Recognition of isolated handwritten Farsi/Arabic alphanumeric using fractal codes

6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004. Pub Date : 2004-03-28 DOI:10.1109/IAI.2004.1300954

S. Mozaffari, K. Faez, H. Kanan

{"title":"Recognition of isolated handwritten Farsi/Arabic alphanumeric using fractal codes","authors":"S. Mozaffari, K. Faez, H. Kanan","doi":"10.1109/IAI.2004.1300954","DOIUrl":null,"url":null,"abstract":"We propose a new method for isolated handwritten Farsi/Arabic characters and numerals recognition using fractal codes. Fractal codes represent affine transformations which, when iteratively applied to the range-domain pairs in an arbitrary initial image, give results close to the given image. Each fractal code consists of six parameters, such as corresponding domain coordinates for each range block, brightness offset and an affine transformation, which are used as inputs for a multilayer perceptron neural network for learning and identifying an input. This method is robust to scale and frame size changes. Farsi's 32 characters are categorized to 8 different classes in which the characters are very similar to each other. There are ten digits in the Farsi/Arabic languages, but since two of them are not used in postal codes in Iran, only 8 more classes are needed for digits. According to experimental results, classification rates of 91.37% and 87.26% were obtained for digits and characters respectively on the test sets gathered from various people with different educational background and different ages.","PeriodicalId":326040,"journal":{"name":"6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004.","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2004-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"49","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IAI.2004.1300954","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 49

Abstract

We propose a new method for isolated handwritten Farsi/Arabic characters and numerals recognition using fractal codes. Fractal codes represent affine transformations which, when iteratively applied to the range-domain pairs in an arbitrary initial image, give results close to the given image. Each fractal code consists of six parameters, such as corresponding domain coordinates for each range block, brightness offset and an affine transformation, which are used as inputs for a multilayer perceptron neural network for learning and identifying an input. This method is robust to scale and frame size changes. Farsi's 32 characters are categorized to 8 different classes in which the characters are very similar to each other. There are ten digits in the Farsi/Arabic languages, but since two of them are not used in postal codes in Iran, only 8 more classes are needed for digits. According to experimental results, classification rates of 91.37% and 87.26% were obtained for digits and characters respectively on the test sets gathered from various people with different educational background and different ages.

查看原文本刊更多论文

识别孤立的手写波斯语/阿拉伯字母数字使用分形代码

本文提出了一种基于分形码的孤立手写波斯语/阿拉伯语字符和数字识别新方法。分形码表示仿射变换，当迭代应用于任意初始图像的范围-域对时，得到接近给定图像的结果。每个分形码由六个参数组成，如每个范围块对应的域坐标、亮度偏移和仿射变换，这些参数被用作多层感知器神经网络的输入，用于学习和识别输入。该方法对缩放和帧大小变化具有鲁棒性。波斯语的32个汉字被分为8个不同的类别，这些类别中的字符彼此非常相似。波斯语/阿拉伯语中有10个数字，但由于其中两个在伊朗的邮政编码中不使用，因此只需要8个数字类。实验结果表明，在不同教育背景和不同年龄人群的测试集上，数字和字符的分类率分别为91.37%和87.26%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004.

自引率

0.00%

发文量