• Course Info
• Lectures
• Exams
• Homework
• Paper Presentation
• Project
• Grading
• Links

Announcements

1. (Dec 27) Course page is online.
2. (Dec 27) Syllabus is available.
3. (Feb 08) Slides for introduction are available.
4. (Feb 15) Slides for digital image fundamentals are available.
5. (Feb 26) Slides for binary image analysis are available.
6. (Feb 26) HW1 is sent out (Check your email).
7. (Feb 29) Slides for introduction to Deep Learning are available.
8. (March 12) Slides for filtering are available.
9. (March 14) HW2 is sent out (Check your email).
10. (March 24) Slides for filtering (Part2) are available.
11. (April 08) Slides for Edge Detection are available.
12. (April 08) HW3 is sent out (Check your email).
13. (April 15) Slides for local feature detectors (Part1) are available.
14. (April 19) Slides for local feature detectors (Part2) are available.
15. (May 10) Slides for color image processing are available.
16. (May 20) Slides for texture analysis are available.
17. (May 22) Slides for segmentation are available.
18. (May 22) Slides for image classification with Kernel Machines are available.

Personnel

Instructor:	Dr. Sedat Ozer (Office: EA 524, Email: sedat AT cs.bilkent.edu.tr)
TA:	Mr. Aydamir Mirzayev (Office: EA 505, Email: aydamir.mirzayev AT bilkent.edu.tr)

Course Information

Schedule:	Wednesdays: 13:40 - 15:30, Fridays:15:40 - 17:30
Office hours:	Sedat Ozer: Wednesdays: 15:50 - 16:50, Fridays: 15:00 - 15:30 TA (Mr. Aydamir Mirzayev): Tuesdays: 11:40 - 12:40 and Wednesdays: 9:40 - 10:40, also by appointment
Catalog description:	Image acquisition, sampling and quantization. Spatial domain processing. Image enhancement. Texture analysis. Edge detection. Frequency domain processing. Color image processing. Mathematical morphology. Image segmentation and region representations. Statistical and structural scene descriptions. Deep learning. Applications.
Prerequisites:	Good background on high-level programming, data structures, linear algebra, and vector calculus. No prior knowledge of image processing or computer vision is assumed.
Syllabus:	Make sure you read the syllabus for course details.

Texts

• I. Goodfellow, Y. Bengio and A. Courville,, Deep Learning, MIT Press, 2016.
• L. G. Shapiro and G. C. Stockman, Computer Vision, Prentice Hall, 2001.
• R. Szeliski, Computer Vision: Algorithms and Applications, Springer 2010.
• R. C. Gonzalez and R. E. Woods, Digital Image Processing, 3rd edition, Prentice Hall, 2008.
• D. A. Forsyth and J. Ponce, Computer Vision: A Modern Approach, Prentice Hall, 2002.
• D. H. Ballard and C. M. Brown, Computer Vision, Prentice Hall, 1982.

