A cluster-based statistical model for object detection
- 1 January 1999
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 1046-1053 vol.2
- https://doi.org/10.1109/iccv.1999.790386
Abstract
This paper presents an approach to object detection which is based on recent work in statistical models for texture synthesis and recognition. Our method follows the texture recognition work of De Bonet and Viola (1998). We use feature vectors which capture the joint occurrence of local features at multiple resolutions. The distribution of feature vectors for a set of training images of an object class is estimated by clustering the data and then forming a mixture of Gaussian models. The mixture model is further refined by determining which clusters are the most discriminative for the class and retaining only those clusters. After the model is learned, test images are classified by computing the likelihood of their feature vectors with respect to the model. We present promising results in applying our technique to face detection and car detection.Keywords
This publication has 15 references indexed in Scilit:
- Face recognition using eigenfacesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A general framework for object detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Probabilistic modeling of local appearance and spatial relationships for object recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Texture characterization via joint statistics of wavelet coefficient magnitudesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Face recognition by elastic bunch graph matchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Interpreting face images using active appearance modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1998
- Cluster-based probability model and its application to image and texture processingIEEE Transactions on Image Processing, 1997
- Bayesian face recognition using deformable intensity surfacesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Pyramid-based texture analysis/synthesisPublished by Association for Computing Machinery (ACM) ,1995
- Distortion invariant object recognition in the dynamic link architectureIEEE Transactions on Computers, 1993