Estimating 3D hand pose using hierarchical multi-label classification
This paper presents an analysis of the design of classifiers for use in a hierarchical object recognition approach. In this approach, a cascade of classifiers is arranged in a tree in order to recognize multiple object classes. We are interested in the problem of recognizing multiple patterns as it...
| Auteurs principaux: | , , , |
|---|---|
| Format: | Journal article |
| Langue: | English |
| Publié: |
Elsevier
2006
|
| _version_ | 1826313472363724800 |
|---|---|
| author | Stenger, B Thayananthan, A Torr, PHS Cipolla, R |
| author_facet | Stenger, B Thayananthan, A Torr, PHS Cipolla, R |
| author_sort | Stenger, B |
| collection | OXFORD |
| description | This paper presents an analysis of the design of classifiers for use in a hierarchical object recognition approach. In this approach, a cascade of classifiers is arranged in a tree in order to recognize multiple object classes. We are interested in the problem of recognizing multiple patterns as it is closely related to the problem of locating an articulated object. Each different pattern class corresponds to the hand in a different pose, or set of poses. For this problem obtaining labelled training data of the hand in a given pose can be problematic. Given a parametric 3D model, generating training data in the form of example images is cheap, and we demonstrate that it can be used to design classifiers almost as good as those trained using non-synthetic data. We compare a variety of different template-based classifiers and discuss their merits. |
| first_indexed | 2024-09-25T04:13:58Z |
| format | Journal article |
| id | oxford-uuid:74c0477d-ea88-407e-9ba0-6e8ccf80114c |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-09-25T04:13:58Z |
| publishDate | 2006 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oxford-uuid:74c0477d-ea88-407e-9ba0-6e8ccf80114c2024-07-11T11:42:37ZEstimating 3D hand pose using hierarchical multi-label classificationJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:74c0477d-ea88-407e-9ba0-6e8ccf80114cEnglishSymplectic ElementsElsevier2006Stenger, BThayananthan, ATorr, PHSCipolla, RThis paper presents an analysis of the design of classifiers for use in a hierarchical object recognition approach. In this approach, a cascade of classifiers is arranged in a tree in order to recognize multiple object classes. We are interested in the problem of recognizing multiple patterns as it is closely related to the problem of locating an articulated object. Each different pattern class corresponds to the hand in a different pose, or set of poses. For this problem obtaining labelled training data of the hand in a given pose can be problematic. Given a parametric 3D model, generating training data in the form of example images is cheap, and we demonstrate that it can be used to design classifiers almost as good as those trained using non-synthetic data. We compare a variety of different template-based classifiers and discuss their merits. |
| spellingShingle | Stenger, B Thayananthan, A Torr, PHS Cipolla, R Estimating 3D hand pose using hierarchical multi-label classification |
| title | Estimating 3D hand pose using hierarchical multi-label classification |
| title_full | Estimating 3D hand pose using hierarchical multi-label classification |
| title_fullStr | Estimating 3D hand pose using hierarchical multi-label classification |
| title_full_unstemmed | Estimating 3D hand pose using hierarchical multi-label classification |
| title_short | Estimating 3D hand pose using hierarchical multi-label classification |
| title_sort | estimating 3d hand pose using hierarchical multi label classification |
| work_keys_str_mv | AT stengerb estimating3dhandposeusinghierarchicalmultilabelclassification AT thayananthana estimating3dhandposeusinghierarchicalmultilabelclassification AT torrphs estimating3dhandposeusinghierarchicalmultilabelclassification AT cipollar estimating3dhandposeusinghierarchicalmultilabelclassification |