A deep learning framework for text-independent writer identification. (October 2020)

• Record Type: Journal Article
• Authors: Javidi, Malihe; Jampour, Mahdi
• Is Part Of: Engineering applications of artificial intelligence. Volume 95(2020)
• Publication Date: 2020-10
• Subjects: Enhanced ResNet -- Deep residual networks -- Text-independent -- Handwriting writer recognition; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2020.103912
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Handwriting Writer Identification (HWI) refers to the process of handwriting text image analysis to identify the authorship of the documents. It has yielded promising results in various applications, including digital forensics, criminal purposes, exploring the writer of historical documents, etc. The complexity of the text image, especially in images with various handwriting makes the writer identification difficult. In this work, we propose an end-to-end system that relies on a straightforward yet well-designed deep network and very efficient feature extraction, emphasizing feature engineering. Our system is an extended version of ResNet by conjugating deep residual networks and a new traditional yet high-quality handwriting descriptor towards handwriting analysis. Our descriptor analyzes the handwriting thickness as a preliminary and essential feature for human handwriting characteristics. Our approach can also provide text-independent writer identification that we do not need to have the same handwriting content for learning our model. The proposed approach is evaluated and achieved consistent results on four public and well-known datasets of IAM, Firemaker, CVL, and CERUG-EN. We empirically demonstrate that our conjugated network outperforms the original ResNet, and it can work well for real-world applications in which patches with few letters exist. Highlights: We proposed an efficient system for offline text-independent handwriting writer identification. An extended architecture of ResNet along with traditional features is proposed. A new handwritten thickness descriptor (HTD) is proposed. Analysis of deep and traditional features is provided. We evaluated our approach on four well-known datasets of IAM, Firemaker, CVL, and CERUG-EN.