Inverse synthetic aperture radar image quality assessment based on PSO-BP neural network

ABSTRACT

Based on particle swarm optimization-back propagation (PSO-BP) neural network, a novel inverse synthetic aperture radar (ISAR) image quality assessment (IQA) method is proposed to address the challenge of selecting high-quality ISAR images from a large number of images. This method incorporates six assessment metrics: energy gradient (EG), effective area ratio of image (EARI), image contrast (IC), image entropy (IE), equivalent number of looks (ENL), and signal-to-noise ratio (SNR) to evaluate the quality of ISAR images. The PSO-BP neural network is employed to fit the relationship between these metrics and ISAR image quality. Experimental results show that the new method is effective in ISAR-IQA under different imaging conditions and various attitudes, and closely matches the subjective evaluation of experts.

KEYWORDS:

• Inverse synthetic aperture radar
• image quality assessment
• PSO-BP neural network

Acknowledgements

This work is supported in part by National Natural Science Foundation of China (No. 62371477), Guangdong Science and Technology Program (No. 2019ZT08X751),and Shenzhen Science and Technology Program (No.KQTD20190929172704911).

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The work was supported by the National Natural Science Foundation of China [No. 62371477]; Guangdong Science and Technology Program [No. 2019ZT08X751]; Shenzhen Science and Technology Program [No.KQTD20190929172704911].