Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.
1. Computer Vision Mubarak Shah
Computer Vision Lab
University of Central Florida
Orlando, FL 32816
2. Computer Vision The ability of computers to see.
3. A picture is worth a thousand words.
4. A word is worth a thousand pictures.
5. Image 2-D array of numbers (intensity values, gray levels)
Gray levels 0 (black) to 255 (white)
Color image is 3 2-D arrays of numbers
Resolution (number of rows and columns)
7. Image Formats TIF
8. Video Sequence of frames
30 frames per second
9. Video Clip
10. Sequence of Images
11. Digitization TV camera is analog, need
A to D converter
Digital Cameras do not need digitization
JVC (MPEG through fire wire, USB)
Sony (MPEG through fire wire, USB)
12. Face Recognition
13. Simple Approach Recognize faces (mug shots) using gray levels (appearance)
Each image is mapped to a long vector of gray levels
Several views of each person are collected in the model-base during training
During recognition a vector corresponding to an unknown face is compared with all vectors in the model-base
The face from model-base, which is closest to the unknown face is declared as a recognized face.
14. Problems and Solution Problems :
Dimensionality of each face vector will be very large (250,000 for a 512X512 image!)
Raw gray levels are sensitive to noise, and lighting conditions.
Reduce dimensionality of face space by finding principal components (eigen vectors) to span the face space
Only a few most significant eigen vectors can be used to represent a face, thus reducing the dimensionality
15. Eigen Vectors and Eigen Values
17. Eigen Values
18. Eigen Vectors
19. Face Recognition
20. Face Recognition
21. Face Recognition
22. Face Recognition
23. Training Create A matrix from training images
Compute C matrix from A.
Compute eigenvectors of C.
Compute eigenvectors of L from eigenvectors of C.
Select few most significant eigenvectors of L for face recognition.
Compute coefficient vectors corresponding to each training image.
For each person, coefficients will form a cluster, compute the mean of cluster.
24. Recognition Create a vector u for the image to be recognized.
Compute coefficient vector for this u.
Decide which person this image belongs to, based on the distance from the cluster mean for each person.