Two combination stages of clustered One-Class Classifiers for writer identification from text fragments. (October 2018)

• Record Type: Journal Article
• Authors: Hadjadji, Bilal; Chibani, Youcef
• Is Part Of: Pattern recognition. Volume 82(2018:Oct.)
• Page Start: 147
• Page End: 162
• Publication Date: 2018-10
• Subjects: Clustered one-class classifiers -- Dynamic fragment weighting combination -- Choquet fuzzy integral -- Writer identification -- Text fragments; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2018.05.001
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Propose a new writer identification system based on text fragments. Use the clustered One-Class classifier for writer identification from text fragments. Propose a new dynamic fragment weighting combination rule. Propose the use of Choquet fuzzy integral to combine multiple systems. The two combination stages of the proposed system offers a competitive performance. Abstract: Writer identification based on handwritten fragments has been reported to give interesting performance. However, while the fragmentation process, inconsistent fragments are generated and affect badly the identification accuracy. Hence, in this paper, a clustered-based One-Class Classifier (OCC) is proposed in order to generate more robust classification model than the distance-based classifier for handwritten fragments. Besides, the problem of inconsistent fragments expands its effect to the test step. Thus, a Dynamic Fragment Weighting Combination (DFWC) rule is proposed to reduce the effect of inconsistent test fragments. Furthermore, due to the difficulty of performing a generic descriptor, three different descriptors related systems are designed and combined through an effective combination scheme based on Choquet fuzzy integral operator. Experimental results conducted on the well-known IFN/ENIT and IAM datasets show good adaptation of the OCC with DFWC. Moreover, the Choquet combination scheme offers more improvements to achieve 97.56% and 94.51% for the used datasets, respectively. The obtained results highlight the reliability of the proposed system in comparison with recent studies for writer identification issue.