L T P Credits Total Marks
SBSB7003 COMPUTER
4 0 0 4 100
VISION
COURSE OBJECTIVES
➢ To review image processing techniques for computer vision.
➢ To understand shape and region analysis, Hough Transform and its applications to detect
lines, circles, ellipses.
➢ To understand three-dimensional image analysis techniques, motion analysis.
UNIT 1 IMAGE PROCESSING FOUNDATIONS 12 Hrs.
Review of image processing techniques – classical filtering operations – thresholding techniques –
edge detection techniques – corner and interest point detection – mathematical morphology – texture.
UNIT 2 SHAPES AND REGIONS 12 Hrs.
Binary shape analysis – connectedness – object labelling and counting – size filtering – distance
functions – skeletons and thinning – deformable shape analysis – boundary tracking procedures –
active contours – shape models and shape recognition – centroidal profiles – handling occlusion –
boundary length measures – boundary descriptors – chain codes – Fourier descriptors – region
descriptors – moments.
UNIT 3 HOUGH TRANSFORM 12 Hrs.
Line detection – Hough Transform (HT) for line detection – foot-of-normal method – line localization
–line fitting – RANSAC for straight line detection – HT based circular object detection – accurate
center location – speed problem – ellipse detection – Case study: Human Iris location – hole detection
–generalized Hough Transform (GHT) – spatial matched filtering – GHT for ellipse detection – object
location – GHT for feature collation.
UNIT 4 3D VISION AND MOTION 12 Hrs.
Methods for 3D vision – projection schemes – shape from shading – photometric stereo – shape from
texture– shape from focus – active range finding – surface representations – point-based
representation – volumetric representations – 3D object recognition – 3D reconstruction –
introduction
to motion – triangulation – bundle adjustment – translational alignment – parametric motion –
splinebased motion – optical flow – layered motion.
UNIT 5 APPLICATIONS 12 Hrs.
Application: Photo album – Face detection – Face recognition – Eigen faces – Active appearance and
3D shape models of faces Application: Surveillance – foreground-background separation – particle
filters – Chamfer matching, tracking, and occlusion – combining views from multiple cameras –
human gait analysis Application: In- vehicle vision system: locating roadway – road markings –
identifying road signs – locating pedestrians
Max. 60 Hr
COURSE OUTCOMES
On completion of the course the student will be able to
CO1 - Implement fundamental image processing techniques required for computer vision
CO2 - Understand Image formation process
CO3 - Extract features form images and do analysis of images
CO4 - Generate 3D model from images
CO5 - Understand video processing, motion computation and 3D vision and geometry
CO6 - Develop applications using computer vision techniques
TEXT / REFERENCE BOOKS
1. E. R. Davies, “Computer & Machine Vision”, Fourth Edition, Academic Press, 2012.
2. R. Szeliski, “Computer Vision: Algorithms and Applications”, Springer 2011.
3. Simon J. D. Prince, “Computer Vision: Models, Learning, and Inference”, Cambridge University
Press, 2012.
4. Mark Nixon and Alberto S. Aquado, “Feature Extraction & Image Processing for Computer
Vision”, Third Edition, Academic Press, 2012.
5. D. L. Baggio et al., “Mastering OpenCV with Practical Computer Vision Projects”, Packt
Publishing, 2012.
6. Jan Erik Solem, “Programming Computer Vision with Python: Tools and algorithms for analyzing
images”, O'Reilly Media, 2012
END SEMESTER EXAMINATION QUESTION PAPER PATTERN
Max. Marks: 100 Exam Duration: 3 Hrs.
PART A: 6 Questions of 5 marks each – No choice 30 Marks
PART B: 2 Questions from each unit with internal choice, each carrying 14 marks 70 Marks
(Out of 100 marks, maximum of 10% problems may be asked)
