Title: | A weight adjustment strategy to prevent cascade of boosted classifiers from overfitting |
Authors: | Park, Ki-Yeong Dong-Seok, Kim |
Citation: | WSCG 2015: full papers proceedings: 23rd International Conference in Central Europeon Computer Graphics, Visualization and Computer Visionin co-operation with EUROGRAPHICS Association, p. 183-189. |
Issue Date: | 2015 |
Publisher: | Václav Skala - UNION Agency |
Document type: | konferenční příspěvek conferenceObject |
URI: | wscg.zcu.cz/WSCG2015/CSRN-2501.pdf http://hdl.handle.net/11025/29516 |
ISBN: | 978-80-86943-65-7 (print) 978-80-86943-61-9 (CD-ROM) |
ISSN: | 2464–4617 (print) 2464–4625 (CD-ROM) |
Keywords: | AdaBoost;bootstrapping;kaskáda posílených klasifikátorů;překlápění;detekce obličeje;detekce chodců |
Keywords in different language: | AdaBoost;bootstrapping;cascade of boosted classifiers;overfitting;face detection;pedestrian detection |
Abstract: | We propose a weight adjustment strategy to prevent a cascade of boosted classifiers from overfitting and to achieve an improved performance. In cascade learning, overfitting often occurs due to the iterative applications of bootstrapping. Since false positives that the previous classifier misclassifies are collected as negative examples through bootstrapping, negative examples more similar to positive examples are prepared as stages go on, and thus classifiers become tuned to the positive examples. When overfitting occurs, the classifier cascade shows performance degradation more in the detection rate than in the false alarm rate. In the proposed strategy, the imbalance between the detection rate and the false alarm rate is evaluated by computing the weight ratio of positive examples to negative examples and it is compensated by adjusting the weight ratio prior to boosting at each stage. Experimental results confirm the effectiveness of the proposed strategy. For experiments, face and pedestrian classifier cascades were trained by employing previous approaches and the proposed strategy. By employing the proposed strategy, the detection rate of classifier cascades was significantly improved for both face and pedestrian. |
Rights: | © Václav Skala - UNION Agency |
Appears in Collections: | WSCG 2015: Full Papers Proceedings |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/29516
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.