Automatic learning and extraction of multi-local features
Authors:
- 1 September 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 917-924
Abstract
In this paper we introduce a new kind of feature - the multi-local feature, so named as each one is a collection of local features, such as oriented edgels, in a very specific spatial arrangement. A multi-local feature has the ability to capture underlying constant shape properties of exemplars from an object class. Thus it is particularly suited to representing and detecting visual classes that lack distinctive local structures and are mainly defined by their global shape. We present algorithms to automatically learn an ensemble of these features to represent an object class from weakly labelled training images of that class, as well as procedures to detect these features efficiently in novel images. The power of multi-local features is demonstrated by using the ensemble in a simple voting scheme to perform object category detection on a standard database. Despite its simplicity, this scheme yields detection rates matching state-of-the-art object detection systems.Keywords
This publication has 16 references indexed in Scilit:
- Object detection by global contour shapePattern Recognition, 2008
- A Bayesian, Exemplar-Based Approach to Hierarchical Shape MatchingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Beyond Local Appearance: Category Recognition from Pairwise Interactions of Simple Features2007
- Pictorial Structures for Object RecognitionInternational Journal of Computer Vision, 2005
- Scale-invariant shape features for recognition of object categories2004
- Learning to detect natural image boundaries using local brightness, color, and texture cuesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Object class recognition by unsupervised scale-invariant learning2003
- Interleaved Object Categorization and Segmentation2003
- Generalizing the Hough transform to detect arbitrary shapesPattern Recognition, 1981
- The Representation and Matching of Pictorial StructuresIEEE Transactions on Computers, 1973