Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Fast face recognition by using an inverted index

: Herrmann, C.; Beyerer, Jürgen

Postprint urn:nbn:de:0011-n-3436067 (833 KByte PDF)
MD5 Fingerprint: 7e4c916be974602b644cce49f09f68d7
Copyright Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.
Created on: 20.8.2015

Lam, E.Y. ; Society of Photo-Optical Instrumentation Engineers -SPIE-, Bellingham/Wash.:
Image Processing: Machine Vision Applications VIII : 10-11 February 2015, San Francisco, California
Bellingham, WA: SPIE, 2015 (Proceedings of SPIE 9405)
ISBN: 978-1-62841-495-0
Paper 940507, 7 pp.
Conference "Image Processing - Machine Vision Applications" <8, 2015, San Francisco/Calif.>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()
face recognition; video retrieval; large-scale; fisher vector; bag of words

This contribution addresses the task of searching for faces in large video datasets. Despite vast progress in the field, face recognition remains a challenge for uncontrolled large scale applications like searching for persons in surveillance footage or internet videos. While current productive systems focus on the best shot approach, where only one representative frame from a given face track is selected, thus sacrificing recognition performance, systems achieving state-of-the-art recognition performance, like the recently published DeepFace, ignore recognition speed, which makes them impractical for large scale applications. We suggest a set of measures to address the problem. First, considering the feature location allows collecting the extracted features in according sets. Secondly, the inverted index approach, which became popular in the area of image retrieval, is applied to these feature sets. A face track is thus described by a set of local indexed visual words which enables a fast search. This way, all information from a face track is collected which allows better recognition performance than best shot approaches and the inverted index permits constantly high recognition speeds. Evaluation on a dataset of several thousand videos shows the validity of the proposed approach.