xiyang ; Zhao, Ming
Author_Institution :
Res. Center for Space Opt. Eng., Harbin Inst. of Technol., Harbin, China
Abstract :
A new method of objectively assessing image quality is presented. This method deals with imaging system Modulation Transfer Function (MTF) and Signal to Noise Ratio (SNR), which are very important for image quality assessment based on matching accuracy requirements in the digital photogrammetric processing. Firstly, the main metrics affecting image quality is theoretically analyzed and mathematically modeled. Subsequently, variations of matching accuracy with MTF and SNR metrics are analyzed, and mathematical model between them is developed based on Back-Propagation Neural Network (BPNN). Finally, the model is verified using real aerial images. The model can be used to predict the effects of MTF and SNR metrics on the matching accuracy, then assess image quality and system design performance according to special matching accuracy requirements.
Keywords :
backpropagation; image matching; neural nets; optical transfer function; photogrammetry; BPNN; MTF; SNR; back-propagation neural network; digital photogrammetric processing; image quality assessment; imaging system parameters; matching accuracy; modulation transfer function; signal to noise ratio; Accuracy; Artificial neural networks; Image quality; Imaging; Mathematical model; Measurement; Signal to noise ratio; BPNN; MTF; SNR; digital photogrammetric processing; image quality assessment; matching accuracy requirements;
Conference_Titel :
Image and Signal Processing (CISP), 2010 3rd International Congress on
Conference_Location :
Yantai
Print_ISBN :
978-1-4244-6513-2
DOI :
10.1109/CISP.2010.5647787
