https://meet.google.com/pmp-dybr-mzb
Module 1: Digital image fundamentals
Image sampling and quantization, basic relationships between pixels, Intensity Transformations – Image Negatives, Log Transformations, power law transformations, Piecewise Linear Transformation Functions, Histogram Processing.
Module 2: Filters
Spatial Filtering -The mechanics of linear spatial filtering, Spatial correlation and convolution, Separable Filter kernels, Smoothing Spatial Filters, Sharpening Spatial Filters, Filters in Frequency Domain- Frequency Domain filtering fundamentals, Low pass filters, High pass filters, Image Restoration – Mean filters, Order Statistics Filters.
Module 3: Image Segmentation
Image Segmentation- Fundamentals, point, line and edge detection, Thresholding, Region Growing, Region Splitting and Merging, Morphological Watersheds.
Module 4: Colour Image Processing
Color Fundamentals, Color Models, Color Transformations – formulation, color components, color slicing, histogram processing of color images, color image smoothing and sharpening, color image segmentation, Noise in color images.
Module 5: Video Processing
Analog Video – Analog video signal, analog video standards, Digital Video – digital video, digital video standards, Video Enhancement – Spaciotemporal Noise Filtering, Video Segmentation – Change Detection, Dominant Motion Segmentation.
Gonzalez, Rafael C. Digital image processing. Pearson education india, 2009.
Tekalp, A. Murat. Digital video processing. Prentice Hall Press, 2015.
Jain, Anil K. Fundamentals of digital image processing. Prentice-Hall, Inc., 1989.
Module 1: Digital Image Fundamentals (7 Lectures)
Overview of Digital Image Processing
Image Sampling and Quantization
Pixel Relationships and Image Structure
Basic Intensity Transformations
Advanced Intensity Transformations
Histogram Processing: Part 1
Histogram Processing: Part 2
Module 2: Filters (7 Lectures)
Introduction to Spatial Filtering
Linear Spatial Filtering Mechanics
Spatial Correlation and Convolution
Smoothing Spatial Filters
Sharpening Spatial Filters
Frequency Domain Filtering Fundamentals
Image Restoration and Filters
Module 3: Image Segmentation (7 Lectures)
Fundamentals of Image Segmentation
Detection Techniques: Point, Line, and Edge
Thresholding in Image Segmentation
Region Growing Techniques
Region Splitting and Merging
Introduction to Morphological Watersheds
Advanced Techniques in Image Segmentation
Module 4: Color Image Processing (7 Lectures)
Color Image Processing Overview
Color Models and Color Space
Color Transformations and Slicing
Histogram Processing for Color Images
Smoothing and Sharpening of Color Images
Color Image Segmentation
Noise Reduction in Color Images
Module 5: Video Processing (7 Lectures)
Introduction to Video Processing
Analog Video Signal and Standards
Digital Video Fundamentals
Video Enhancement Techniques
Video Segmentation: Basics
Video Segmentation: Advanced Techniques
Motion Detection and Analysis in Video Processing
Review Paper: 15 marks
Assignments : 5 marks
Seminar: 5 marks
Quiz(es): 5 marks
Internal Examination: 10 marks
Rubrics for Assessment of Review Paper
TBA
Objective:
Write a Python program to demonstrate the concept of image sampling, where an input image is translated into a grid of individual pixels that can be processed and stored by digital devices.
Requirements:
Implement a function display_sampling that takes in three parameters:
image_path: A string representing the path to the image.
desired_width: An integer representing the desired width of the output image in pixels.
desired_height: An integer representing the desired height of the output image in pixels.
The function should read the image from the provided path and display both the original and sampled versions side by side.
Pixels which are not sampled should have the same value as the previous sampled pixel, effectively creating blocks of uniform color in the sampled image.
The sampled version should be of the same dimensions as the original, but represent the content in the desired width and height.
Properly handle any potential errors like incorrect image paths or issues with image reading.
Hints:
Use libraries like numpy, matplotlib, and OpenCV for image processing.
Carefully consider how to calculate the sampling rate based on the desired output dimensions.
