Quantification of the shape of handwritten characters: a step to objective discrimination between writers based on the study of the capital character O.

نویسندگان

  • R Marquis
  • M Schmittbuhl
  • W D Mazzella
  • F Taroni
چکیده

In view of contributing to the scientific validation of the individuality of handwriting, the testing of the two so called fundamental laws of handwriting--1: no two people write exactly alike; 2: no one person writes the same word exactly the same way twice--was approached by analysing the shape of 445 handwritten capital characters O produced by three individuals. A methodology based on classical Fourier descriptors was applied to the characters contours, which were extracted through an automated procedure of image analysis. Precise individual characterization of the shape was possible through Fourier analysis. Within-writer variability of the shape of character O for the writers selected could be shown in an objective and quantitative way through the statistical analysis of the Fourier descriptors. It was demonstrated that this polymorphism differed between the three writers. Differentiation between writers was quantitatively demonstrated by discriminant analysis of the Fourier descriptors, and by the existence of marked morphological distances between the set of characters O of each writer. The degree of dissimilitude of the character O writings could, thus, be assessed. Because of relatively reduced within-writer variability and a pronounced differentiation between the writers, a morphological profile could be established and discrimination between writers could be obtained through the quantification of the shape of one handwritten character.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

بازشناسی برخط حروف مجزای دست‌نویس فارسی بر اساس تشخیص گروه بدنه اصلی با استفاده از ماشین بردار پشتیبان

In this paper a new method for the online recognition of handwritten Persian characters has been proposed which uses a set of simple features and Support Vector Machine (SVM) as a classifier. The task of preprocessing allows us to equalize feature vectors from different characters. This algorithm is implemented in two steps. In the first step, input character is classified into one of eighteen ...

متن کامل

Handwritten Character Recognition using Modified Gradient Descent Technique of Neural Networks and Representation of Conjugate Descent for Training Patterns

The purpose of this study is to analyze the performance of Back propagation algorithm with changing training patterns and the second momentum term in feed forward neural networks. This analysis is conducted on 250 different words of three small letters from the English alphabet. These words are presented to two vertical segmentation programs which are designed in MATLAB and based on portions (1...

متن کامل

Neural Network Based Recognition System Integrating Feature Extraction and Classification for English Handwritten

Handwriting recognition has been one of the active and challenging research areas in the field of image processing and pattern recognition. It has numerous applications that includes, reading aid for blind, bank cheques and conversion of any hand written document into structural text form. Neural Network (NN) with its inherent learning ability offers promising solutions for handwritten characte...

متن کامل

پویانمایی شخصیت کارتونی با انتقال حرکت مفصلی و مبتنی بر اسکلت موجودات دیگر

Abstract: Nowadays, the animators give life to the fancy characters by making natural movements to organs of cartoon characters. To achieve this goal, movements of living individuals can be applied into cartoon characters. In this paper, a skeletal correspondence finding based method is proposed to transfer movement of a 2D character into a new character, where these two shapes have the same st...

متن کامل

یک روش دو مرحلهای برای بازشناسی کلمات دستنوشته فارسی به کمک بلوکبندی تطبیقی گرادیان تصویر

This paper presented a two step method for offline handwritten Farsi word recognition. In first step, in order to improve the recognition accuracy and speed, an algorithm proposed for initial eliminating lexicon entries unlikely to match the input image. For lexicon reduction, the words of lexicon are clustered using ISOCLUS and Hierarchal clustering algorithm. Clustering is based on the featur...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • Forensic science international

دوره 150 1  شماره 

صفحات  -

تاریخ انتشار 2005