Lect 17 - Object Recg ECE620 Summer 2011 Lec 1

Lect 17 - Object Recg ECE620 Summer 2011 Lec 1 - CVIP...

Info iconThis preview shows pages 1–9. Sign up to view the full content.

View Full Document Right Arrow Icon
1 CVIP Laboratory 1 Aly A. Farag University of Louisville Help with these slides were provided by Mostafa Abdelrahman Research Assistant, CVIP Lab, Electrical and Computer Engineering Dept., University of Louisville, KY, 40292 July 5 th , 2011 CVIP Laboratory Object Recognition & Feature Extraction Lecture 1
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
2 CVIP Laboratory 2 Outlines Object Recognition Problem o Definition o Application o Challenges Existing Object Recognition Techniques o Global features approach. o Local features approach. Edge detectors Corner Detectors Blob Detectors Region detectors SIFT CSIFT SPS
Background image of page 2
3 CVIP Laboratory 3 What is object recognition? An object in image processing is a segment of an image that can be interpreted as a single unit. Example of object classes are face, car, motorbike, airplane, etc. this object can be described by pattern of pixels that differs from its immediate neighborhood which called feature . These set of objects attributes, or features, can be used for recognition purposes. Object Definition
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
4 CVIP Laboratory 4 What is object recognition? Object Recognition can be divided in to two main steps: Categorization: what is the class of the object: face, car, motorbike, airplane, etc. Identification: Naming an object in sight “Dr. Farag face”, “my car” End product: Ability to retrieve information of object Object Recognition Definition
Background image of page 4
5 CVIP Laboratory 5 Object Recognition Challenges Why object recognition is difficult? Space of all possible views is large. Present image is not similar to past. Image.(variation)
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
6 CVIP Laboratory 6 Object Recognition Applications Biometric recognition systems based on o Face Recognition o Iris o Fingerprint Surveillance Industrial inspection Content-based image retrieval (CBIR) Robotics Medical imaging Human computer interaction Intelligent vehicle systems ………………………………. to name a few.
Background image of page 6
7 CVIP Laboratory 7 Object Recognition Techniques Objects can be described by different approaches Model-based approaches: Try to represent (approximate) the object as a collection of three dimensional, geometrical primitives (boxes, spheres, cones, cylinders, generalized cylinders, surface of revolution) Shape-based approaches: Represent an object by its shape/contour. Appearance-based models: only appearance of the object-of-interest is used ( like using PCA for face recognition) Based on the applied features these methods can be sub-divided into two main classes, local and global approaches.
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
8 CVIP Laboratory 8 Object Recognition Techniques Local features approaches: Search for salient regions characterized by e.g. corners, edges, or entropy. These regions are characterized by a proper descriptor.
Background image of page 8
Image of page 9
This is the end of the preview. Sign up to access the rest of the document.