Gender Identification on Handwriting: Correlation and Methods
Discover the correlation between the visual appearance of handwriting and the gender of the writer in forensic analysis, paleography, graphology, neurology, and demographic studies. Explore the application of various feature extraction and classification methods for gender identification based on handwriting features, such as tortuosity, direction, curvatures, chain code, edge detection, and more.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Gender Identification On Handwritings Supervised by Dr. M. Siyamalan W.R.I.N. Kalugalla 2015/CSC/023
Introduction Correlation between the visual appearance of handwriting and the gender of writer Applies in : Forensic analysis Document examining Paleography Graphology Neurology Demographic studies
Literature Review Reference Dataset Feature Extraction Method Classification Method Implementation Result used 1. Binarizing using Otsu thresholding algorithm 2. Probability Distribution Function (PDF) is extracted Features extracted : Tortuosity Direction Curvatures Chain code Edge detection K Nearest Neighborhood L1 Regularized Logistic Regression Decision Tree and Random Forest QUWI dataset (English and Arabic) kNN : 71.54%, Decision tree : 62.53%, random forest: 72.57% [1] Script dependent: 75% Script independent: 68% QUWI dataset (English and Arabic) 1. Binarizing using global thresholding 2. Extracting the oBIFs 3. Making oBIF histogram & oBIF column histogram Support Vector Machine (SVM) [2]
Reference Dataset used Feature Extraction Method Classification Method Implementation Result 1. Applying a Gabor filter bank 2. Collecting the mean and variance of each filtered image in a matrix 3. Fourier transform of the matrix is used as the feature QUWI dataset (English and Arabic) Artificial Neural Network (ANN) [3] Average rate : 68% IAM dataset (English) KHATT dataset (Arabic) Extract gradient features using Histogram of Oriented Gradients (HOG) Gradient Local Binary Patterns(GLBP) HOG : 70.71% GLBP : 70% [4] Support Vector Machine (SVM)
References 1) Xie Q., Q. Xu. Gender Prediction from Handwriting. Data Mining Course Project -at the 12th International Conference on Document Analysis and Recognition (ICDAR) 2013 2) G a t t a l, A., C. D j e d d i, I. S i d d i q i, Y. C h i b a n i. Gender Classification from Offline Multi-Script Handwriting Images Using Oriented Basic Image Features (oBIFs). Expert Systems with Applications,2018 3) M i r z a, A., M. M o e t e s u m, I. S i d d i q i, C. D j e d d i. Gender Classification from Off-line Handwriting Images Using Textural Features. - International Conference on Frontiers in Handwriting Recognition, ICFHR, 2016 4) B o u a d j e n e k, N. H. N., Y. C. Age, Gender and Handedness Prediction from Handwriting using Gradient Features. 13th International Conference on Document Analysis and Recognition (ICDAR), 2015 5) Writer Identification and Writer Retrieval using the Fisher Vector on Visual Vocabularies at the 12th International Conference on Document Analysis and Recognition (2013)
Summary Depend on the textural features of the handwritten document Bag-of-words (BoW) model is not commonly used in the feature extraction of past related works BoW model I. Feature Detection II. Feature Representation III. Codebook Generation
