Automatic image quality tuning framework for optimization of ISP parameters based on multi-stage optimization approach

Abstract

Image signal processors (ISP) plays a significant role in camera systems by converting the RAW image from image sensor to a processed image. In order to achieve best image quality, the ISP parameters have to be configured in an iterative manner for various lighting conditions and scenarios, which is carried out by a camera tuning engineer. Usually, the manual tuning process takes up to several weeks to months due to huge number of ISP parameters to be optimized and the iterations involved to achieve good image quality. In this paper, we present a novel approach to automatically tune ISP parameters based on a multi-stage multi-criteria optimization approach using Non sorted Genetic algorithm (NSGA-II) for achieving objective and subjective image quality. In this approach, we focus on important blocks in ISP such as noise reduction, sharpness and tone mapping for human vision use-cases for camera systems widely used for smart phones or smart home IoT devices. The experiments for validating our approach are carried out under different scenarios using Qualcomm’s Spectra 380 ISP simulator and OV13880 sensor and the performance of automatic tuned IQ is compared with manual tuned IQ and some of the previous works done for automatically tuning ISP parameters. With the automatic ISP tuning approach, we verify the significant performance improvement in terms of IQ metrics and time consumed for the tuning process when compared to manual tuning approach.