Lectures

Topics	Contents
Introduction [ Slides ]	Topics: Overview Example applications Demos: Google Cloud Vision API Microsoft Computer Vision API Microsoft computer vision research blog and demos Clarifai demo Imagga auto-tagging demo
Digital Image Fundamentals [ Slides ]	Topics: Acquisition, sampling, quantization Image enhancement Image formats Linear algebra and MATLAB review Readings: SS Ch 1, 2 GW Ch 1, 2, 3.1-3.4 References: R. C. Gonzales, R. E. Woods, "Review material and slides on linear algebra, probability, and linear systems," 2002. Software: Matlab code examples for processing images Matlab code examples for histogram enhancement
Binary Image Analysis [ Slides ]	Topics: Pixels and neighborhoods Mathematical morphology Connected components analysis Automatic thresholding Readings: SS Ch 3.1-3.5, 3.8 GW Ch 2.5, 9.1-9.5, 10.3 References: M. Sezgin, B. Sankur, "Survey Over Image Thresholding Techniques and Quantitative Performance Evaluation" (local copy), Journal of Electronic Imaging, 13(1):146-165, January 2004. Software: Matlab code examples for binary image analysis
Introduction to Deep Learning [ Slides: Part 1 | Part 2 | Part 3 | Part 4 ]	Topics: Introduction to Classification Logistic Regression Fully Connected Neural Networks Convolutional Neural Networks Image Classification with LeNet
Filtering [ Slides: Part 1 | Part 2 ]	Topics: Spatial domain filtering Frequency domain filtering Image enhancement Readings: SS Ch 5.1-5.5, 5.10-5.11 GW Ch 3.5-3.8, 4 Software: Matlab code examples for filtering
Edge Detection [ Slides ]	Topics: Edges, lines, arcs Hough transform Readings: SS Ch 5.6-5.8, 10.3-10.4 GW Ch 10.1-10.2 References: A. Fitzgibbon, M. Pilu, R. B. Fisher, "Direct Least Square Fitting of Ellipses" (local copy), IEEE Trans. on Pattern Analysis and Machine Intelligence, 21(5):476-480, May 1999. Y. Li, L. G. Shapiro, "Object Recognition for Content-Based Image Retrieval" (local copy), Lecture Notes in Computer Science, 2004. S. Kiranyaz, M. Ferreira, M. Gabbouj, "Automatic Object Extraction Over Multiscale Edge Field for Multimedia Retrieval", IEEE Trans. on Image Processing, 15(12):3759-3772, December 2006. M. S. Costa, L. G. Shapiro, "3D Object Recognition and Pose with Relational Indexing" (local copy), Computer Vision and Image Understanding, 79(3):364-407, September 2000. Software: Edge detection demo by Yi Li Line and arc finding demo by Yi Li Building recognition demo by Yi Li Hough transform demo
Local Feature Detectors [Slides: Part1 | Part 2 ]	Topics: Corners and other interest points Invariants References: C. Schmid, R. Mohr, C. Bauckhage, "Evaluation of Interest Point Detectors" (local copy), International Journal of Computer Vision, 37(2):151-172, June 2000. K. Mikolajczyk, C. Schmid, "Scale & Affine Invariant Interest Point Detectors" (local copy), International Journal of Computer Vision, 60(1):63-86, October 2004. D. G. Lowe, "Distinctive Image Features From Scale-Invariant Keypoints" (local copy), International Journal of Computer Vision, 60(2):91-110, November 2004. K. Mikolajczyk, C. Schmid, "A Performance Evaluation of Local Descriptors" (local copy), IEEE Trans. on Pattern Analysis and Machine Intelligence, 27(10):1615-1630, October 2005. K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir, L. Van Gool, "A Comparison of Affine Region Detectors" (local copy), International Journal of Computer Vision, 65(1-2):43-72, November 2005. Local invariant features tutorial by Schmid and Lowe at CVPR 2003 N. Snavely, S. M. Seitz, R. Szeliski, "Photo tourism: Exploring photo collections in 3D" (local copy, web page), ACM Transactions on Graphics (SIGGRAPH Proceedings), 25(3):835-846, 2006. I. Simon, N. Snavely, S. M. Seitz, "Scene Summarization for Online Image Collections" (local copy, web page), IEEE International Conference on Computer Vision, October 14-20, 2007. Software: Affine covariant features by University of Oxford SIFT keypoint detector by David Lowe Affine interest point detectors by INRIA Rhone-Alpes Affine invariant region detector by Timor Kadir VLFeat open source library Aperture problem demonstration
Color Image Processing [ Slides ]	Topics: Color spaces and conversions Readings: SS Ch 6.1-6.5 GW Ch 6
Texture Analysis [ Slides ]	Topics: Statistical approaches Structural approaches Readings: SS Ch 7 GW Sec 11.3.3
