Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: THEend8_
CSCI435/CSCI935 Computer Vision
Algorithms and Systems Subject
Use image enhancement techniques. • Use object detection and recognition techniques. • Use video processing techniques to detect moving objects. • Design and implement basic computer vision systems for real applications. 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 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 Subject Materials for Review Lecture slides: Available on the subject Moodle. Recommended books: D. Forsyth, J. Ponce. Computer Vision a Modern Approach, Prentice Hall, 2012 (2nd ed.) E. R Davies, Computer and machine vision: theory, algorithms and practicalities, Academic Press; 4th edition; 2012 Assignments 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 25/10/2021 9 Final Examination… Exam Date & Starting time 13:30 (Sydney time) Monday 15 November 2021 Please check SOLS Exam Duration 2 hours Grace Period • 30 minutes for preparing and submitting answer sheets in a single pdf file 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