Abstract
We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of the object: shape, appearance, occlusion and relative scale. An entropy-based feature detector is used to select regions and their scale within the image. In learning the parameters of the scale-invariant object model are estimated. This is done using expectation-maximization in a maximum-likelihood setting. In recognition, this model is used in a Bayesian manner to classify images. The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).
Keywords
Artificial intelligencePattern recognition (psychology)Cognitive neuroscience of visual object recognitionComputer scienceExpectation–maximization algorithmInvariant (physics)Probabilistic logicComputer visionEntropy (arrow of time)Principle of maximum entropyClassifier (UML)Feature extractionContextual image classificationObject detectionMaximum likelihoodMathematicsImage (mathematics)Statistics
Affiliated Institutions
Related Publications
Video Google: a text retrieval approach to object matching in videos
We describe an approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video. The object is represented by a s...
A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition
We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a semi-supervised manner: the model is learnt from example images ...
A Discriminative Framework for Modelling Object Classes
Here we explore a discriminative learning method on underlying generative models for the purpose of discriminating between object categories. Visual recognition algorithms learn...
ORB: An efficient alternative to SIFT or SURF
Feature matching is at the base of many computer vision problems, such as object recognition or structure from motion. Current methods rely on costly descriptors for detection a...
EfficientDet: Scalable and Efficient Object Detection
Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and...
Publication Info
- Year
- 2003
- Type
- article
- Volume
- 2
- Pages
- II-264
- Citations
- 2035
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
2035
OpenAlex
Cite This
Rob Fergus,
Pietro Perona,
Andrew Zisserman
(2003).
Object class recognition by unsupervised scale-invariant learning.
, 2
, II-264.
https://doi.org/10.1109/cvpr.2003.1211479
Identifiers
- DOI
- 10.1109/cvpr.2003.1211479