Image Signal Processor (ISP) Tuning using Machine Learning (ML) methods

Image Signal Processor (ISP) is responsible for improving camera signal quality and producing high-quality images. ISP has a vast number of parameters which should be tunned based on both camera sensor and operating environment. Sensor related ISP parameters are tunned offline for each camera sensor. Parameters related to environment such as white balancing gains must be fine-tuned during the runtime. The offline phase is cumbersome and costly. At the same time, the runtime for fine-tuning should be fast and accurate. Therefore, the proposed tuning framework needs to achieve two goals at the same time: a) tune the sensor related parameters automatically in lab and b) fine-tuning ISP in the field with a runtime.