Handwriting-Based Gender Classification Using End-to-End Deep Neural Networks

  title={Handwriting-Based Gender Classification Using End-to-End Deep Neural Networks},
  author={Evyatar Illouz and Eli David and Nathan S. Netanyahu},
Handwriting-based gender classification is a well-researched problem that has been approached mainly by traditional machine learning techniques. In this paper, we propose a novel deep learning-based approach for this task. Specifically, we present a convolutional neural network (CNN), which performs automatic feature extraction from a given handwritten image, followed by classification of the writer's gender. Also, we introduce a new dataset of labeled handwritten samples, in Hebrew and English… Expand
State-of-the-art Approaches for Handwriting-based Recognition on Gender and Handedness Using Deep Learning
Handwriting-based demographic identification, such as gender or handedness classification, has many applications in forensic biometrics and archaeology. Most of the existing methods heavily rely onExpand
Forensic Analysis of Bangla Handwritten Letters
This research used a Bangla handwriting dataset to identify the age, gender, and location (district) of the writer using deep learning algorithms, and is the first to address these three features from Bangle handwriting. Expand


Gender and Handedness Prediction from Offline Handwriting Using Convolutional Neural Networks
This work describes an experimental study on the suitability of deep neural networks to three automatic demographic problems: gender, handedness, and combined gender-and-handedness classifications, respectively, carried out on two public handwriting databases. Expand
Local descriptors to improve off-line handwriting-based gender prediction
The use of local descriptors are proposed in order to improve the gender classification based on offline handwritten text by employing Histogram of Oriented Gradients, Local Binary Patterns as well as grid features, which are successful in various pattern recognition applications. Expand
Gender Classification from Offline Handwriting Images Using Textural Features
The textural measurements are exploited as the discriminating attribute between male and female writings and the proposed technique evaluated on a subset of the QUWI database realized promising results under different experimental settings. Expand
Automatic analysis of handwriting for gender classification
A study to predict gender of individuals from scanned images of their handwritings based on extracting a set of features from writing samples of male and female writers and training classifiers to learn to discriminate between the two. Expand
Gender classification from offline multi-script handwriting images using oriented Basic Image Features (oBIFs)
The present study demonstrates the effectiveness of relatively less investigated oBIFs as a robust textual descriptor in gender classification competitions reporting classification rates of 71%, 76% and 68% respectively; outperforming the participating systems of these competitions. Expand
Improving handwriting based gender classification using ensemble classifiers
A system to predict gender from images of handwriting using textural descriptors that is significantly better than those of the state-of-the-art systems on this problem validating the ideas put forward in this study. Expand
Automatic prediction of age, gender, and nationality in offline handwriting
This study proposes several geometric features to characterize handwritings and uses these features to perform the classification of hand Writings with regards to age, gender, and nationality and combines these features using random forests and kernel discriminant analysis. Expand
Automatic detection of gender and handedness from on-line handwriting
This paper applies state-of-the-art classification methods to distinguish between male and female handwriting, and left and righthandedness to classify handwritten data with respect to gender and handedness. Expand
Wavelet-based gender detection on off-line handwritten documents using probabilistic finite state automata
The experimental results show the superiority of the proposed technique over existing techniques in terms of classification rates, and a script-independent approach applied to English, French & Arabic handwritings. Expand
Age, gender and handedness prediction from handwriting using gradient features
Two gradient features for writer's gender, handedness, and age range prediction are introduced, including the Histogram of Oriented Gradients and the so-called gradient local binary patterns, which is an improved gradient feature that incorporates the local binary pattern neighborhood in the gradient calculation. Expand