digplanet beta 1: Athena
Share digplanet:

Agriculture

Applied sciences

Arts

Belief

Chronology

Culture

Education

Environment

Geography

Health

History

Humanities

Language

Law

Life

Mathematics

Nature

People

Politics

Science

Society

Technology

Given images containing various known objects in the world, a classifier can be learned from them to automatically categorize the objects in future images. Simple classifiers built based on some image feature of the object tend to be weak in categorization performance. Using boosting methods for object categorization, then, is a way to unify the weak classifiers in a special way to boost the overall ability of categorization.

## Problem of object categorization

Object categorization is a typical task of computer vision which involves determining whether or not an image contains some specific category of object. The idea is closely related with recognition, identification, and detection. Appearance based object categorization typically contains feature extraction, learning a classifier, and applying the classifier to new examples. There are many ways to represent a category of objects, e.g. from shape analysis, bag of words models, or local descriptors such as SIFT, etc. Examples of supervised classifiers are Naive Bayes classifier, SVM, mixtures of Gaussians, neural network, etc. However, recent research has shown that object categories and their locations in images can be discovered in an unsupervised manner as well.[1]

## Status quo for object categorization

The recognition of object categories in images is a challenging problem in computer vision, especially when the number of categories is large. This is due to high intra class variability and the need for generalization across variations of objects within the same category. Objects within one category may look quite different. Even the same object may appear unalike under different viewpoint, scale, and illumination. Background clutter and partial occlusion add difficulties to recognition as well.[2] Humans are able to recognize thousands of object types, whereas most of the existing object recognition systems are trained to recognize only a few, e.g., human face, car, simple objects, etc.[3] Research has been very active on dealing with more categories and enabling incremental additions of new categories, and although the general problem remains unsolved, several multi-category objects detectors (number of categories around 20) for clustered scenes have been developed. One means is by feature sharing and boosting.

## Boosting methods in machine learning

Boosting is a general method for improving the accuracy of any given learning algorithm.[4] A typical application of AdaBoost as one of the popular boosting algorithms is fast face detection by P. Viola and M. Jones, Viola–Jones object detection framework. There AdaBoost is used both to select good features (very simple rectangles) and to turn weak learners into a final strong classifier.

## Using boosting methods for object categorization

### Boosting for binary categorization

We use AdaBoost for face detection as an example of binary categorization. The two categories are faces versus background. The general algorithm is as follows:

1. Form a large set of simple features
2. Initialize weights for training images
3. for T rounds
1. Normalize the weights
2. For available features from the set, train a classifier using a single feature and evaluate the training error
3. Choose the classifier with the lowest error
4. Update the weights of the training images: increase if classified wrongly by this classifier, decrease if correctly
4. Form the final strong classifier as the linear combination of the T classifiers (coefficient larger if training error is small)

After boosting, a classifier constructed from 200 features could yield a 95% detection rate under a $10^{-5}$ false positive rate.[5]

Another application of boosting for binary categorization is a system which detects pedestrians using patterns of motion and appearance.[6] This work is the first to combine both motion information and appearance information as features to detect a walking person. It takes a similar approach as the face detection work of Viola and Jones.

### Boosting for multi-class categorization

Compared with binary categorization, multi-class categorization looks for common features that can be shared across the categories at the same time. They turn to be more generic edge like features. During learning, the detectors for each category can be trained jointly. Compared with training separately, it generalizes better, needs less training data, and requires less number of features to achieve same performance.

The main flow of the algorithm is similar to the binary case. What is different is that a measure of the joint training error shall be defined in advance. During each iteration the algorithm chooses a classifier of a single feature (features which can be shared by more categories shall be encouraged). This can be done via converting multi-class classification into a binary one (a set of categories versus the rest),[7] or by introducing a penalty error from the categories which do not have the feature of the classifier.[8]

In the paper "Sharing visual features for multiclass and multiview object detection", A. Torralba et al. used GentleBoost for boosting and showed that when training data is limited, learning via sharing features does a much better job than no sharing, given same boosting rounds. Also, for a given performance level, the total number of features required (and therefore the run time cost of the classifier) for the feature sharing detectors, is observed to scale approximately logarithmically with the number of class, i.e., slower than linear growth in the non-sharing case. Similar results are shown in the paper "Incremental learning of object detectors using a visual shape alphabet", yet the authors used AdaBoost for boosting.

