Please use this identifier to cite or link to this item:
|Type:||Artigo de evento|
|Title:||A Robust Adaboost-based Algorithm For Low-resolution Face Detection|
|Abstract:||This work presents a face detection algorithm based on Multiscale Block Local Binary Patterns (MB-LBP) and an improved AdaBoost algorithm. The proposed boosting algorithm is capable of avoiding sample overfitting over its training process. This goal is achieved by making use of the information of sample misclassification frequency to update the weight distribution in the training process. Experimental results evidence some advantages of the proposed method over the classical AdaBoost algorithms, including the generalization capacity, overfitting avoidance and high precision rate on low-resolution images. © 2012 Springer-Verlag.|
|Appears in Collections:||Unicamp - Artigos e Outros Documentos|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.