Image Segmentation [ Slides ]	Topics: Histogram-based approaches Clustering-based approaches Region growing Split-and-merge Morphological approaches Graph-based approaches Readings: SS Ch 10.1 GW Ch 10.4-10.5 References: J. Shi, J. Malik, "Normalized Cuts and Image Segmentation" (local copy), IEEE Trans. on Pattern Analysis and Machine Intelligence, 22(8):888-905, August 2000. C. Carson, S. Belongie, H. Greenspan, J. Malik, "Blobworld: Image Segmentation Using Expectation-Maximization and Its Applications to Image Querying" (local copy), IEEE Trans. on Pattern Analysis and Machine Intelligence, 24(8):1026-1038, August 2002. Y. Deng, B. S. Manjunath, "Unsupervised Segmentation of Color-Texture Regions in Images and Video" (local copy), IEEE Trans. on Pattern Analysis and Machine Intelligence, 23(8):800-810, August 2001. P. Soundararajan, S. Sarkar, "An In-Depth Study of Graph Partitioning Measures for Perceptual Organization" (local copy), IEEE Trans. on Pattern Analysis and Machine Intelligence, 25(6):642-660, June 2003. D. Comaniciu, P. Meer, "Mean shift: a robust approach toward feature space analysis" (local copy), IEEE Trans. on Pattern Analysis and Machine Intelligence, 24(5):603-619, May 2002. X. Ren, J. Malik, "Learning a classification model for segmentation" (local copy), IEEE International Conference on Computer Vision, 2003. P. F. Felzenszwalb, D. P. Huttenlocher, "Efficient Graph-Based Image Segmentation" (local copy), International Journal of Computer Vision, 59(2):167-181, September 2004. A. Levinshtein, A. Stere, K. N. Kutulakos, D. J. Fleet, S. J. Dickinson, K. Siddiqi, "TurboPixels: Fast Superpixels Using Geometric Flows" (local copy), IEEE Trans. on Pattern Analysis and Machine Intelligence, 31(12):2290-2297, December 2009. Image segmentation research at UC Santa Barbara Graph-based image segmentation tutorial by Shi, Fowlkes, Martin, Sharon at CVPR 2004 L. Vincent, P. Soille, "Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations" (local copy), IEEE Trans. on Pattern Analysis and Machine Intelligence, 13(6):583-598, June 1991. C. Vachier, F. Meyer, "The Viscous Watershed Transform" (local copy), Journal of Mathematical Imaging and Vision, 22(2-3):251-267, 2005. B. E. Bejnordi, G. Litjens, M. Hermsen, N. Karssemeijer, J. A. W. M. van der Laak, "A multi-scale superpixel classification approach to the detection of regions of interest in whole slide histopathology images" (local copy), SPIE Medical Imaging Symposium, Digital Pathology Conference, 2015. R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, S. Susstrunk, "SLIC Superpixels Compared to State-of-the-art Superpixel Methods" (local copy), IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11):2274-2282, May 2012. Y. Y. Boykov, M.-P. Jolly, "Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images" (local copy), 8th International Conference on Computer Vision, 1:105-112, July 2001. Y. Boykov, G. Funka-Lea, "Graph cuts and efficient N-D image segmentation" (local copy), International Journal of Computer Vision, 70(2):109--131, November 2006. Software: Berkeley segmentation engine Normalized cuts segmentation by Jianbo Shi JSEG: segmentation of color-texture regions by UC Santa Barbara Edgeflow segmentation by UC Santa Barbara EDISON: mean-shift segmentation by Rutgers Superpixel segmentation by Greg Mori Graph-based segmentation by Pedro Felzenszwalb Turbopixels algorithm for superpixel segmentation by Alex Levinshtein SLIC superpixels by EPFL Graph cut segmentation by Yuri Boykov
Representation and Description [ Slides ]	Topics: Image representations and descriptors Region representations and descriptors Readings: SS Ch 10.2, 3.7 GW Ch 11 References: D. Zhang, G. Lu, "Review of Shape Representation and Description Techniques" (local copy), Pattern Recognition, 37(1):1-19, January 2004.
Pattern Recognition Overview [ Slides: Part 1 | Part 2 ]	Topics: Brief introduction to pattern recognition Readings: SS Ch 4 GW Ch 12.1-12.2 References: A. K. Jain, R. P. W. Duin, J. Mao, "Statistical Pattern Recognition: A Review" (local copy), IEEE Trans. on Pattern Analysis and Machine Intelligence, 22(1):4-37, January 2000. Software: K-means clustering demo by Yi Li
