JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD
JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD B. Tech IV Year COMPUTER VISION Previous Question Paper (July - 2023 - R16)
Note: i) Question paper consists of Part A, Part B. ii) Part A is compulsory, which carries 25 marks. In Part A, Answer all questions. iii) In Part B, Answer any one question from each unit. Each question carries 10 marks and may have a, b as sub questions.
Part A
Define Texture.
Answer
Texture is a visual pattern characterized by the spatial arrangement of intensity variations, colors, or shapes that repeat across a surface. It provides essential information about the surface properties of objects, such as roughness, smoothness, or orientation, independent of color or intensity.
What is meant by Global Thresholding?
Answer
Global Thresholding is an image segmentation technique that partitions an image into foreground and background by applying a single, constant threshold value across the entire image. A pixel is classified as foreground if its intensity is greater than the threshold and background otherwise, based on the assumption that the object and background have distinct intensity distributions.
What is meant by Size Filtering?
Answer
Sign in to view the complete answer paper.
Define Crossing Number.
Answer
Sign in to view the complete answer paper.
What is the application of Foot of Normal Method?
Answer
Sign in to view the complete answer paper.
Why Hough Transform is robust against noise and background clutter?
Answer
Sign in to view the complete answer paper.
What is the physical significance of the straight line contour in gradient space?
Answer
Sign in to view the complete answer paper.
What is meant by Triangulation?
Answer
Sign in to view the complete answer paper.
What are Particle Filters?
Answer
Sign in to view the complete answer paper.
What are Eigen Faces?
Answer
Sign in to view the complete answer paper.
Part B
Explain about the components used in Image processing.
Answer
Sign in to view the complete answer paper.
Discuss how the various filter masks are generated to sharpen images in spatial domain.
Answer
Sign in to view the complete answer paper.
Describe in detail about the different Thresholding methodologies used to segment the object of interest.
Answer
Sign in to view the complete answer paper.
Explain the first and second order derivatives used to detect the edges in an Image.
Answer
Sign in to view the complete answer paper.
Discuss the algorithm for Object Labelling and counting in Binary images.
Answer
Sign in to view the complete answer paper.
Describe the centroidal profile approach to shape analysis. Also discuss the problems with the centroidal profile approach.
Answer
Sign in to view the complete answer paper.
Outline the (r, θ) graph method for recognition of objects in two dimensions, and state its main advantages and limitations. Describe the shape of the (r, θ) graph for an equilateral triangle.
Answer
Sign in to view the complete answer paper.
Explain the methods for tackling the problems of Occlusion.
Answer
Sign in to view the complete answer paper.
Describe how the Hough transform may be used to locate straight edges. Explain what is seen in the parameter space if many curved edges also appear in the original image.
Answer
Sign in to view the complete answer paper.
Explain the basic RANSAC algorithm for finding the line with greatest support.
Answer
Sign in to view the complete answer paper.
Round coins of a variety of sizes are to be located, identified, and sorted in a vending machine. Discuss whether the chord-tangent method should be used for this purpose instead of the usual form of Hough transform circle location scheme operating within a 3D (x, y, r) parameter space.
Answer
Sign in to view the complete answer paper.
Describe the methods for overcoming the speed problem in detection of circle using Hough Transform.
Answer
Sign in to view the complete answer paper.
Sketch a curve of the function cosmθ. Estimate what the value of m would have to be for 90% of the R1 component to be reflected within 10˚ of the direction for pure specular reflection.
Answer
Sign in to view the complete answer paper.
State the conditions under which matt surfaces may properly be described as “Lambertian”. Show that the normal at a point on a Lambertian surface must lie on a cone of directions whose axis points to the point source of illumination.
Answer
Sign in to view the complete answer paper.
When visually inferring a 3D representation of a face, it is useful to extract separately both a shape model, and a texture model. Explain the purposes of these steps, their use in morphable models for pose-invariant face recognition, and how the shape and texture models are extracted and later re-combined
Answer
Sign in to view the complete answer paper.
What is Optical Flow? Derive the equation for Optical flow and state the assumptions made in deriving the equation.
Answer
Sign in to view the complete answer paper.
With necessary equations describe the basic idea behind Chamfer matching.
Answer
Sign in to view the complete answer paper.
Discuss in detail about Face Detection and Face Recognition.
Answer
Sign in to view the complete answer paper.
Explain in detail about In-vehicle Vision System.
Answer
Sign in to view the complete answer paper.
Describe the method of Foreground and Background separation in Images.
Answer
Sign in to view the complete answer paper.