Project 4: Class Recognition Using Discriminative Local Features

 

  

 

Description

         Implement the part based method for object recognition, described in “Class Recognition Using Discriminative Local Features”, by  G. Dorkó, C. Schmid. Implement only likelihood ranking.

         Test it on Oxford object data set.

         Compare the performance of the algorithm using different point detectors: Saliency Scale, Saliency Affine, Harris-Laplace scale, Harris-Laplace Affine (The code for point detectors is provided).

         Compare the performance of the algorithm with original SIFT and with SIFT without rotation invariance. The initial code for SIFT is provided, but should be edited to remove rotation invariance.

 

Results

The classifier trained on specific category, say airplanes, should be tested on airplanes images and on images of general background. The results should be organized in Receiver Operating Characteristic (ROC). This curve show correct detections as a function of incorrect detections. Then calculate an Equal Error Rate (EER) as

p(True Positive) = 1 - p(False Positive),

True positives are images of airplanes that were classified as containing airplanes. False positives are images of background that were classified as containing airplanes.

Do the same for all the categories.

Compare EER for different choices of interest point detector. Note that the algorithm has a parameter p that should be adjusted when changing the interest point detector.

 

Data set

Oxford dataset: containing faces, airplanes, cars, motorbikes ( The background collection is not very good there)

 

Background images:

In GRAZ_01 download no_bike_no_person.zip

In GRAZ_02 download none.zip

 

Interest Point Detectors

·        Saliency scale detector

·        Saliency affine detector

·        Harris-Laplace and others

 

SIFT Software

·        Matlab

·        C vesrion

 

 

Useful Links

Class lecture on object detection

 "Distinctive image features from scale-invariant keypoints" by David Lowe

“A comparison of affine region detectors”, K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir and L. Van Gool.

“Scale and affine invariant interest point detectors” K. Mikolajczyk, C. Schmid, IJCV, Volume 60, Number 1 - 2004

 

Status

Claimed by Aviv and Pavel