Computer Vision Seminar – Color Imaging
Course Homepage:
http://cs.haifa.ac.il/hagit/courses/seminars/colorImaging/colorImaging.html
You must choose a topic. Your lecture must include at least 2 different papers
(2 approaches or 2 problems etc) as well
as a paper on the topic using Machine Learning from the last 4 years which you
can either cover in details or briefly.
Please choose 3 topics that which you would like to present in order of
preference.
List the Lecture number as well as the title.
I cant promise but will do my best to accommodate
you.
Send your list to me at hagit@cs.haifa.ac.il
with the subject: Seminar Topics
For fair play – send the email NOT BEFORE 21:00 Tonight
6/3/23
(Note: I will NOT read an email if arrived before 21:00).
Lecture 1 – Intro (13/03/23)
Topics: The eye and retina, cone and rod
sensors, image formation model, vector representation for color computation,
Resources: "Foundations of Vision" (book) by Brian A. Wandell
https://foundationsofvision.stanford.edu/
Chapter 3: The photoreceptor Mosaic
only up to Visual Interferometry (not
included)
Chapter 4: Wavelength Encoding
From: Photopic Wavelength Encoding up to and not including: A Standard Set of
Color-Matching Functions
Also: The Biological Basis of Photopic Color-matching
Also: Cone Photopigments and Color-matching
Chapter 9: Color
Spectral Image Formation up to and not including Sensor-based error measures
then up to Color Constancy: Experiments
Note: before talking about Linear Models (of illumination) explain
representation of spectral data by vectors and
talk about Linear Systems Methods in Chapter 2.
Also, can use slides from: IST01_Eye, IST02_Color, IST06_ImageFormation
Lecture 2– Color Spaces (20/03/23)
Topics: linear color spaces, XYZ,
opponent color spaces: HSV, YIQ, YUV
perceptual color spaces (non linear): LAB , SCIELAB
Resources: "Foundations of Vision" (book) by Brian A. Wandell
https://foundationsofvision.stanford.edu/
Chapter 9: color
The Perceptual Organization of Color up to and not including The Cortical Basis
of Color Appearance
Find additional sources online
Also, can use slides from: IST03_ColorXYZ,
IST04_ColorOpponent, IST05_ColorLAB
Lecture 3
Color Segmentation - K-Means + Mean Shift () SKIP THIS TALK
Classic k-mean – Duda and Hart "Pattern Recognition"
Fast Image
Segmentation Based on K-Means
Clustering with
Histograms in HSV Color Space
Tse-Wei Chen 1, Yi-Ling Chen 2,
Shao-Yi Chien
http://www.murase.nuie.nagoya-u.ac.jp/~twchen/paper/mmsp08_seg.pdf
Segmentation by Fusion of
Histogram-Based
K-Means Clusters
in Different Color Spaces
Max Mignotte
http://www.iro.umontreal.ca/~mignotte/Publications/IEEE_IP08.pdf
K-Means and EM
David Jacobs
http://www.cs.umd.edu/~djacobs/CMSC828seg/EM.pdf
D. Forsyth
http://luthuli.cs.uiuc.edu/~daf/courses/CS5432009/Week%206/EMSeg.pdf
Expectation-Maximization Algorithm
and Image Segmentation
Daozheng Chen
http://www.cs.umd.edu/~dchen/papers/CMSC660_Term_Project.pdf
Mean Shift: A Robust Approach Toward Feature
Space Analysis
D. Comaniciu and P. Meer
Pami 24(5) 2002
https://courses.csail.mit.edu/6.869/handouts/PAMIMeanshift.pdf
http://www.cse.yorku.ca/~kosta/CompVis_Notes/mean_shift.pdf
http://homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_COPIES/TUZEL1/MeanShift.pdf
Improved mean shift segmentation approach for natural
images
Yiping Hong , Jianqiang Yi
and Dongbin Zhao .
(cant find online)
Mean Shift Based Clustering in High Dimensions: A Texture
Classification
Example
Bogdan Georgescu, Ilan Shimshoni and Peter Meer
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.117.9132&rep=rep1&type=pdf
D. Comaniciu, V. Ramesh, and P. Meer. Kernel-based
object tracking. IEEE
Trans. Pattern
Analysis Machine Intelligence, 25(5):564–577, May 2003.
