This course introduces algorithms in computer vision and image processing so as to develop students with basic knowledge to explain how computer could understand the visual world. The course describes visual understanding from the perspective of low-level image processing mid-level statistical inferencing and high-level vision recognition. The topics include feature extraction image segmentation, object recognition, motion analysis and scene understanding, along with real-world applications that vision algorithms have been successfully applied.

For a student to pass the course, at least 30% of the maximum mark for the examination must be obtained.