CIS 350 Principles and Applications Of Computer Vision

CIS 350 Principles and Applications Of Computer Vision Dr. Rolf Lakaemper

May I introduce myself… • Rolf Lakaemper • Ph. D (Doctorate Degree) 2000 Hamburg University, Germany • Since 1/2003 Assist. Professor at Department of Computer and Information Sciences, Temple University • Main Research Area: Computer Vision

Computer Vision ?

Computer Vision ? “Computer vision’s great trick is extracting descriptions of the world from pictures or sequences of pictures” (Forsyth/Ponce: Computer Vision)

Pictures/Movies: How to • Represent • Process / Prepare • Handle • Recognize Objects

Representation • Digital Images • Color Spaces • Gray Images • Binary Images • Geometrical Properties

Representation • Digital Images • Color Spaces • Gray Images • Binary Images • Geometrical Properties

How to process / prepare: • Filters • Edges • Geometric Primitives • Lines, Circles

Low Level Object Handling: • Image / Video Compression • Huffman • JPEG • MPEG • …

Low Level Object Handling: • Object representation

Low Level Object Handling: • Segmentation

Object Recognition: • Color, Texture, Shape

Object Recognition: • Applications • • • Character recognition Face Recognition Shape Recognition (Image Databases)

Central Distance Fourier (MATLAB DEMO)

3 D Distance Histogram (MATLAB DEMO)

ISS – An Image-Database using the ASR – Algorithm Dr. Rolf Lakaemper

The Interface (JAVA – Applet)

The Sketchpad: Query by Shape

The First Guess: Different Shape - Classes

Selected shape defines query by shape – class

Result

Specification of different shape in shape – class

Result

Let's go for another shape. . .

. . . first guess. . .

. . . and final result

Query by Shape, Texture and Keyword

Result

CIS 350 Schedule: We: Introduction to topic Fr: LAB Mo: Discussion

CIS 350 Schedule: We: Introduction to topic Fr: LAB Mo: Discussion