Segmentation-Free Approaches for Handwritten Numeral String Recognition
This addresses the challenge of handwritten numeral string recognition for document analysis, offering an incremental improvement by avoiding over-segmentation burdens.
The paper tackles the problem of recognizing handwritten numeral strings of unknown length without segmentation by proposing segmentation-free methods using Convolutional Neural Networks, achieving state-of-the-art performance and highlighting the importance of contextual information like a length classifier.
This paper presents segmentation-free strategies for the recognition of handwritten numeral strings of unknown length. A synthetic dataset of touching numeral strings of sizes 2-, 3- and 4-digits was created to train end-to-end solutions based on Convolutional Neural Networks. A robust experimental protocol is used to show that the proposed segmentation-free methods may reach the state-of-the-art performance without suffering the heavy burden of over-segmentation based methods. In addition, they confirmed the importance of introducing contextual information in the design of end-to-end solutions, such as the proposed length classifier when recognizing numeral strings.