Rubrics (Total: 100 points)
Functionality (60 points total)
Correctly reading the image: 10 points
Accurate calculation of the sampling rate based on desired dimensions: 20 points
Proper sampling of the image, including the "previous pixel" fill requirement: 20 points
Displaying the original and sampled images side by side: 10 points
Error Handling (20 points total)
Handling incorrect image paths gracefully (e.g., displaying an error message): 10 points
Handling other potential issues like invalid desired dimensions: 10 points
Code Quality (10 points total)
Cleanliness and readability of the code: 5 points
Proper comments and documentation: 5 points
Efficiency (10 points total)
Efficient implementation without unnecessary computations: 10 points
Submission
Create a folder with the name <YourRollNo.>_<YourName> in this folder.
Upload your .ipynb file with the results. The file should be named as <YourRollNo.>_<YourName>.ipynb. The first cell in the notebook should contain your name and roll no.
Along with the .ipynb file, upload a single image displaying the original and the sampled images side by side. You can decide the values for the desired height and width.
Date
Assigned on 05-10-2023
Due on 11-10-2023
Fundamentals of Image Segmentation
Definition and purpose of image segmentation.
Overview of different segmentation techniques.
Comparison of manual vs. automatic segmentation.
Role of image segmentation in various fields (medical, remote sensing, etc.).
Challenges in accurate segmentation.
Impact of image quality on segmentation results.
Future trends and advancements in image segmentation.
Point, Line, and Edge Detection in Image Processing
Introduction to feature detection: purpose and applications.
Methods for detecting points: corner detection, interest point detection.
Techniques for line detection: Hough transform, edge linking.
Edge detection algorithms: Canny, Sobel, Prewitt.
Applications in robotics, surveillance, and medical imaging.
Challenges in accurate feature detection in varied conditions.
Recent advancements and machine learning approaches in feature detection.
Thresholding Techniques in Image Segmentation
Fundamentals of thresholding in image processing.
Binary vs. multi-level thresholding.
Global thresholding techniques: Otsu’s method, iterative methods.
Local and adaptive thresholding strategies.
Application of thresholding in document image analysis and object recognition.
Comparison of thresholding techniques in different scenarios.
Evolving methods in thresholding with AI and deep learning.
Advanced Methods in Region Growing for Image Segmentation
Principles and basics of region growing.
Seed selection and region growing criteria.
Handling noise and variation in region growing.
Application in segmentation of textured images.
Comparison with other segmentation techniques.
Optimization strategies for efficient region growing.
Use of region growing in 3D imaging and volumetric data.
Region Splitting and Merging: Techniques and Applications
Introduction to region splitting and merging.
Algorithms and criteria for region splitting.
Process of region merging and its advantages.
Application in satellite imagery and geographical information systems.
Challenges in handling large and complex images.
Integration with other segmentation techniques.
Recent developments and future potential of region splitting and merging.
Morphological Watersheds in Image Processing
Understanding the concept of morphological watersheds.
Algorithmic approach to watershed segmentation.
Handling over-segmentation in watershed methods.
Applications in biological imaging and materials science.
Integration with other morphological operations.
Challenges and limitations in practical applications.
Recent advancements in watershed algorithms.
Color Image Processing: An Introduction
Fundamentals of color image processing.
Color models: RGB, CMYK, HSV, and their uses.
Color spaces and color conversion techniques.
Importance in digital image processing and graphics.
Color balancing and correction techniques.
Role in enhancing visual perception.
Future trends in color processing with AI and machine learning.
Color Transformations in Image Processing
Basics of color transformations.
Techniques for color space conversion.
Color component manipulation for image enhancement.
Applications in artistic rendering and visual effects.
Color model-based image processing algorithms.
Challenges in maintaining color fidelity.
Emerging technologies in color transformation.
Histogram Processing of Color Images
Introduction to histograms in color image processing.
Techniques for color histogram equalization.
Use of histogram in contrast enhancement and color balancing.
Multidimensional histograms for complex color processing.
Applications in image retrieval and indexing.
Challenges in histogram processing of high dynamic range images.
Latest trends in histogram processing using deep learning.
Color Image Segmentation Techniques
Overview of color image segmentation methods.
Importance of color information in segmentation.
