...
首页> 外文期刊>Neural computing & applications >Understanding NFC-Net: a deep learning approach to word-level handwrittenIndicscript recognition
【24h】

Understanding NFC-Net: a deep learning approach to word-level handwrittenIndicscript recognition

机译:了解NFC-Net:Word-Level HandwrittinIncecript认可的深入学习方法

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       

摘要

This paper presents a deep learning architecture modified for resource-constrained environments, calledNon-Fully-Connected Networkor NFC-Net, based on convolutional neural network architecture in order to solve the problem ofIndicscript recognition from handwritten word images. NFC-Net mainly targets resource constraint environment where there is a limited computation power or inadequate training samples or restricted training time. Previous approaches to handwritten script recognition included handcrafted features such as structure-based features and texture-based features. In contrast, here our model learns relatively different features from raw input pixels using NFC-Net. Various parameters of the NFC-Net are adjusted to present a vast and comprehensive study of the neural net in the domain of handwritten script recognition. In order to evaluate the performance of the NFC-Net with suitable parameter estimation, a dataset of 18,000 handwritten multiscript word images consisting of 1500 text words from each of the 12 officially recognizedIndicscripts has been considered and a maximum script recognition accuracy of 96.30% is noted. Our proposed model also performs better than some of the recently published script recognition methods in bi-script, tri-script, tetra-script and 12-script scenarios. It has been additionally tested on the RaFD and BHCCD datasets with improved results to prove dataset independency of our model.
机译:本文基于卷积神经网络架构,提出了一种修改用于资源受限环境的深度学习架构,被称为已被称为Networkor NFC-Net,以便解决来自手写字图像的Indicscript识别问题。 NFC-NET主要针对资源约束环境,其中有有限的计算能力或培训样本不足或受限制的培训时间。以前的手写脚本识别方法包括手工制作的功能,例如基于结构的特征和基于纹理的功能。相比之下,我们的模型使用NFC-Net的原始输入像素从原始输入像素中学习相对不同的功能。调整NFC-Net的各种参数,以提出对手写脚本识别领域的神经网络的广泛和全面研究。为了评估NFC-Net的性能,具有合适的参数估计,已经考虑了由12个官方识别的incedicscript中的每一个由1500个文本单词组成的18,000个文本单词的数据集,并指出了96.30%的最大脚本识别准确度。我们所提出的模型也比Bi脚本,三脚脚本,Tetra脚本和12脚本方案中最近发布的脚本识别方法更好地表现更好。它还在RAFD和BHCCD数据集上进行了改进的结果,结果证明了我们模型的数据集独立性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号