Department Events
IMAGE PROCESSING & DEEP LEARNING
Course Objectives:
The course will enable the students to
- Explore the concepts of image processing and its application
- Introduce students to basic applications, concepts, and techniques of deep learning.
Course | Learning outcome (at course level) | Learning and teaching strategies | Assessment Strategies | |
Course Code | Course title | |||
24DCAI 801A |
IMAGE PROCESSING & DEEP LEARNING (Theory) | CO145. Discuss the concepts of computer vision and image processing. CO146. Apply the basic image processing operations on images. CO147. Apply image recognition and object detection on images/objects. CO148. Examine the various types of neural networks and their performance metrics. CO149. Develop a deep learning model for a real life problem and evaluate its performance. CO150. Contribute effectively in course-specific interaction
| Approach in teaching: Interactive Lectures, Discussion, PowerPoint Presentations, Informative videos
Learning activities for the students: Self-learning assignments, Effective questions, presentations.
| Assessment tasks will include Class Test on the topics, Semester end examinations, Quiz, Student presentations and assignments. |
Image Processing VS Computer Vision, Problems in Computer Vision, Fundamentals Applications Image processing system components, phases in image processing. Introduction to images, Image formation, Image as a Matrix, Manipulating Pixels, Displaying and Saving an Image, Display Utility Functions, Color Image, Image Channels, Splitting and Merging Channels, Manipulating Color pixels, Images with Alpha Channel
creating, cropping, resizing images, creating image masks,
Mathematical operations on images. Data Type Conversion, Contrast Enhancement, Brightness Enhancement
Image Annotation: draw a line ,Circle ,Rectangle Ellipse and Draw text over an image
point operators, linear filtering, neighborhood operators, fourier transforms, segmentation. Feature Detection and Matching – points and patches, edges, lines, Feature-based Alignment – 2D, 3D feature-based alignment, pose estimation.
Recognition – object detection, face recognition, instance recognition, category recognition
Types of neural networks, MLP, KNN, Restricted Boltzmann Machine, topology, training and applications of RBM. Implementation of MLP, KNN and RBM. Metrics, Accuracy Measures: Precision, recall, F-measure, confusion matrix, cross-validation.
Deep learning, applying and validating DBN, Autoencoders, denoising and applying auto encoders and assessing performance. Ensemble methods (bagging, stacking, boosting algorithms), random forest. Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN).
SUGGESTED TEXT BOOKS:
- Elements of Deep Learningg for Computer Vision, Bharat Sikka,bpb,2021.
- Computer Vision. Algorithms and Applications, Richard Szeliski http.//szeliski.org/Book/
- Sebastian Raschka & Vahid Mirjalili,” Python Machine Learning”, Second Edition,Packt>.
- McKinney, Python for Data Analysis. O’ Reilly Publication, 2017.
SUGGESTED REFERENCE BOOKS:
- Learning OpenCV. Computer Vision in C++ with the OpenCV Library (2nd edition) by Gary Bradski, Adrian Kaehler
- Madhavan, “Mastering Python for Data Science”, Packt, 2015.
REFERENCE JOURNALS:
- Journal of Real-Time Image Processing (JRTIP) springer: https://www.springer.com/journal/11554
- IEEE Transactions on Image Processing: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=83
e-RESOURCES INCLUDING LINKS
- NPTEL: Deep Learning for Computer Vision, IIT Hyderabad : https://nptel.ac.in/courses/106106224
- Image processing by Saikiran Panjala, Slideshare: https://www.slideshare.net/MadhushreeGhosh3/image-processing-76619758
