期刊
MULTIMEDIA TOOLS AND APPLICATIONS
卷 80, 期 6, 页码 9657-9669出版社
SPRINGER
DOI: 10.1007/s11042-020-09545-7
关键词
Automatic segmentation; Handwritten character recognition; Deep learning algorithms
The study proposes a novel and generic framework for automating the segmentation and labeling processes of handwritten datasets, which is significantly faster than manual and semi-automatic methods. The dataset, consisting of 160,000 samples, was collected for an oriental language and classified using traditional and state-of-the-art machine learning algorithms.
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 x and 65 x faster, respectively. Further, we also present the classification of this dataset by traditional and state-of-the-art machine learning algorithms.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据