Color image
segmentation using mean shift and improved ant clustering
LIU Ling-xing, TAN Guan-zheng M.
Sami Solima
http://edu.zndxzk.com.cn/down/upfile/soft/20120410/24-p1040-E110034.pdf
Lecture 4 Color Segmentation - Graph-Cut / Normalized
Cut segmentation (27/3/2023)
Topics: Images as graphs, Min-cut, normalized-cut, Laplacian Matrix,
multi-segment cuts,
interactive segmentation (using GMM)
J. Shi and J.Malik,
“Normalized Cuts and Image Segmentation,” Proc. CVPR 1997.
also
IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8), 888-905,
August 2000.
http://www.cs.berkeley.edu/~malik/papers/SM-ncut.pdf
Boykov, Y., Jolly, M., "
Interactive graph cuts for optimal boundary and region
segmentation of objects in N-D images." In: International Conference on
Computer
Vision, Vancouver , BC. (2001) 105–112
http://www.csd.uwo.ca/faculty/yuri/Papers/iccv01.pdf
Boykov, Y., Veksler,
O., Zabih, R.: Fast approximate energy
minimization via
graph cuts. IEEE Trans.
Pattern Anal. Mach. Intell. 23 (2001) 1222–1239
http://www.csd.uwo.ca/faculty/yuri/Abstracts/pami01-abs.html
Good slides on Graph rep
http://web.cs.hacettepe.edu.tr/~erkut/bbm413.f13/w13-segmentation-b-4pp.pdf
Lecture 5 – Image Recoloring –
(17/4/2023)
Topics to
cover: Colorization by Example, Using Similar Images
Colorization by Example
Revital Irony, Daniel Cohen-Or,
and Dani Lischinski
EGSR 2005
http://www.cs.tau.ac.il/~dcor/online_papers/papers/colorization05.pdf
“Intrinsic colorization,”
X. Liu, L. Wan, Y. Qu, T.-T. Wong, S. Lin, C.-S. Leung, and P.-A. Heng,
ACM Transactions on Graphics (Proc. of SIGGRAPH Asia), vol. 27, no. 3, pp. 152
(1–9), 2008
http://www.cse.cuhk.edu.hk/~ttwong/papers/incolor/paper/incolor.pdf
Image Colorization Using Similar Images
Raj Kumar Gupta1, Alex
Yong-Sang Chia2, Deepu Rajan, Ee Sin Ng2 and Huang Zhiyong
http://people.cs.clemson.edu/~jzwang/1301863/mm2012/p369-gupta.pdf
Automatic Image
Colorization via Multimodal Predictions
Guillaume Charpiat , Matthias Hofmann , Bernhard Schölkopf
http://130.203.133.150/viewdoc/download?doi=10.1.1.165.8029&rep=rep1&type=pdf
Inducing Semantic
Segmentation from an Example
Yaar Schnitman, Yaron Caspi, Daniel Cohen-Or, and Dani Lischinski
ACCV2005
http://www.cs.tau.ac.il/~dcor/online_papers/papers/Yaar05.pdf
Lecture 6 - Color based Forgery detection - Chromatic Aberration (1/5/2023)
Topics to
cover: Forgery intro, Chromatic aberration explained,
Forgery detection based on
chromatic aberration
A.C. Popescu and H. Farid,
‘Exposing digital forgeries through chromatic aberration’,
ACM Multimedia and
Security Workshop, pp. 48–55, 2006.
