CV Chapter 4 Recognition and Categorization

1. 3D object is represented by a set of images (So-called appearances)

2. No 3D model of object needed

3. Feature vector matching with multiple training views for recognition

1. 3D object is represented by a global descriptor

2. Match descriptors for recognition

3. Descriptors have built in variations

4. Other variations have to be incorporated by training data

1. Consider edges contours and (oriented) intensity gradients

2. Robust to small shifts and rotations

3. Local histograms offer more spatial information

Find a certain object (identification) and find all appearances of a general object (categorization)

1. Slide window over space and scale // Cluttered scene

2. Feature extraction learned by training data

3. Binary classifier which returns yes or no

Brute force

1. Color histogram // Sensitive to illumination and intraclass

2. Pixel intensities // Sensitive to small shifts

3. Eigenfaces

1. Mean of training images

2. Low dimensional representation of mean with linear subspace

3. Compare new image with face space