Upload
zukun
View
218
Download
0
Embed Size (px)
Citation preview
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 1/17
Object Class Recognition Using
Discriminative Local Features
Gyuri Dorko and Cordelia Schmid
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 2/17
Introduction
This method is a two step approach to develop adiscriminative feature selection for object partrecognition and detection.
The first step extracts scale and affine invariantlocal features.
The second generates and trains a model using the features in a “weakly supervised” approach.
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 3/17
Local Descriptors
Detectors
Harris-Laplace
Harris-Affine
Entropy (Kadir & Brady)
Descriptors
SIFT (Scale Invariant Feature Transform)
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 4/17
Learning
This is also a two step process
Part Classifier
EM clustering in the descriptor space
Part Selection
Ranking by classification likelihood
Ranking by mutual information criterion
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 5/17
Learning the part classifiers
With the clustering set positive descriptors are obtained to estimate aGaussian Mixture Model (GMM). It is a parametric estimation of theof the probability distribution of the local descriptors.
Where K is the number of Gaussian components and:
The dimension of the vectors x is 128 corresponding to the dimensions of theSIFT features.
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 6/17
Learning the part classifiers
The model parameters mi, Si and P(Ci ) are computed with theexpectation-maximization (EM) algorithm. The EM is initialized with the output of the K-means algorithm. This are the equations toupdate the parameters at the jth maximization (M) step.
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 7/17
Learning the part classifiers
The clusters are obtained from assigning each descriptor to its closestcomponent. The clusters typically contain representative object parts or textures.
Here we see some characteristicclusters of each database.
With the mixture model a boundary is defined for each component toform K part classifiers . Each classifieris associated with one Gaussian
A test feature y is assigned to thecomponent i* having the highestprobability.
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 8/17
Selection
The selection ranks the components according to its ability to discriminate between the object-class and the background.
By classification likelihood. Promotes having hightrue positives and low false positives.
By mutual information. Selects part classifiers based
on the information content to separate backgroundfrom the objects-class.
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 9/17
Ranking by classification likelihood
The ranking is computed as follows:
Where V (u) and V (n) are the unlabeled (potentially positive) descriptors v j(u)
and negative descriptors v j(n) from the validation set . Performs selection by
classification rate. This component hay have very low recall rates. Even
though this parts are individually rare, combinations of them providesufficient recall with excellent precision.
Recall: true features/( true features + true negatives)
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 10/17
Ranking by mutual information
Best to select a few discriminative general partclassifiers.
Ranks parts classifiers basedon their informationcontent for separating thebackground from theobject-class.
The mutual information of component Ci and object-class O is:
Naively assumes all
unlabeled as the object
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 11/17
Final feature Classifier
Based on the ranking, the n part classifiers of thehighest rank are chosen and marked as positive.
The rest are marked as negative, the truenegative and the non-discriminative positiveones.
Note that each part classifier is based on aGaussian component, thus the MAP criteriononly activates one part classifier per descriptor.
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 12/17
Applications
Initial step for localization within images. Theoutput is not binary but a ranking of the partclassification.
Classification of the presence or absence of anobject in an image. Here is required anadditional criterion of how many p positive classified descriptors are required to mark thepresence of an object. The authors uses thisbecause it is easier to compare.
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 13/17
Experimental Results
Precision by detector and ranking
Feature selection with increasing n
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 14/17
Experimental Results
ROC (Receiver Operating Characteristic) True positives on equal-error rate
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 15/17
Experimental Results
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 16/17
Experimental Results
Selection of the entropy detector
Selection results of different feature detectors
8/2/2019 slide: Object Class Recognition Using Discriminative Local Features
http://slidepdf.com/reader/full/slide-object-class-recognition-using-discriminative-local-features 17/17
Thanks!