T.V. Lanh, S. Emmanuel, and M.S. Kankanhalli,
I. Yerushalmy and H. Hel-Or,
‘Digital image
forgery detection based on lens and sensor aberration’,
International Journal
of Computer Vision, vol. 92, no. 1, pp. 71–91, 2011
Owen Mayer and Matthew C. Stamm
Accurate and Efficient Image Forgery Detection Using Lateral
Chromatic Aberration
TIFS 2018
https://misl.ece.drexel.edu/wp-content/uploads/2018/02/Mayer_TIFS_2018.pdf
Lecture 7 – Shadow Removal from Images (8/5/23)
Topics to
cover: Intrinsic image, invariant color models, using anchor
points,
Shadow removal from Image
Sequences
Eli Arbel and Hagit Hel-Or
Texture-Preserving Shadow Removal in Color Images Containing Curved Surfaces
CVPR 2007
https://cs.haifa.ac.il/hagit/papers/CONF/CVPR07_ArbelHelOr-shadowRemoval.pdf
Graham D. Finlayson, Steven D. Hordley,
and Mark S. Drew,
"Removing Shadows From Images using Retinex",
Color Imaging Conference, pp. 73-79, November 2002.
http://www.cs.sfu.ca/~mark/ftp/Cic10/cic10retinex.pdf
http://citeseer.ist.psu.edu/710866.html
In Journal of Optical Society of America, A, Vol 18 (2), pp253-264, 2001.
G. D. Finlayson and S. D. Hordley,
and M. S. Drew "
Recovery of chromaticity image free from shadows via illumination
invariance",
In Proceedings International Conference on Computer Vision,
Workshop on Colour and Photometric Methods
in Vision, 2003.
http://www.cs.sfu.ca/~mark/ftp/Iccv03ColorWkshp/iccv03wkshp.pdf
E. Salvador, P. Green, and T. Ebrahimi.
Shadow
identification and classification using invariant color models.
In
Proceedings of ICASSP 01, volume 3, pages 1545--1548. IEEE, 2001.
http://www.elec.qmul.ac.uk/staffinfo/andrea/papers/icassp01.pdf
Cast shadow segmentation using invariant color features
Elena Salvador,a Andrea Cavallaro,b,* and Touradj Ebrahimi
http://lts1pc19.epfl.ch/repository/Salvador2004_774.pdf
Color Invariance
J.M. Geusebroek, R. van den Boomgaard, A.W.M. Smeulders, H. Geerts
IEEE PAMI December 2001 (Vol. 23, No. 12) pp. 1338-1350
Shadow removal
from a real picture
International
Conference on Computer Graphics and Interactive Techniques archive
Masashi Baba
Naoki Asada
Proceedings of the
SIGGRAPH 2003 conference on Sketches & applications
Shadow Removal from a Real Image Based on Shadow Density
Masashi
Baba Masayuki Mukunoki Naoki
Asada
http://www.cv.its.hiroshima-cu.ac.jp/~baba/Shadow/
Improving Shadow Suppression in Moving Object Detection
with HSV Color Information
Rita Cucchiara, Costantino Grana, Massimo Piccardi, Andrea Prati,
Stefano Sirotti
Y. Weiss. Deriving intrinsic images
from image sequences. In ICCV01, pages II:
68{75. IEEE, 2001.
http://www.cs.huji.ac.il/~yweiss/iccv01.pdf
Y. Matsushita and
K. Nishino, “Illumination normalization with time-dependent intrinsic images
for video surveillance,” IEEE
Trans. Pattern Anal. Mach. Intell., 26, pp. 1336-1348 (2004).
