Length Independent Writer Identification Based on the Fusion of Deep and Hand-Crafted Descriptors

Alaa Sulaiman,Khairuddin Omar,Mohammad F Nasrudin,Anas Arram

doi:10.1109/access.2019.2927286

Abstract

Writer's identification from a handwritten text is one of the most challenging machines learning problems because of the variable handwritten sources, various languages, the similarity between writer's pattern, context variation, and implicit characteristics of handwriting styles. In this paper, a combination of the deep and hand-crafted descriptor is utilized to learn patterns from the handwritten images. First, to do so, the local patches are extracted from the handwritten images. Then, these patches are simultaneously fed to deep and hand-crafted descriptors to generate the local descriptions. The extracted local features are then assembled to make the whole description matrix. Finally, by applying the vector of locally aggregated descriptors (VLAD) encoding on the description matrix, a 1-D feature vector is extracted to represent the writer's pattern. It is worthwhile to mention that the generated description does not rely on any language model or context information. Thus, the proposed approach is language and content independent. In addition, the proposed method does not have any restriction on the input length, hence, the writer's sample can be a passage, paragraph, line, sentence, or even a word. The obtained results on three public benchmark datasets of IAM, CVL, and Khatt indicate that the proposed method has a high-accuracy rate in writing identification task. Furthermore, the performance of the proposed method on CVL dataset using both German and English samples demonstrates that the proposed approach has a high capability in learning a writer's pattern from both languages at the same time.

Highlights

During recent years, writer identification from handwriting text images became an interesting application and a hot research topic in the areas of computer vision and machine learning
EXPERIMENTAL RESULTS The experimental result of the proposed writer identification method is evaluated on three public benchmarks of IAM, CVL and Khatt datasets
In order to compare the performance of patch-based deep descriptor with the image-based deep descriptor, we only considered complete line images of the English passages for CVL and IAM and Arabic line images for Khatt datasets

Summary

Introduction

Writer identification from handwriting text images became an interesting application and a hot research topic in the areas of computer vision and machine learning. Writer identification is to assign a handwriting text image to a certain writer from a set of pre-defined characteristics, i.e., recognizing a person based on his/her handwriting text images. In spite of the large number of approaches which have been proposed for the writer identification, this field of research is still challenging in computer vision and machine learning. This is due to the large intra-class variability and large interclass similarities in the shape of handwriting text images. It is obvious that writer identification is challenging because of language variation

Methods

Results

Conclusion