Techniques: region-based, clustering-based, and boundary-based segmentation.
Application in medical imaging, surveillance, and autonomous vehicles.
Challenges in segmenting images with varying color dynamics.
Integration with machine learning for improved segmentation.
Future directions in color image segmentation research.
Noise Reduction Techniques in Color Images
Types of noise typically found in color images.
Spatial vs. frequency domain techniques for noise reduction.
Algorithms: median filter, Gaussian filter, wavelet transforms.
Impact of noise reduction on image quality.
Applications in digital photography and video processing.
Adaptive noise reduction techniques.
Advanced noise reduction using AI and deep learning.
Analog Video Standards and Signal Processing
Overview of analog video standards (NTSC, PAL, SECAM).
Characteristics of analog video signals.
Techniques for analog signal processing and enhancement.
Conversion of analog to digital video signals.
Role of analog standards in modern broadcasting.
Challenges in preserving and digitizing analog video.
Future of analog video in a digital world.
Digital Video and Its Standards
Introduction to digital video technology.
Comparison of various digital video standards (HDTV, SDTV, 4K, 8K).
Digital video compression techniques (MPEG, H.264, HEVC).
Importance of digital standards in streaming and broadcasting.
Challenges in digital video transmission and storage.
Impact of digital video on media consumption.
Emerging trends and future of digital video standards.
Video Enhancement: Spatiotemporal Noise Filtering
Understanding video noise and its sources.
Techniques for spatiotemporal noise filtering.
Comparison of various noise filtering algorithms.
Impact of noise filtering on video quality.
Application in surveillance, film restoration, and broadcasting.
Adaptive and AI-based noise filtering methods.
Challenges and future directions in video noise reduction.
Video Segmentation: Change Detection Techniques
Fundamentals of video segmentation.
Techniques for change detection in video streams.
Application in event detection and video surveillance.
Challenges in detecting changes in dynamic scenes.
Integration with machine learning for improved accuracy.
Real-time change detection methods.
Future trends in automated video analysis.
Dominant Motion Segmentation in Video Processing
Understanding dominant motion in video scenes.
Techniques for segmenting and tracking dominant motion.
Application in sports analysis, traffic monitoring, and film editing.
Challenges in accurate motion segmentation.
Role of optical flow and motion vectors.
Advanced methods using deep learning and AI.
Future of motion analysis in automated video processing.
Advanced Color Correction Techniques in Digital Media
The importance of color correction in image and video processing.
Techniques for advanced color grading and correction.
Tools and software commonly used in the industry.
Application in film, television, and digital photography.
Balancing artistic intent with technical constraints.
Role of color theory in color correction.
Future trends and technology in color correction.
Content (40 marks)
Accuracy (10 marks): Information is factually correct, well-researched.
Relevance (10 marks): Content is directly related to the seminar topic and objectives.
Depth (10 marks): Presentation covers the topic comprehensively, including background information and current trends.
Originality (10 marks): The presentation provides unique insights or a novel approach to the topic.
Organization (20 marks)
Structure (10 marks): Clear introduction, body, and conclusion; logical flow of ideas.
Pacing (10 marks): Time is well-managed, with neither rushed nor excessively slow segments.
Audio and Voice Delivery (20 marks)
Clarity (10 marks): Speaker articulates clearly, with good diction and appropriate volume.
Engagement (10 marks): Speaker uses tone variation and pauses effectively to maintain interest.
Visual Aids (10 marks)
Quality (5 marks): Slides or visual aids are legible, aesthetically pleasing, and free from excessive text.
Usefulness (5 marks): Visual aids enhance understanding of the topic and are relevant to the content discussed.
Understanding and Knowledge (10 marks)
Grasp of Topic (5 marks): Speaker demonstrates a strong understanding of the subject matter.
Responses to Hypothetical Questions (5 marks): Speaker anticipates and addresses potential questions in the presentation.
Technical Quality (10 marks)
Video/Audio Quality (10 marks): The audio is clear without background noise, and the video (if any visual elements are present) is steady and well-lit.
Please upload the slides and the videos here. Do not create a separate folder for each student. Format for filename: <RollNo>_<Name>_<Slides/Video>