An online writer identification system using regression-based feature normalization and codebook descriptors |
| |
| Affiliation: | 1. School of Mathematics and Statistics, Wuhan University, Wuhan 430072, PR China;2. School of Management, Huaibei Normal University, Huaibei 235000, PR China;3. Computational Science Hubei Key Laboratory, Wuhan University, Wuhan, 430072, PR China;1. School of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, South Korea;2. Mobile Division, Samsung Electronics, Suwon 16677, South Korea;1. School of Management and Economics, Beijing Institute of Technology, Beijing 100081, China;2. School of Business Administration, Southwestern University of Finance and Economics, Chengdu 610074, China;3. Katz Graduate School of Business, University of Pittsburgh, Pittsburgh, PA 15260, USA;1. Centro de Investigação de Montanha (CIMO), Escola Superior Agrária, Instituto Politécnico de Bragança, Campus de Santa Apolónia, Apartado 1172, 5301-854 Bragança, Portugal;2. Unidade de Xestión Forestal Sostible (UXFS), Departamento de Enxeñaría Agroforestal, Escola Politécnica Superior, Universidade de Santiago de Compostela, Campus Terra, 27002 Lugo, Spain |
| |
| Abstract: | This paper describes a strategy to identify the authorship of online handwritten documents. We regard our research framework to that of a retrieval problem and adapt the so called codebook based Vector of Local Aggregate descriptor (VLAD) that has been promising for the object retrieval application in image processing. The codebook comprises a set of code vectors with associated Voronoi cells computed from a clustering algorithm on a set of feature vectors along the online trace. However, we show that the VLAD formulation at times, cannot effectively discriminate between writers, when their respective feature vectors are not linearly separable in the Voronoi cell of the code vectors. To overcome this problem, we propose a novel descriptor that improves upon the VLAD formulation. Secondly, we explore a normalization for the feature vectors prior to the generation of the VLAD. Our method is different to the min–max and z-score in that it takes care in ensuring that the codevectors are not influenced by the presence of outliers in the data. The performance of our proposed descriptor with the new feature normalization are evaluated on two publicly available Online Handwriting Databases – the IAM and IBM-UB1. The results show a marked improvement over the VLAD. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