http://www.cvl.iis.u-tokyo.ac.jp/papers/all/650.pdf
Saritha Murali and V. K. Govindan and Saidalavi Kalady
Single image shadow removal by optimization using non-shadow
anchor values
Computational Visual Media volume 5, pages311–324(2019)
https://link.springer.com/content/pdf/10.1007/s41095-019-0148-x.pdf
Lecture 8 –
Heart Rate from RGB (15/5/23)
Remote heart rate measurement using low-cost RGB face video: a
technical literature review
Philipp V. ROUAST, Marc T.P. ADAM, Raymond CHIONG , David
CORNFORTH
Frontiers in CS, 2016
https://www.rouast.com/pdf/rouast2016remote_a.pdf
Contactless and Hassle Free Real Time Heart Rate Measurement with
Facial Video
Shubham Pratap Singh, Neeru Rathee1 Harsh Gupta, Paolo Zamboni,
Ajay Vikram Singh
TSS-ISCU
https://d-nb.info/1170111076/34
Real Time Heart Rate Monitoring from Facial RGB Color Video Using
Webcam
May 2016
Workshop of the Swedish Artificial Intelligence Society (SAIS
2016)At: Malmö
Hamidur Rahman, Mobyen
Uddin Ahmed, Shahina Begum, Peter Funk
https://ep.liu.se/ecp/129/002/ecp16129002.pdf
Dynamic heart rate measurements from video sequences
Yong-Poh Yu,1,* P. Raveendran,1,2 and Chern-Loon Lim1,3
Biomed Opt Express 2015
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4505702/
RhythmNet: End-to-end Heart Rate Estimation from Face
via Spatial-temporal Representation
Xuesong Niu, Shiguang Shan, Hu Han, Member, Xilin
Chen
https://arxiv.org/pdf/1910.11515.pdf
Heart Rate Measurement Using Facial Videos
Garima Uppal, Neelam Rup Prakash, Parveen Kalra
Advances in Computational Sciences and Technology Volume 10,
Number 8 (2017)
https://www.ripublication.com/acst17/acstv10n8_14.pdf
Lecture 9 –
Emotion detection from RGB sequences (22/5/23)
Topics to cover: what is emotion, Action
Unites, micro emotions
color spaces for face analysis,
Micro expression detection from RGB sequences.
Facial color is an efficient mechanism to visually transmit emotion.
C. F. Benitez-Quiroz, R. Srinivasan, and A. M. Martinez.
Proceedings of the National Academy of Sciences,
115(14):3581–3586, 2018.
Micro-expression recognition using color spaces. IEEE Transactions
on Image Processing,
S.-J. Wang, W.-J. Yan, X. Li, G. Zhao, C.-G. Zhou, X. Fu, M. Yang,
and J. Tao.
24(12):6034–6047, 2015.
Micro Expression classification using facial color and deep
learning methods
Hadas Shahar and Hagit Hel
CVPR workshop – 2019
Lecture - Face Detection Using Color () SKIP THIS TALK
Survey:
A Survey on Pixel-Based Skin Color Detection Techniques
Vladimir Vezhnevets ∗. Vassili
Sazonov. Alla Andreeva
GRAFICON
http://graphicon.ru/oldgr/en/publications/text/gc2003vsa.pdf
A
Robust Skin Color Based Face Detection Algorithm,
Sanjay Kr. Singh , D.
S. Chauhan , Mayank Vatsa , Richa Singh
Journal of Science and Engineering, 2003
http://www.csee.wvu.edu/~mayankv/papers/tkjse.pdf
Robust
Face Detection Combined Skin Color Features, Template Matching and VQ Histogram
Method
Qiu Chen, Koji Kotani, Yoshiyuki
Taniguchi, Zhibin Pan, and Tadahiro Ohmi
in Practical Environmentsh, Intelligent
Automation and Soft Computing, Vol. 10, No. 2, pp. 143-154, 2004.
http://wacong.org/autosoft/vol10/10_2/6.pdf
Face Detection
in Still Color Images Using Skin Color Information
Amine, Ghouzali and Rziza
Proceedings ISCCSP2006
http://www.eurasip.org/Proceedings/Ext/ISCCSP2006/defevent/papers/cr1268.pdf
Detecting
human faces in color images
J. Cai , A. Goshtasby
Image and Vision Computing, 1999
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.122.9898&rep=rep1&type=url&i=0
http://www.cs.wright.edu/~agoshtas/facechroma.html
D. Chai and
K. N. Ngan,
``Face Segmentation Using Skin-Color Map in Videophone Applications'',
IIEEE Trans. Circuits Sys. Video Tech., vol. 9, no. 4, pp. 551-564, June 1999
http://suraj.lums.edu.pk/~cs504m04/csvt99.pdf
Comparison
of Five Color Models in Skin Pixel Classification
Benjamin D. Zarit , Boaz J.
Super , Francis K. H. Quek
ICCV’99 Int’l Workshop on Color 1999
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.129.9666&rep=rep1&type=url&i=0
Lecture 10 – Demosaicing (29/5/23)
Topics to cover: Camera structure, sensors,
what is Demosiacing. demosaicing
artifacts
Demosaicing techniques.
