[论文解读] ANN-based Innovative Segmentation Method for Handwritten text in Assamese

Kaustubh Bhattacharyya, Kandarpa Kumar Sarma|ArXiv.org|Nov 4, 2009

Handwritten Text Recognition Techniques参考文献 8被引用 11

一句话总结

本文提出了一种基于人工神经网络（ANN）的动态分割方法，用于手写阿萨姆语文本，克服了传统基于投影的静态分割方法的局限性。通过训练神经网络从过度分割的文本行中识别单个字符，该方法通过模式匹配确定最优分割边界，在低资源印度文字如阿萨姆语中实现了更高的字符级分割准确率。

ABSTRACT

Artificial Neural Network (ANN) s has widely been used for recognition of optically scanned character, which partially emulates human thinking in the domain of the Artificial Intelligence. But prior to recognition, it is necessary to segment the character from the text to sentences, words etc. Segmentation of words into individual letters has been one of the major problems in handwriting recognition. Despite several successful works all over the work, development of such tools in specific languages is still an ongoing process especially in the Indian context. This work explores the application of ANN as an aid to segmentation of handwritten characters in Assamese- an important language in the North Eastern part of India. The work explores the performance difference obtained in applying an ANN-based dynamic segmentation algorithm compared to projection- based static segmentation. The algorithm involves, first training of an ANN with individual handwritten characters recorded from different individuals. Handwritten sentences are separated out from text using a static segmentation method. From the segmented line, individual characters are separated out by first over segmenting the entire line. Each of the segments thus obtained, next, is fed to the trained ANN. The point of segmentation at which the ANN recognizes a segment or a combination of several segments to be similar to a handwritten character, a segmentation boundary for the character is assumed to exist and segmentation performed. The segmented character is next compared to the best available match and the segmentation boundary confirmed.

研究动机与目标

• 为解决手写阿萨姆语字符（一种低资源印度文字）在手写文本识别流程中的准确分割挑战。
• 克服静态投影基分割方法的局限性，后者常因书写风格多变和字符重叠而失效。
• 开发一种基于人工神经网络（ANN）的动态分割方法，根据字符识别自适应地确定分割边界。
• 通过优化分割阶段，提高手写阿萨姆语文本识别的整体准确率。

提出的方法

• 该方法首先使用传统的基于投影的技术，将手写行静态分割为词级组件。
• 然后将每个分割出的词进一步过度分割为更小的子段，以生成潜在的字符边界。
• 训练好的人工神经网络（ANN）评估每个子段及其相邻子段的组合，以判断其是否匹配已知的手写字符。
• 该ANN在来自多个个体收集的手写阿萨姆语字符数据集上进行训练，以确保对书写风格差异的鲁棒性。
• 当ANN以高置信度识别出某一段（或若干段组合）匹配已知字符时，即确认分割边界。
• 最终的分割结果通过将识别出的字符与训练数据库中的最佳匹配进行比较来验证。

实验结果

研究问题

• RQ1 基于ANN的动态分割方法是否能在手写阿萨姆语文本分割中优于传统的静态投影基方法？
• RQ2 当应用于手写阿萨姆语文本的过度分割子词时，ANN在检测最优分割边界方面的有效性如何？
• RQ3 在多样化手写样本上训练ANN，对阿萨姆语字符分割准确率的提升程度如何？
• RQ4 该动态分割方法如何处理手写阿萨姆语文本中重叠或分离不良的字符？

主要发现

• 基于ANN的动态分割方法在手写阿萨姆语文本分割中表现出优于静态投影基分割方法的性能。
• 通过利用ANN的模式识别能力，该动态方法更可靠地识别字符边界，从而实现了更高的分割准确率。
• 采用过度分割结合ANN评估的方式，实现了边界的自适应检测，减少了因书写不一致导致的错误。
• 该方法在处理手写阿萨姆语中常见的笔画粗细变化和字符连接性方面表现出色。
• 通过与训练集中最佳匹配字符的比较，系统确认了分割边界，增强了可靠性。
• 结果表明，ANN在低资源印度文字手写识别任务中可显著提升分割质量。