While intelligent cameras are beginning to disrupt the use of conventional cameras, it is still not easy to effectively integrate the many new optics, sensors, and processors. This growing choice in components provides better options to improve cost, performance, and image quality for each product and variant, but means ISPs often need to be re-engineered. In turn, this exercise consumes more valuable time and resources from the research and development team, or hard costs if the process is outsourced to a third party.

Introducing CRISP-EC ISP

A software-based image processor that is optimized holistically for final image quality means that errors are minimized and changes can be implemented on the fly. Instead of working linearly and compounding the errors at each stage in the image signal processing pipeline, CRISP-EC dynamically optimizes for final image quality and balances all the different functions.

This is especially useful for companies working on embedded high-performance computational or computer vision cameras or post-processing images in the cloud. Whether they are focused on innovative cameras or new applications, their ISP work can be minimized and allow the development team to funnel energy into their core mission. The availability of a software ISP for next-generation cameras and cloud-based applications will accelerate innovation and push the limits of image quality.

Conventional camera pipeline

Separate processes aggregate errors

Traditional ISP


  • Each imaging process is an IP block, separately integrated to optics and hardware, which vary across devices.
  • The RAW imaging data is referred to only at the outset; each process then creates errors that carry over across the pipeline.
  • These errors are aggregated, creating suboptimal image & use of resources. For OEMs, this means a painstaking integration and testing, often delaying production.


A unified framework optimizes for quality



  • CRISP-EC is a software image reconstruction engine that incorporates all processes into one unified framework.
  • The Reconstruction Engine iterates based on the RAW imaging data, ensuring errors are minimized.
  • The framework’s objective is to optimize final image quality based on input variables. This leads to higher quality images, simple integration, and a better use of resources.
  • Approach unlocks new cloud-based processing applications and business models