A novel framework for generating handwritten datasets

Abstract

The performance of deep learning algorithms is highly dependent on the size and diversity of data. However, for handwritten character recognition, dataset creation, segmentation, and labeling are time consuming and laborious tasks and not much researched. This work proposes a novel and generic framework which automates the segmentation and labeling processes for handwritten datasets. First, a user collects handwritten glyphs on the proposed form. Next, based on a priori knowledge, local peaks from horizontal and vertical projection functions are computed. This helps in locating and segmenting individual samples automatically. To show the effectiveness of the proposed framework, a dataset of 160,000 samples is collected for an oriental language. We profile the segmentation of samples from one sheet with three approaches: manual, semi-automatic, and the proposed fully automatic approach. Compared to the manual and semi-automatic processes, the proposed approach is 120 × and 65 × faster, respectively. Further, we also present the classification of this dataset by traditional and state-of-the-art machine learning algorithms.