Script identification from handwritten documents using SIFT method

机译：使用SIFT方法从手写文档中识别脚本

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Automatic identification of scripts from document images helps selecting appropriate OCR for character recognition and content retrieval. In this paper, Scale invariant Feature Transformation (SIFT) based script identification has been proposed. Features are extracted using SIFT approach at word level (two, three or more character words) and KNN classifier has been used to recognize the script. Experiments are performed by extracting the words from document images consisting of English, Kannada, and Devanagari scripts. Overall accuracy reported for the proposed system is 97.65% and 96.71% for bi-script and tri-scripts, respectively.

机译：从文档图像中自动识别脚本有助于选择合适的OCR进行字符识别和内容检索。本文提出了基于尺度不变特征变换（SIFT）的脚本识别方法。使用SIFT方法在单词级别（两个，三个或更多字符单词）提取特征，并且已使用KNN分类器识别脚本。通过从包含英语，卡纳达语和梵文的脚本的文档图像中提取单词来进行实验。报告的拟议系统的总体准确性（双脚本和三脚本）分别为97.65％和96.71％。

著录项

来源
《IEEE International Conference on Power, Control, Signals and Instrumentation Engineering》|2017年|520-526|共7页
会议地点 Chennai(IN)
作者
G G Rajput; Suryakant Baburao Ummapure;
展开▼
作者单位

Department of Computer Science Rani Channamma University Belagavi Karnataka India;

Department of Computer Science Gulbarga University Kalaburagi Karnataka India;

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Feature extraction; Character recognition; Optical character recognition software; Image segmentation; Image recognition; Handwriting recognition; Task analysis;

机译：特征提取;字符识别；光学字符识别软件；图像分割图像识别；手写识别；任务分析;

相似文献

外文文献
中文文献
专利

1. Separating Indic Scripts with matra for Effective Handwritten Script Identification in Multi-Script Documents [J] . Obaidullah Sk Md, Goswami Chitrita, Santosh K. C., International Journal of Pattern Recognition and Artificial Intelligence . 2017,第5期

机译：使用matra分隔印度语脚本，以在多脚本文档中有效地识别手写脚本
2. PHDIndic_11: page-level handwritten document image dataset of 11 official Indic scripts for script identification [J] . Obaidullah Sk Md, Halder Chayan, Santosh K. C., Multimedia Tools and Applications . 2018,第2期

机译：PHDIndic_11：11个官方印度脚本的页面级手写文档图像数据集，用于脚本识别
3. Handwritten Indic Script Identification in Multi-Script Document Images: A Survey [J] . Obaidullah Sk Md, Santosh K. C., Das Nibaran, International Journal of Pattern Recognition and Artificial Intelligence . 2018,第10期

机译：多脚本文档图像中的手写印度文字识别：一项调查
4. Script identification from handwritten documents using SIFT method [C] . G G Rajput, Suryakant Baburao Ummapure IEEE International Conference on Power, Control, Signals and Instrumentation Engineering . 2017

机译：使用SIFT方法从手写文档识别脚本标识
5. Writer identification of Arabic handwritten documents. [D] . Awaida, Sameh Mohammad. 2011

机译：阿拉伯手写文件的作家身份证明。
6. Evaluating current automatic de-identification methods with Veteran’s health administration clinical documents [O] . Oscar Ferrández, Brett R South, Shuying Shen, 2012

机译：使用Veteran的健康管理临床文档评估当前的自动去识别方法
7. Identification of Devnagari and Roman Scripts from Multi-script Handwritten Documents [O] . Pawan Kumar Singh, Ram Sarkar, Nibaran Das, 2013

机译：从多脚本手写文档的Devnagari和Roman脚本的识别
8. Script-Independent Text Line Segmentation in Freestyle Handwritten Documents [R] . Li, Y. , Zheng, Y. , Doermann, D. , 2006

机译：自由式手写文档中与脚本无关的文本行分割

Script identification from handwritten documents using SIFT method

摘要

著录项

相似文献

相关主题

期刊订阅