## References

1. ^ Sivic, Russell, Efros, Freeman & Zisserman, "Discovering objects and their location in images", ICCV 2005
2. ^ A. Opelt, A. Pinz, et al., "Generic Object Recognition with Boosting", IEEE Transactions on PAMI 2006
3. ^ M. Marszalek, "Semantic Hierarchies for Visual Object Recognition", 2007
4. ^ Y. Freund R. E. Schapire, "A Short Introduction to Boosting", 1999
5. ^ P. Viola, M. Jones, "Robust Real-time Object Detection", 2001
6. ^ P. Viola, et al., "Detecting Pedestrians Using Patterns of Motion and Appearance", ICCV 2003
7. ^ A. Torralba, K. P. Murphy, et al., "Sharing visual features for multiclass and multiview object detection", IEEE Transactions on PAMI 2006
8. ^ A. Opelt, et al., "Incremental learning of object detectors using a visual shape alphabet", CVPR 2006

Original courtesy of Wikipedia: http://en.wikipedia.org/wiki/Boosting_methods_for_object_categorization — Please support Wikipedia.
A portion of the proceeds from advertising on Digplanet goes to supporting Wikipedia.
 18 videos foundNext >
 Efficient Rotation Invariant Object Detection using Boosted Random Ferns.Object detection using Boosted Random Ferns -BRFs-. Results on IRI Freestyle Motocross Dataset (Test 2). ----- The method makes use of a simple two-step appr... Robust Vehicle Detection in Real Time using a cascade of boosted classifiers - Vishnu K NarayananEEL 6562 Final Project Presentation and Demo. Color Edge Saliency Boosting Using Natural Image StatisticsDavid Rojas Vigo, Joost van de Weijer, Theo Gevers Universitat Autonoma de Barcelona, Spain More videos from the CGIV 2010/MCS'10 conference are available he... Face detection in MATLAB using Adaptive boostingwww.ece301.com for tutorials on how I did this. My first try at face detection using MATLAB. Algorithm completely written by me. Using adaptive boosting and ... Comparison of Colour Difference Methods for Natural ImagesHenri Kivinen, Mikko Nuutinen, Pirkko Oittinen Aalto University School of Science and Technology, Finland More videos from the CGIV 2010/MCS'10 conference ar... 3D people detection and tracking[OVERVIEW] 3D people detection and tracking in range data. This method is able to detect people up to 20m range in urban environments. A 500frames dataset is... radionics trend link - part 12visit http://www.radionics.org Have chi energy sent to your inbox! http://www.chitransfertest.com Watch our live broadcasts and learn how to use chi generato... FPGA Based Real Time Face Detection using Adaboost and Histogram EqualizationThis paper introduces a novel technique to detect faces in real-time with very high detection rate. It is essentially a feature-based approach, in which a cl... Basic Vehicle Tracking ExampleI developed using: Visual Studio C++ 2010, OpenCV 2.3.1, Boost C++ Libraries (1.48.0), cvBlob (0.10.3) More projects: http://be.net/andrewssobral. Human Action Recognition in realistic scenarios - actioncliptrain00014.flvSome of the action classes may be context-free which means that inclusion of the scene in which the action is performed will bring no extra information about...
 18 videos foundNext >

We're sorry, but there's no news about "Boosting methods for object categorization" right now.

 Limit to books that you can completely read online Include partial books (book previews) .gsc-branding { display:block; }

Oops, we seem to be having trouble contacting Twitter

# Talk About Boosting methods for object categorization

You can talk about Boosting methods for object categorization with people all over the world in our discussions.