Important RGPV Question
AL-603 (A) Image and Video Processing
VI Sem, AIML
Module 1: Image Representation and Analysis
Q.1 What is digital image representation? Explain numerical representation of images.
Q.2 Define computer vision and explain its relationship with image processing.
Q.3 Explain different image enhancement techniques.
Q.4 What are color transforms? Give examples.
Q.5 Differentiate between geometric and color transformations.
Q.6 Explain image augmentation with suitable techniques.
Q.7 Discuss the concept of image filtering and noise reduction.
Q.8 What are common methods used in image preprocessing?
Q.9 Explain the concept of histogram equalization.
Q.10 Define and describe feature recognition in image processing.
Q.11 What is feature extraction? List its applications.
Q.12 Differentiate between low-level and high-level vision tasks.
Q.13 Explain edge detection and its role in feature extraction.
Q.14 Discuss the significance of sharpening and smoothing filters.
Q.15 Numerical: Apply geometric transformation on a given image matrix.
Module 2: Image Segmentation and Object Detection
Q.1 What is image segmentation? Why is it important?
Q.2 Describe thresholding methods for segmentation.
Q.3 What is edge-based segmentation? Explain.
Q.4 Define object detection and explain its steps.
Q.5 Discuss contour detection in digital images.
Q.6 Explain the role of OpenCV in segmentation.
Q.7 What is region growing and region splitting method?
Q.8 Explain the Canny edge detector with steps.
Q.9 Discuss Sobel and Prewitt operators.
Q.10 Explain background subtraction technique for videos.
Q.11 How does morphology help in object segmentation?
Q.12 Compare supervised and unsupervised segmentation.
Q.13 Explain adaptive thresholding with an example.
Q.14 What are contours? How are they detected?
Q.15 Numerical: Apply background subtraction on a frame sequence.
Module 3: Object Motion and Tracking
Q.1 What is object tracking in video processing?
Q.2 Explain single point tracking over time.
Q.3 What are motion models? List types.
Q.4 Describe optical flow and its application in tracking.
Q.5 How to analyze videos as frame sequences?
Q.6 Explain frame differencing method for motion detection.
Q.7 What is feature matching across image frames?
Q.8 Describe Kalman filter for tracking.
Q.9 Explain background modeling in object tracking.
Q.10 What is block matching algorithm?
Q.11 Differentiate between dense and sparse optical flow.
Q.12 Explain how a moving car is tracked using optical flow.
Q.13 Discuss feature tracking using Lucas-Kanade method.
Q.14 Describe Mean-Shift and CamShift algorithms.
Q.15 Numerical: Estimate motion vectors using given image frames.
Module 4: Robotic Localization
Q.1 Define robotic localization.
Q.2 Explain Bayesian statistics for robot localization.
Q.3 How are sensor measurements used for robot navigation?
Q.4 What is Gaussian uncertainty?
Q.5 Discuss Kalman and Particle filters in localization.
Q.6 Explain the working of histogram filter in localization.
Q.7 How does sensor noise affect localization accuracy?
Q.8 Describe SLAM and its relevance.
Q.9 Explain pose estimation using known landmarks.
Q.10 What is the role of environment mapping in robotics?
Q.11 Discuss belief grid approach for localization.
Q.12 How is probability distribution used in position estimation?
Q.13 What is odometry and how is it used in robotics?
Q.14 Explain robot path prediction using statistical models.
Q.15 Numerical: Apply histogram filter on a grid with measurement updates.
Module 5: Image Restoration
Q.1 What is image degradation model?
Q.2 List different types of noise in images.
Q.3 Explain inverse filtering in image restoration.
Q.4 What is Wiener filter? How does it work?
Q.5 How is degradation function estimated?
Q.6 Compare restoration and enhancement.
Q.7 Discuss spatial domain and frequency domain filtering.
Q.8 What is motion blur and how is it corrected?
Q.9 Explain the difference between restoration and reconstruction.
Q.10 Describe median filtering technique.
Q.11 Explain regularization in restoration problems.
Q.12 How to handle periodic noise in restoration?
Q.13 Discuss constrained least square restoration.
Q.14 What are point spread functions?
Q.15 Numerical: Restore an image using Wiener filter with given parameters.
— Best of Luck for Exam —
