# Computer Science & Engineering Department

## Prerequisites

Good background in image processing (CS674), computer vision (CS685), pattern recognition (CS679), linear algebra, probabilities, and statistics.

## Texts

We will not use any text in this course; all of the material will be drawn from lecture notes and research papers.

## Useful Texts

• Emanuele Trucco, Alessandro Verri, Introductory Techniques for 3-D Computer Vision, Prentice Hall, 1998.
• Forsyth and Ponce, Computer Vision - A modern approach, Prentice Hall, 2002.
• Shapiro and Stockman, Computer Vision, Prentice Hall, 2001.

## Description and Objectives

Recognizing objects from images has been a challenging task in computer vision. This is because objects may look very different from different viewing positions. The most successful approach is in the context of "model-based" object recognition, where the environment is rather constrained and recognition relies upon the existence of a set of predefined model objects. Given an unknown scene, recognition implies: (i) the identification of a set of features from the unknown scene which approximately match a set of features from a known view of a model object, (ii) the recovery of the geometric transformation that the model object has undergone (i.e., pose recovering) and, (iii) verification that other features coincide with predictions. Since usually there is no a-priori knowledge of which model points correspond to which scene points, recognition can be computationally too expensive, even for a moderate number of models. Our goal in this course would be to study several well known techniques in object recognition.

This course is primarily intended for highly motivated students interested in doing research in object recognition and computer vision in general. It will be essential for students to have a solid understanding of basic topics in math, such as linear algebra, probability and statistics, and calculus. It will also be useful to have some knowledge of computer vision, image processing, and geometry. In general, the more math a student knows, the easier the course will be.

## Topics

• Image Formation and Perspective Projection
• Approximations to Perspective Projection
• Segmentation and Feature Extraction
• 2D Object Recognition Using Geometric Models
• 3D Object Recognition Using Geometric Models
• Object Recognition Using Appearance Models
• Grouping
• Error Analysis

## Course Requirements

This course is primarily intended for highly motivated students interested in doing research in object recognition and computer vision in general. It will be essential for students to have a solid understanding of basic topics in math, such as linear algebra, probability and statistics, and calculus. It will also be useful to have some knowledge of computer vision, image processing, and geometry. There would be no exams in this course. Grading will be based on paper presentations, reports, class participation, and a project. Details are provided in the course syllabus.

## Project Topics

Department of Computer Science & Engineering, University of Nevada, Reno, NV 89557
Page created and maintained by: Dr. George Bebis (bebis@cse.unr.edu)