Detailed Information on Publication Record
2015
Multi-modal Person Identification
SEDMIDUBSKÝ, Jan, Jakub VALČÍK and Pavel ZEZULABasic information
Original name
Multi-modal Person Identification
Authors
SEDMIDUBSKÝ, Jan (203 Czech Republic, guarantor, belonging to the institution), Jakub VALČÍK (203 Czech Republic, belonging to the institution) and Pavel ZEZULA (203 Czech Republic, belonging to the institution)
Edition
2015
Other information
Language
English
Type of outcome
Software
Field of Study
10201 Computer sciences, information science, bioinformatics
Country of publisher
Czech Republic
Confidentiality degree
není předmětem státního či obchodního tajemství
References:
RIV identification code
RIV/00216224:14330/15:00080528
Organization unit
Faculty of Informatics
Keywords in English
multi-modal person identification; face recognition; walk cycle recognition; motion retrieval
Technical parameters
The more detailed information about this technology along with the information about software acquisition is available at: http://disa.fi.muni.cz/prototype-applications/person-identification/.
Odpovědná osoba pro jednání: prof. Ing. Pavel Zezula, CSc., Fakulta informatiky, Masarykova univerzita, Botanická 68a, Brno, tel.: 54949 7992
Tags
Tags
International impact
Změněno: 25/8/2015 13:37, doc. RNDr. Jan Sedmidubský, Ph.D.
Abstract
V originále
Multi-modal Person Identification (MMPI) is a software technology for multi-modal recognition of persons according to their faces and the way they walk. The recognition process is based on analysis of detected face images and motion capture data — both acquired by motion capturing devices, including popular Microsoft Kinect and ASUS Xtion. The acquired data are firstly preprocessed by (1) detecting face images and extracting MPEG-7 face features and (2) detecting walk cycles and extracting movement features in form of relative velocities of the specific joints for each walk cycle. Both the face and walk-cycle features extracted from a query motion are used to retrieve two independent sets of the most similar faces and walk cycles. These retrieved sets are processed by a multi-modal classification method to recognize the query person identity. The MMPI technology is demonstrated via a web application that allows users to select a query motion and verify whether the technology recognizes the query person correctly.
Links
| VG20122015073, research and development project |
|