Deep Adaptive Learning for Writer Identification based on Single Handwritten Word Images

Abstract

There are two types of information in each handwritten word image: explicit information which can be easily read or derived directly, such as lexical content or word length, and implicit attributes such as the author's identity. Whether features learned by a neural network for one task can be used for another task remains an open question. In this paper, we present a deep adaptive learning method for writer identification based on single-word images using multi-task learning. An auxiliary task is added to the training process to enforce the emergence of reusable features. Our proposed method transfers the benefits of the learned features of a convolutional neural network from an auxiliary task such as explicit content recognition to the main task of writer identification in a single procedure. Specifically, we propose a new adaptive convolutional layer to exploit the learned deep features. A multi-task neural network with one or several adaptive convolutional layers is trained end-to-end, to exploit robust generic features for a specific main task, i.e., writer identification. Three auxiliary tasks, corresponding to three explicit attributes of handwritten word images (lexical content, word length and character attributes), are evaluated. Experimental results on two benchmark datasets show that the proposed deep adaptive learning method can improve the performance of writer identification based on single-word images, compared to non-adaptive and simple linear-adaptive approaches.

arXiv commentUnder view of Pattern Recognition

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• An Overview of Multi-Task Learning in Deep Neural Networks
• Self-Transfer Learning for Fully Weakly Supervised Object Localization
• DeepWriter: A Multi-Stream Deep CNN for Text-independent Writer Identification

Cited by in corpus (7)

• FragNet: Writer Identification using Deep Fragment Networks
• Deep Generalized Max Pooling
• Offline Text-Independent Writer Identification based on word level data
• Intra-Variable Handwriting Inspection Reinforced with Idiosyncrasy Analysis
• MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition
• Offline Writer Identification based on the Path Signature Feature
• Self-supervised Deep Reconstruction of Mixed Strip-shredded Text Documents