Digital Camera Image Quality Tuning

Course Number: SC05

Sunday 26 January • 8:00 – 12:15
Course Length: 4 hours
Course Level: Intermediate
Instructor:  Luke Cui, Amazon

Learning Outcomes
This course enables the attendee to understand:

  • The goals of image quality tuning.
  • Hardware capabilities based on specification.
  • Capabilities of the image processing pipelines.
  • Objective image quality metrics and standards applicable to tuning.
  • Overview of the image quality tuning process.
  • Tunings tools and their development.
  • Deep dive into the tuning process.
  • Camera per module factory calibration.
  • 3A tuning processes and steps.
  • Scene classification, analysis, and measurement.
  • Camera geometric and radiometric defect and distortion corrections.
  • De-mosaicking, color transformation and correction.
  • Tone curves, LUTS and their significance.
  • Denoising, noise masking and substitution.
  • Tone and color preference tuning.
  • Subjective image quality and competitive benchmarking for tuning.
  • Tuning for autonomous robots.
  • Application of deep neural networks to tuning.
  • Tracking the performance of best performance smartphone cameras.

Digital camera image quality tuning is critical in the camera development process. It is an interdisciplinary field that is as much art as science. It is also a treacherous engineering process that is full of pseudoscience pitfalls and prone to engineering blunders. This course intends to prepare perspective professionals for that process starting from fundamental science and techniques to the evaluation of current competitive smartphone cameras.

Intended Audience
Camera and imaging engineers, scientists, students, and program managers.

Luke Cui has been hands-on working on imaging systems for over thirty years with a BS in optics, MS in color science and PhD in human vision. He has been involved with the delivery of numerous market proven digital imaging systems, working from photons, lenses, sensors, cameras, color science, imaging processing, image quality evaluation systems, to psychophysics and human vision. He has more than sixty patents and patent applications. He has worked for Macbeth Co. on standard lighting, color formulation, spectrophotometry, and colorimetry; led high speed document scanner optical imaging system development at Lexmark International, working from lens design to final image pipeline tuning; and led camera tuning of most Surface products on the market at Microsoft, covering from system specification, ISP evaluation, selection, and all phases of camera tuning. Currently, he is a principal imaging scientist at Amazon Prime Air, working on sensing systems for autonomous drones. Disclaimer: Opinions and content covered by the course are solely his own and do not express the views or opinions of his employer, past and present.

1/26/2020 8:00 AM - 1/26/2020 12:15 PM