Case Studies [ Slides: Part 1 | Part 2 (with kind permission from Prof. Linda Shapiro) | Part 3 (with kind permission from Joseph Redmon) ]	Topics: Image classification Object recognition Deep learning References: Y. Liu, D. Zhang, G. Lu, W.-Y. Ma, "A Survey of Content-Based Image Retrieval with High-Level Semantics" (local copy), Pattern Recognition, 40(1):262-282, January 2007. X. S. Zhou, T. S. Huang, "Relevance Feedback in Image Retrieval: A Comprehensive Review" (local copy), Multimedia Systems, 8(6):536-544, April 2003. S. Antani, R. Kasturi, R. Jain, "A Survey on the Use of Pattern Recognition Methods for Abstraction, Indexing and Retrieval of Images and Video" (local copy), Pattern Recognition, 35(4):945-965, April 2002. A. W. M. Smeulders, M. Worring, S. Santini, A. Gupta, R. Jain, "Content-Based Image Retrieval at the End of the Early Years" (local copy), IEEE Trans. on Pattern Analysis and Machine Intelligence, 22(12):1349-1380, December 2000. Y. Rui, T. S. Huang, S.-F. Chang, "Image Retrieval: Current Techniques, Promising Directions, and Open Issues" (local copy), Journal of Visual Communication and Image Representation, 10(1):39-62, March 1999. Y. Rubner, C. Tomasi, L. J. Guibas, "The Earth Mover's Distance as a Metric for Image Retrieval" (local copy), International Journal of Computer Vision, 40(2):99-121, November 2000. A. Vailaya, M. A. T. Figueiredo, A. K. Jain, H.-J. Zhang, "Image Classification for Content-Based Indexing" (local copy), IEEE Trans. on Image Processing, 10(1):117-130, January 2001. G. Csurka, C. R. Dance, L. Fan, J. Willamowski, C. Bray, "Visual Categorization with Bags of Keypoints", (local copy), European Conference on Computer Vision, 2004. L. Fei-Fei, P. Perona, "A Bayesian Hierarchical Model for Learning Natural Scene Categories" (local copy), IEEE Conference on Computer Vision and Pattern Recognition, 2:524-531, June 20-25, 2005. P. Quelhas, F. Monay, J.-M. Odobez, D. Gatica-Perez, T. Tuytelaars, "A Thousand Words in a Scene" (local copy), IEEE Trans. on Pattern Analysis and Machine Intelligence, 29(9):1575-1589, September 2007. D. Gokalp, S. Aksoy, "Scene Classification Using Bag-of-Regions Representations", IEEE Conference on Computer Vision and Pattern Recognition, Beyond Patches Workshop, June 23, 2007. M. R. Boutell, J. Luo, C. M. Brown, "Factor Graphs for Region-Based Whole-Scene Classification" (local copy), IEEE Conference on Computer Vision and Pattern Recognition, Workshop on Semantic Learning Applications in Multimedia, June 17, 2006. Y. Li, J. A. Bilmes, L. G. Shapiro, "Object Class Recognition using Images of Abstract Regions" (local copy), IAPR International Conference on Pattern Recognition, 1:40-43, August 23-26, 2004. Y. Li, L. G. Shapiro, J. A. Bilmes, "A Generative/Discriminative Learning Algorithm for Image Classification" (local copy), IEEE International Conference on Computer Vision, 2:1605-1612, October 17-21, 2005. J. Xiao, K. Ehinger, J. Hays, A. Torralba, A. Oliva, "SUN Database: Exploring a Large Collection of Scene Categories" (local copy), International Journal of Computer Vision, 119(1):3-22, August 2016. G. Patterson, C. Xu, H. Su, J. Hayes, "The SUN Attribute Database: Beyond Categories for Deeper Scene Understanding" (local copy), International Journal of Computer Vision, 108(1):59-81, May 2014. B. Zhou, A. Lapedriza, J. Xiao, A. Torralba, A. Oliva, "Learning Deep Features for Scene Recognition using Places Database" (local copy), Advances in Neural Information Processing Systems, 2014. Recognizing and learning object categories tutorial by Fei-Fei, Fergus and Torralba at ICCV 2009 Visual object recognition tutorial by Leibe and Grauman at AAAI 2008 (local copy) N. Dalal, B. Triggs, "Histograms of oriented gradients for human detection", (local copy), IEEE Conference on Computer Vision and Pattern Recognition, 1:886-893, June 20-25, 2005. P. F. Felzenszwalb, R. B. Girshick, D. McAllester, D. Ramanan, "Object Detection with Discriminatively Trained Part-Based Models", (local copy), IEEE Trans. on Pattern Analysis and Machine Intelligence, 32(9):1627-1645, September 2010. A. Krizhevsky, I. Sutskever, and G. Hinton, "ImageNet classification with deep convolutional neural networks", (local copy), Advances in Neural Information Processing Systems, 1106-1114, 2012. R. Girshick, J. Donahue, T. Darrell, J. Malik, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation", (local copy), (arXiv version), IEEE Conference on Computer Vision and Pattern Recognition, 580-587, June 23-28, 2014. K. Simonyan, A. Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition", (local copy), International Conference on Learning Representations, 2015. R. Girshick, J. Donahue, T. Darrell, J. Malik, "Region-Based Convolutional Networks for Accurate Object Detection and Segmentation", (local copy), IEEE Trans. on Pattern Analysis and Machine Intelligence, 38(1):142-158, January 2016. L. J. P. van der Maaten and G. E. Hinton, "Visualizing High-Dimensional Data Using t-SNE", (local copy), Journal of Machine Learning Research, 9(11):2579-2605, 2008. Evaluation of feature encoding methods LabelMe database Scene UNderstanding (SUN) database Places database Interactive visualization of deep networks: Places-CNN, ImageNet-CNN