Image Demosaicing: A Systematic Survey, Xin Li, Bahadir Gunturk, Lei Zhang, SPIE2011 https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.141.634&rep=rep1&type=pdf
Using Natural Image Properties as Demosaicing
Hints. (ICIP 2004)
I. Omer and M. Werman
https://www.researchgate.net/publication/4138072_Using_natural_image_properties_as_demosaicing_hints
The Canonical Correlations of Color Images and their use for Demosaicing
Hel-Or, Yacov
HPL-2003-164R1
20040227
https://faculty.idc.ac.il/toky/Publications/TR/CCA.pdf
Comparison of color demosaicing
methods
Olivier Losson, Ludovic Macaire, Yanqin Yang
https://hal.archives-ouvertes.fr/hal-00683233/document
Color Filter Array Demosaicking: New Method and
Performance Measures,
Wenmiao Lu and Yap-Peng Tan, IEEE Transactions on
Image Processing,
vol. 12, no. 10, pp. 1194-1210, Oct 2003.
http://elynxsdk.free.fr/ext-docs/Demosaicing/more/news0/Color%20Filter%20Array%20Demosaicking-New%20Method%20and%20Performance%20Measures.pdf
Lecture 11 - – Jpeg Compression
and Extensions (5/6/23)
Topics to cover: Image compression general , JPEG compression,
JPEG artifacts, JPEG 2000 compression
DCTune: A Technique for visual
optimization of DCT quantization matrices for individual images (1993)
Andrew B. Watson, Society for Information Display Digest of Technical Papers
XXIV, 946-949. http://vision.arc.nasa.gov/publications/sid93/sid93.pdf
Perceptual optimization of DCT color quantization matrices (1994)
Andrew B. Watson, Proceedings, IEEE International Conference on Image
Processing,
http://vision.arc.nasa.gov/publications/icip94.pdf
Perceptual adaptive JPEG coding (1996)
Ruth Rosenholtz & Andrew B. Watson Proceedings,
IEEE International Conference on Image Processing, Lausanne, Switzerland, 1,
901-904.
http://vision.arc.nasa.gov/publications/AdaptiveJPEG/AdaptiveJPEG.pdf
Lecture 12 - Halftoning (12/6/23)
Topics to cover: Printing process, what is
halftoning, BW halftoning methods, Color halftoning
"Improving Digital Halftones by Exploiting Visual
System Properties (summary and pointers to other papers)
http://vision.arc.nasa.gov/personnel/jbm/home/publications/proc/half.pdf
DBS
Principled halftoning based on human vision models (1992)
Jeffrey B. Mulligan & Albert J. Ahumada Jr.,
Proc. SPIE/SPSE Conference 1666 On Human Vision, Visual Processing, And Visual
Display III, 109-121.
http://vision.arc.nasa.gov/personnel/jbm/home/publications/proc/huvi.pdf
temporal halftoning
Methods for Spatiotemporal Dithering. (1993)
Mulligan, J.B., SID Int. Symp. Dig. Tech. Papers, 24,
155-158.
http://vision.arc.nasa.gov/personnel/jbm/home/publications/proc/spie93.pdf
P. Hilgenberg, T.J. Flohr, C.B. Atkins, and C.A. Bouman. Least-squares modelbased
video halftoning.
In Proceedings of the SPIE, volume 2179, pages 207--117,
http://dynamo.ecn.purdue.edu/~bouman/publications/pdf/ei94a.ps
color halftoning
Digital halftoning methods for selectively partitioning error into achromatic
and chromatic channels (1990)
Jeffrey B. Mulligan , Proc. SPIE/SPSE Conference No. 1249 On Human Vision,
Visual Processing and Visual Display, Paper No. 21, Feb 1990.
http://vision.arc.nasa.gov/publications/spie90.pdf
Principled Methods for Color Dithering Based on Models of the Human Visual
System. (1992)
Mulligan, J.B., and Ahumada, A.J. Jr., SID Int. Symp. Dig. Tech. Papers, 23, 194- 197.
