基于人工神经网络的鼠标手势英语句子识别
English Sentence Recognition using Artificial Neural Network through Mouse-based Gestures
摘要：
手写是人们日常交流的重要手段之一。虽然手写体识别问题已经被考虑了60多年，但仍然有许多悬而未决的问题，特别是在无约束手写句子识别任务中。本文研究了基于人工神经网络的连续英文句子自动识别系统。所提出的人工神经网络是使用传统的自监督神经网络的反向传播算法进行训练的，该算法为系统提供了很强的学习能力，从而在前馈人工神经网络的训练中被证明是非常成功的。所设计的算法不仅能够翻译离散的手势动作，而且能够通过鼠标翻译连续的手势。本文采用高效的神经网络方法对鼠标画出的英文句子进行识别。该方法有效地提取了英语句子的边界，确定了识别英语句子的区域，并将其绘制在图像中，然后利用人工神经网络进行识别。所提出的方法英语句子识别（ESR）系统的设计和测试成功。实验结果表明，该方法具有较高的检测速度和检测精度.
英文摘要：
Handwriting is one of the most important means of daily communication. Although the problem of handwriting recognition has been considered for more than 60 years there are still many open issues, especially in the task of unconstrained handwritten sentence recognition. This paper focuses on the automatic system that recognizes continuous English sentence through a mouse-based gestures in real-time based on Artificial Neural Network. The proposed Artificial Neural Network is trained using the traditional backpropagation algorithm for self supervised neural network which provides the system with great learning ability and thus has proven highly successful in training for feed-forward Artificial Neural Network. The designed algorithm is not only capable of translating discrete gesture moves, but also continuous gestures through the mouse. In this paper we are using the efficient neural network approach for recognizing English sentence drawn by mouse. This approach shows an efficient way of extracting the boundary of the English Sentence and specifies the area of the recognition English sentence where it has been drawn in an image and then used Artificial Neural Network to recognize the English sentence. The proposed approach English sentence recognition (ESR) system is designed and tested successfully. Experimental results show that the higher speed and accuracy were examined.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
