We present a study of the in-camera image processing through an extensive analysis of more than 10,000 images from over 30 cameras. The goal of this work is to investigate if image values can be transformed to physically meaningful values, and if so, when and how this can be done. From our analysis, we found a major limitation of the imaging model employed in conventional radiometric calibration methods and propose a new in-camera imaging model that fits well with today’s cameras. With the new model, we present associated calibration procedures that allow us to convert sRGB images back to their original CCD RAW responses in a manner that is significantly more accurate than any existing methods. Additionally, we show how this new imaging model can be used to build an image correction application that converts an sRGB input image captured with the wrong camera settings to an sRGB output image that would have been recorded under the correct settings of a specific camera.
We also describe a method to construct a sparse lookup table (LUT) that is effective in modeling the camera imaging pipeline that maps a RAW camera image to its sRGB output based on the new aforementioned color processing model. We show how to construct a LUT using a novel nonuniform lattice regression method that adapts the LUT lattice to better fit the underlying 3D function which was previously formulated as a RBF function. Our method offers not only a performance speedup of an order of magnitude faster than RBF, but also a compact mechanism to describe the imaging pipeline.
Cybersecurity Awareness Training Presentation v2024.03
Creating Picture Legends For Group Photos
1. Creating Picture Legends for
Group Photos
Junhong Gao† Seon Joo Kim‡ Michael S. Brown†
† School of Computing ,National University of Singapore
‡ Department of Computer Science, SUNY Korea
2.
3.
4. • Automatic Human Body and Face Detections
- Face detection: Viola et al. , Lienhart et al. …
- Human body detection: Dalal et al., Zhu et al. …
• Interactive Image Segmentation
- Boundary based: Kass et al., Mortensen et al. …
- Scribble based: Li et al., Rother et al. …
- Paint based: Liu et al. …
5.
6. 1 2 3
Face Detection Person-wise
with Adjustment rectangle cropping
5 Final Legend 4 User Interactive
Result Refinement
Initial Automatic Segmentation
9. • Segmentation formulated as a Markov-Random-
Field(MRF):
• Data term is defined by color mixture model and head-
and-shoulder/body prior
R
G B
×
10. • Segmentation formulated as a Markov-Random-
Field(MRF):
• Data term is defined by color mixture model and head-
and-shoulder/body prior
• Smoothness is based on intensity difference of adjacent
pixels with different labels.
11.
12.
13. - -
• Over 100 manually
segmented training
data
14. - -
• Over 100 manually
segmented training
data
1.0
0.0
15. - -
B F
H
U
F B
Background region
Unknown region
Hair region
Foreground region
17. • Label from starting point of the
scribble is set to be foreground L4
label
• All the labels that the scribble L3
L1
covered are set to be unknown
labels
L2
• Other labels are fixed as
background labels
29. • Presented a framework to create picture legends from
group photos.
• Proposed our head-and-shoulder and upper body
prior to assist the segmentation
• Simplified a multi-labeled MRF problem into a
consecutive binary segmentation problem