http://vision.arc.nasa.gov/personnel/jbm/home/publications/proc/sid92.pdf
Color 1/2toning using DBS
T. J. Flohr, B. W. Kolpatzik,
R. Balasubramanian,
D. A. Carrara, C. A. Bouman, and J. P. Allebach, "Model based color image quantization,"
Proc. of SPIE/IS&T Conf. on Human Vision, Visual Processing, and Digital
Display, pp. 270-281, San Jose,
CA, January 31-February 4, 1993, Vol. 1993.
http://citeseer.ist.psu.edu/flohr93model.html
Lecture 13 – Image Quality Measures - () SKIP THIS TALK
Topics to cover: What is IQA, types of noise,
full, partial and no reference IQA
SSIM, SSIM for color, S-CIELAB color
Multi-scale structural similarity for image quality
assessment
Z Wang, E P Simoncelli, A C Bovik.
37th Asilomar Conf. on Signals, Systems and Computers,
http://www.cns.nyu.edu/pub/eero/wang03b.pdf
Image quality assessment: From error visibility to
structural similarity
Z Wang, A C Bovik, H R Sheikh, and E P Simoncelli.
IEEE Trans Image Processing, 13(4):600-612, Apr 2004.
http://www.cns.nyu.edu/pub/eero/wang03-reprint.pdf
Stimulus synthesis for efficient evaluation and refinement of perceptual image
quality metrics
Z Wang and E P Simoncelli.
Proc. SPIE Conf on Human Vision and Electronic Imaging,
http://www.cns.nyu.edu/pub/eero/wang04a.pdf
X. M. Zhang and B. A. Wandell,
"A spatial extension to cielab for digital color
image reproduction,"
Society of Information Display Sumposium Technical
Digest, vol. 27, pp. 731--734, 1996
http://citeseer.ist.psu.edu/zhang96spatial.html
http://citeseer.ist.psu.edu/cache/papers/cs/14589/http:zSzzSzwhite.stanford.eduzSzhtmlzSzxmeizSzscielabzSzscielab3zSzscielab3.pdf/zhang96spatial.pdf
http://white.stanford.edu/~brian/scielab/scielab3/scielab3.html
X. Zhang, D. A. Silverstein, J. E. Farrell, and B. A. Wandell,
"Color image quality metric S-CIELAB and its application on halftone
texture visibility," in COMPCON97 Digest of Papers, pp. 44--48, IEEE,
1997.
http://citeseer.ist.psu.edu/zhang97color.html
http://white.stanford.edu/~brian/scielab/spie97/spie97.html
X. Zhang, J. Farrell, B. A. Wandell, Applications of
a spatial extension to CIELAB, in: SPIE, 1997.
http://citeseer.ist.psu.edu/zhang97applications.html
X. Zhang, B. A. Wandell: "Color image fidelity
metrics evaluated using image distortion maps."
Signal Processing 70(3), 201--214, 1998.
http://citeseer.ist.psu.edu/zhang98color.html
Christian J. van den Branden Lambrecht, Joyce E. Farrell:
"Perceptual quality metric for digitally coded color images."
in Proceedings of the European Signal Processing Conference, pp. 1175--1178,
Trieste, Italy, September 10--13, 1996.
http://citeseer.ist.psu.edu/28332.html
Colour Image Quality Assessment
Using the Combined Full-Reference Metric
Krzysztof Okarma
Computer Recognition Systems 4 pp 287-296
Full-Reference Image Quality Assessment Measure Based on
Color Distortion
Zianou Ahmed Seghi and
Fella Hachouf
IFIP Advances in Information and Communication Technology book series
https://www.researchgate.net/profile/Zianou-Seghir/publication/276291048_Full-Reference_Image_Quality_Assessment_Measure_Based_on_Color_Distortion/links/5556171708ae6943a87336dc/Full-Reference-Image-Quality-Assessment-Measure-Based-on-Color-Distortion.pdf
No-Reference Color Image Quality Assessment: From Entropy
to Perceptual Quality
Xiaoqiao Chen, Qingyi
Zhang, Manhui Lin, Guangyi
Yang, Chu He
https://arxiv.org/pdf/1812.10695