Back close

Course Detail

Course Name Computer Vision
Course Code 26CS748
Program M. Tech. in Computer Science & Engineering
Credits 3
Campus Bengaluru, Coimbatore, Chennai, Nagercoil

Syllabus

Introduction to Computer Vision and its applications. Image formation, image sensing, sampling, quantization, and digital image representation. Image enhancement techniques: histogram processing, interpolation, spatial filtering, smoothing, sharpening, and noise reduction. Image quality assessment and evaluation metrics. Image transformations: Fourier Transform, Discrete Cosine Transform (DCT), and overview of wavelet transforms. Image restoration, frequency-domain filtering, and mathematical morphology.

Image segmentation techniques: thresholding, edge detection, region-based segmentation, watershed algorithm, and evaluation metrics. Image representation and feature extraction techniques. Color models, texture analysis, and feature descriptors including SIFT, SURF, ORB, and HOG. Feature matching and object recognition using classical computer vision approaches. Applications of image analysis in healthcare, autonomous systems, agriculture, and surveillance.

Introduction to deep learning-based computer vision. Convolutional Neural Networks (CNNs), convolution operations, pooling, feature learning, and image classification. Transfer learning and pretrained models. Attention mechanisms and Vision Transformers (ViT). Self-supervised learning and vision foundation models. Video representation and analysis: optical flow, object detection, object tracking, pose estimation, and human activity recognition. Multimodal vision systems: image captioning, Vision-Language Models, Segment Anything Models (SAM), and Edge AI-based vision applications. Case studies on intelligent vision systems.

Course Objectives

Pre-Requisite(s): Linear Algebra, Basic Probability and Statistics, Python Programming (preferred)

Course Type: Lab/Project

Course Objectives

  • To introduce the fundamental concepts of image processing and computer vision techniques for visual data analysis.
  • To provide an understanding of classical and deep learning-based approaches for image and video understanding.
  • To enable students to develop and evaluate computer vision solutions for real-world applications.

Course Outcomes

CO1 Understand the fundamentals of image formation, representation, enhancement, and processing techniques used in computer vision.
CO2 Apply image analysis, segmentation, and feature extraction techniques for solving computer vision problems.
CO3 Analyze and utilize deep learning approaches including CNNs, transfer learning, attention mechanisms, and Vision Transformers for visual recognition tasks.
CO4 Design and evaluate computer vision applications using object detection, tracking, video analysis, multimodal vision, and edge-based vision systems.

CO-PO Mapping

CO PO1 PO2 PO3 PO4 PO5 PO6
CO1 3 2 1 2 1
CO2 3 3 2 2 3 1
CO3 3 3 3 2 3 2
CO4 3 3 3 3 3 2

Evaluation Pattern

Evaluation Pattern: 70/30

Assessment Internal Weightage External Weightage
Midterm Examination 20  
Continuous Assessment (Theory) 20  
Continuous Assessment (Lab) 30  
End Semester   30

Note: Continuous assessment may include quizzes, tutorials, laboratory assessments, case studies, assignments, and other course-related evaluation components. The Mid-Term examination may be conducted as a two-hour written examination or a two-hour laboratory-integrated examination, as applicable. The End-Semester assessment may be conducted either as a two-hour written examination, a laboratory-integrated examination, or as a project presentation and evaluation, provided the project-based assessment is approved by the Department.

Text Books/ References

  1. Rafael C. Gonzalez and Richard E. Woods, Digital Image Processing, 4th Edition, Pearson Education, 2018.
  2. Richard Szeliski, Computer Vision: Algorithms and Applications, 2nd Edition, Springer, 2022.
  3. Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, 2016.
  4. Mohamed Elgendy, Deep Learning for Vision Systems, Manning Publications, 2020.
  5. Joseph Howse and Joe Minichino, Learning OpenCV 4 Computer Vision with Python, Packt Publishing, 2020.
  6. Hands-On Vision Transformers with PyTorch, Packt Publishing, 2024.
  7. Recent research articles from reputed journals and conferences in the field of Computer Vision and Artificial Intelligence.

DISCLAIMER: The appearance of external links on this web site does not constitute endorsement by the School of Biotechnology/Amrita Vishwa Vidyapeetham or the information, products or services contained therein. For other than authorized activities, the Amrita Vishwa Vidyapeetham does not exercise any editorial control over the information you may find at these locations. These links are provided consistent with the stated purpose of this web site.

Admissions Apply Now