Sparse patch-histograms for object classification in cluttered images

Authors:
Thomas Deselaers;Andre Hegerath;Daniel Keysers;Hermann Ney
Affiliations:
Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Aachen, Germany;Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Aachen, Germany;Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Aachen, Germany;Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Aachen, Germany
Venue:
DAGM'06 Proceedings of the 28th conference on Pattern Recognition
Year:
2006

Citing 14
Cited 12

Empirical Evaluation of Dissimilarity Measures for Color and Texture

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Object Recognition Using Composed Receptive Field Histograms of Higher Dimensionality

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Classification Error Rate for Quantitative Evaluation of Content-based Image Retrieval Systems

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Local Context in Non-Linear Deformation Models for Handwritten Character Recognition

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
Random Subwindows for Robust Image Classification

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Discriminative Training for Object Recognition Using Image Patches

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Generative versus Discriminative Methods for Object Recognition

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Object Class Recognition Using Multiple Layer Boosting with Heterogeneous Features

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Generic Object Recognition with Boosting

IEEE Transactions on Pattern Analysis and Machine Intelligence
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
TextonBoost: joint appearance, shape and context modeling for multi-class object recognition and segmentation

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Scene classification via pLSA

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
Improving a discriminative approach to object recognition using image patches

PR'05 Proceedings of the 27th DAGM conference on Pattern Recognition

Image classification using cluster cooccurrence matrices of local relational features

MIR '06 Proceedings of the 8th ACM international workshop on Multimedia information retrieval
Exploring the relationship between feature and perceptual visual spaces

Journal of the American Society for Information Science and Technology
Features for image retrieval: an experimental comparison

Information Retrieval
Automatic medical image annotation in ImageCLEF 2007: Overview, results, and discussion

Pattern Recognition Letters
Discriminative cue integration for medical image annotation

Pattern Recognition Letters
Deformations, patches, and discriminative models for automatic annotation of medical radiographs

Pattern Recognition Letters
Grayscale medical image annotation using local relational features

Pattern Recognition Letters
Chest x-ray characterization: from organ identification to pathology categorization

Proceedings of the international conference on Multimedia information retrieval
Dense simple features for fast and accurate medical X-ray annotation

CLEF'09 Proceedings of the 10th international conference on Cross-language evaluation forum: multimedia experiments
X-ray categorization and spatial localization of chest pathologies

MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part III
Towards the improvement of textual anatomy image classification using image local features

MMAR '11 Proceedings of the 2011 international ACM workshop on Medical multimedia analysis and retrieval
Image retrieval and annotation using maximum entropy

CLEF'06 Proceedings of the 7th international conference on Cross-Language Evaluation Forum: evaluation of multilingual and multi-modal information retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a novel model for object recognition and detection that follows the widely adopted assumption that objects in images can be represented as a set of loosely coupled parts. In contrast to former models, the presented method can cope with an arbitrary number of object parts. Here, the object parts are modelled by image patches that are extracted at each position and then efficiently stored in a histogram. In addition to the patch appearance, the positions of the extracted patches are considered and provide a significant increase in the recognition performance. Additionally, a new and efficient histogram comparison method taking into account inter-bin similarities is proposed. The presented method is evaluated for the task of radiograph recognition where it achieves the best result published so far. Furthermore it yields very competitive results for the commonly used Caltech object detection tasks.