An online writer identification system using regression-based feature normalization and codebook descriptors. (15th April 2017)

• Record Type: Journal Article
• Authors: Venugopal, Vivek; Sundaram, Suresh
• Is Part Of: Expert systems with applications. Volume 72(2017)
• Page Start: 196
• Page End: 206
• Publication Date: 2017-04-15
• Subjects: Online writer identification -- Codebook descriptors -- Feature normalization -- IAM Online Handwriting Database -- IBM UB1 database; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2016.11.038
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: Adaptation of the VLAD framework to online writer identification. Addressal of a potential drawback with the VLAD framework. Proposal of a novel descriptor that alleviates the drawback of the VLAD. A feature normalization method that enhances the writer identification performance. Proposal tested on IAM and IBM UB 1 Online Handwriting Databases. 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.