Exams

• There will be one midterm exam in this course and that will be after the paper presentations. The format of the exam will be announced in the classroom.

Homework

1. First HW (HW1) has been sent out. Check your email. Due: March 06, 2020.
2. Second HW (HW2) has been sent out. Check your email. Due: Monday, March 30, 2020.
3. Third HW (HW3) has been sent out. Check your email. Due: Thursday, April 16, 2020.

Please make sure you fully understand the honor code in the syllabus as well as the Bilkent University Policy on Academic Honesty (in Turkish) and the Rules and Regulations of the Higher Education Council (YOK) (in Turkish). Cheating and plagiarism on exams, quizzes, and assignments will be punished according to these regulations.

Paper Presentations

You will present your chosen paper in the class-room. This will be a group presentation relevant to your final project (you should select a paper relevant to your project).

Each project group will present one paper. Your choice of paper MUST be approved by the instructor (Dr. Sedat Ozer) first. Unapproved papers and their presentations will not be graded. Each group have to prepare an email summarizing the following info in an email and should use the email subject "Proposed paper title for CS555": (or submit it on a form, if you received a link for submitting that information online)

In your email submission, you need to include:

Paper's info:
• Full title of the paper as shown on the paper,
• Complete author list of the paper,
and where the paper is published (peer-reviewed) along with its publication year,
• Paper's abstract,
• Paper's link to download,
• Also include your own project title and your project's one sentence description in another paragraph.


The paper presentation will take 20% of your final grade. Please choose a paper relevant to your project title. Presentation details: For "the content" of the paper that you picked, you will focus on the following details and will present them in your presentation:


• Check for the code of the paper on GitHub or on another online platform and download and run the code to generate author's results.
• Understand the goal of the paper: What is new, and what was done previously as described in the paper.
• What is the overall solution and the architecture presented in the paper,
• What metrics used in the paper and their definitions,
• What are the results, and how they are presented.
• BONUS: apply the code on another data-set that was not used in the paper and compute the performance metrics used in the paper. (+%3 on your final grade). You need to get instructor's approval first to receive the bonus!
• Expect to have a short presentation focusing on the above-listed points.

Project

Follow your in-class discussions and in-class slides for detailed info about the final projects. You will also recevie an email including more info about your final project submission. (Info about how to submit your final projects will be announced after the midterm!)

Grading Policy

Please refer to the course syllabus for the grading scheme.

Related Links

• Previous semesters for CS 484
  • Fall 2017
  • Fall 2016
  • Fall 2015
  • Spring 2015
  • Fall 2012
  • Spring 2012
  • Spring 2011
  • Spring 2010
  • Spring 2009
  • Spring 2008
  • Spring 2007
• Shapiro and Stockman book
  • Book's website at UW
  • Book's website at MSU
• Szeliski book
  • Book's website
• Gonzales and Woods book
  • Book's website
• Forsyth and Ponce book
  • Book's website
• Ballard and Brown book
  • Book's website
• Matlab tutorials
  • Matlab Tutorial by Udemy
  • Matlab Primer v2
  • Matlab Tutorial by Indiana University
  • Matlab Tutorial by the University of New Hampshire
  • Matlab Tutorial by MIT
  • Matlab Tutorial by the University of Washington
  • Matlab Tutorial by Gonzales and Woods
  • MathWorks - Matlab Tutorial
  • MathWorks - Student Center
  • MathWorks - Image Processing Toolbox (function list)
• Others
  • Industrial applications of computer vision