Learning the image processing pipeline
Abstract/Contents
- Abstract
- Many creative ideas are being proposed for image sensor designs, and these may be useful in applications ranging from consumer photography to computer vision. To understand and evaluate each new design, we must create a corresponding image-processing pipeline that transforms the sensor data into a form that is appropriate for the application. The need to design and optimize these pipelines is time-consuming and costly. We explain a method that combines machine learning and image systems simulation that automates the pipeline design. The approach is based on a new way of thinking of the image-processing pipeline as a large collection of local linear filters. We illustrate how the method has been used to design pipelines for novel sensor architectures in consumer photography applications.
Description
Type of resource | software, multimedia |
---|---|
Date created | May 2016 |
Creators/Contributors
Author | Jiang, Haomiao | |
---|---|---|
Author | Tian, Qiyuan | |
Author | Farrell, Joyce | |
Author | Wandell, Brian |
Subjects
Subject | camera image processing pipeline |
---|---|
Subject | digital camera |
Subject | demosaicking |
Subject | denoising |
Subject | machine learning |
Genre | Dataset |
Bibliographic information
Related Publication | Lansel, Steven, and Brian Wandell. "Local linear learned image processing pipeline." Imaging Systems and Applications 10 Jul. 2011: IMC3. |
---|---|
Related Publication | Tian, Qiyuan et al. "Automating the design of image processing pipelines for novel color filter arrays: Local, Linear, Learned (L3) method." IS&T/SPIE Electronic Imaging 7 Mar. 2014: 90230K-90230K-8. |
Related Publication | Jiang, Haomiao et al. "Local Linear Approximation for Camera Image Processing Pipelines.", Electronic Imaging, 2016 |
Related Publication | Tian, Qiyuan, and Haomiao Jiang. "Accelerating a learning–based image processing pipeline for digital cameras." (2015). |
Related item |
|
Location | https://purl.stanford.edu/bk962py0458 |
Access conditions
- Use and reproduction
- User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
- License
- This work is licensed under an Open Data Commons Attribution License v1.0.
Preferred citation
- Preferred Citation
- Jiang, Haomiao and Tian, Qiyuan and Farrell, Joyce and Wandell, Brian. (2016). Learning the image processing pipeline. Stanford Digital Repository. Available at: http://purl.stanford.edu/bk962py0458
Collection
Contact information
- Contact
- hjiang36@gmail.com
Also listed in
Loading usage metrics...