CS代考 CSCI435/CSCI935 – cscodehelp代写
CSCI435/CSCI935
Computer Vision – Algorithms and Systems
Subject Review & Final Exam
Lecturer: Assoc/Prof Wanqing Li
Room 3.101
Web: http://www.uow.edu.au/~wanqing
25/10/2021
Subject Learning Outcomes
On successful completion of this subject, students are expected to:
• Understand the principle of digital image and video cameras.
• Use image enhancement techniques.
• Use object detection and recognition techniques.
• Use video processing techniques to detect moving
• Design and implement basic computer vision systems
for real applications.
25/10/2021 2
Topics Covered in the Subject
Photometry and colourimetry
light, colour perception and colour spaces
Image acquisition
Optical system. sampling, image sensors, single sensor based
digital camera, colour processing chain Image quality & enhancement
Criteria of quality, sharpness, low- & high-pass filter in spatial and frequency domain, enhancement, noise, image spectrum and pyramids
Edge detection
Gradient, edge detection operators, zero-crossing, LoG, DoG,
Canny edge detector Key point detection
Harris corner detection, SIFT interest points and descriptors, BoW, image similarity
25/10/2021 3
Topics Covered in the Subject
Shape detection
Hough transform (line), circle detection
Image segmentation
Visual features, perceptual grouping, thresholding (heuristic &
Otsu’s), clustering-based (k-means, mean-shift) Binary image processing
Binary morphology, connected component analysis CD and background modelling
Robust CD, Background modelling (running average/median/Gaussian GMM)
Object detection
General framework (detection as classification), sliding window vs. reginal proposal (selective search), skin-colour based face detection, AdaBoost (Viola & Jones detector), HoG for detection of humen and faces
25/10/2021 4
Topics Covered in the Subject
Image classification and object recognition
General framework, human perception of faces, face recognition system, normalization of faces, eigenfaces, LBP-based face recognition
Motion estimation
Optical flow, HS method, LK method, global motion, motion
analysis and its applications
Convolitional Neural Networks (ConvNets)
Linear classifier, softmax classifiers, optimization, multiple layer perceptron (fully connected layers), gradient backpropagation, convolutional layers, learning ConvNet parameters (mini-batch SGD, batch normalization), hyper-parameters, regularization and dropout, data augmentation, typical ConvNets for CV
25/10/2021 5
Subject Materials for Review
Lecture slides:
Available on the subject Moodle.
Recommended books:
D. Forsyth, J. Ponce. Computer Vision a Modern Approach,
, 2012 (2nd ed.)
E. R Davies, Computer and machine vision: theory, algorithms and practicalities, Academic Press; 4th edition; 2012
Stanford’s course Convolutional Neural Networks for Visual Recognition http://cs231n.stanford.edu/
Assignments
25/10/2021 6
Assessments
Assignments (60% in total)
3x Coding projects 3 = 60%
Final Exam (40%)
Minimum requirement 40% = 16 marks
25/10/2021 7
Final Examination
Materials and Aids Allowed Open book
Exam Structure
Problem solving and discussion
4 questions, 10% each
Each question has multiple sub-questions
This exam will run via Moodle
25/10/2021 8
Final Examination…
Exam Date & Starting time
13:30 (Sydney time) Monday 15 November
Please check SOLS
Exam Duration 2 hours
• 30 minutes for preparing and submitting answer sheets in a
single pdf file
25/10/2021 9
Final Examination – Instructions
Have a set of A4 blank paper ready On the first page, write
Your full name, Student Number & UOW login name Answer each question on a separate page clearly
either handwriting or using suitable editing software at your own choice
Scan or take photos of your answer sheets and convert them into one single pdf file (<200MB)
Name the pdf file as
Submit the pdf file via Moodle
See the next slide on how to scan/convert your hand-write answer sheets into a
single pdf file using your mobile
25/10/2021 10
How to create one pdf file
Important: Be prepared with knowing how to create one pdf file from your working solutions.
There is freely available software that can be used to scan your answer sheets and convert them into a single pdf file. These links may be of assistance.
https://www.youtube.com/watch?v=BCccqxhPyJw (Scan documents) https://www.youtube.com/watch?v=d_olWftSgIM (Convert image to pdf)
iPhone https://www.idownloadblog.com/2017/05/12/how-to-save-photos-pdf-
iphone-ipad/
https://www.igeeksblog.com/how-to-convert-photos-to-pdf-on-iphone- ipad/
25/10/2021 11
Example Problems
Disclaimer
This is not an exclusive list of problems that may appear in the final exam, they are just examples
25/10/2021 12
Example Problems
Single sensor based cameras and image processing
Key components
How each component affects quality of
Noise propagation
How to enhance images with low visual quality
25/10/2021 13
Example Problems
Automatic Recognition of the following road sign in images
Automatic counting the number of balls
25/10/2021 14
Example Problems
People Counting
Detection of car registration Classification of vehicles Detection of hands Problems in assignments
25/10/2021 15
Types of Possible Questions
How will you classify this problem with regards to computer vision problems you have studied in the class?
Propose a solution to the problem. Divide the solution into components and describe the solution using a block diagram or flowchart. Explain the function, input and output of each components.
For each component in the solution, choose suitable algorithms and briefly describe how the algorithms works.
Describe how you would test your solution and measure its performance.
Discuss whether your algorithm would work in “certain” conditions, Explain why it works or why it does not work.
What are the possible factors that may affect the accuracy of your system?
25/10/2021 16
How to contact me
Consultation via Zoom
Monday 15:30 – 17:30 Wednesday 16:30 – 18:30
Set the subject of the email as
o CSCI435 or CSCI935: (topic of the email) Will be responded as soon as possible
25/10/2021 17
25/10/2021 18
