Handwriting-based gender and handedness classification using convolutional neural networks

Rahmanian, Mina; Shayegan, Mohammad Amin

doi:10.1007/s11042-020-10170-7

Cited by 26 publications

(9 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of the two CNN architectures concerning accuracy is 80.05% for GoogleNet, 83.32% for ResNet. Rahmanian and Shayegan [25] showed gender and handedness classification by using advanced CNNs: DenseNet201, InceptionV3, and Xception. Two databases, IAM (English texts) and KHATT (Arabic texts), have been employed in this study.…”

Section: Related Workmentioning

confidence: 99%

Hybrid Features for Gender Classification System based on Pre-segmented Handwritten Gurumukhi Characters Using Machine Learning Algorithms

SINGLA

Maini

Kumar

2023

Preprint

View full text Add to dashboard Cite

Identification of handwriting has been an evolving task for mitigating specific issues in the fields of machine learning and pattern recognition. In the fields of artificial intelligence and machine learning, a gender classification method based on one or more features has emerged as a promising idea for addressing issues such as criminal, forensic, and suspected examinations. Predicting an individual's age, gender, and handedness based on their handwriting is one of the more challenging offline handwriting applications. The authors have presented a novel approach to classifying gender as male or female based on pre-segmented Gurumukhi (Punjabi) characters using feature extraction methods and classification algorithms such as K-NN, random forest, SVM, and MLPs in this proposed work. On a dataset of about 72,000 Gurumukhi characters, we extracted diagonal, transition, zoning, and peak extent based features (which consists of 280 writers with 150 males and 130 females). Our results show that by using a hybridization of multiple feature extraction techniques, the random forest classifier achieves higher accuracy than other classifiers.

show abstract

Section: Related Workmentioning

confidence: 99%

Hybrid Features for Gender Classification System based on Pre-segmented Handwritten Gurumukhi Characters Using Machine Learning Algorithms

SINGLA

Maini

Kumar

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In the last few years, quite several research works have been reported in the area of handwriting recognition systems based on different approaches and techniques which have been tailored toward specific areas of applications. For instance, authors in [9,10] suggested a technique for handwriting-based age, gender, and nationality categorization. For classification, these authors employed kernel discriminant analysis with spectral regression and a random forest classifier.…”

Section: Literature Reviewmentioning

confidence: 99%

“…(8) Where, is the force acting on an agent from an agent at dimension and iteration? The CGSA algorithm incorporates the stochastic characteristics by assuming that the total forces acting on an agent I in a dimension d are a randomly weighted sum of the components of the force generated by other agents as given in equation ( 9) (9) The total force acting on the agent was calculated using equation ( 10); (10) Where is a random number in the interval [0,1]…”

Section: Step (Iii): Gravitational Constantmentioning

confidence: 99%

An Offline Handwriting Age Range Prediction System Using an Optimized Deep Learning Technique

Omolara¹,

Oyedepo²,

Wasiat³

et al. 2023

IJETAE

View full text Add to dashboard Cite

One of the distinguishing features of an individual is handwriting and it has been established that everyone has unique handwriting differing from one another. This unique feature evolves with time and is influenced by a variety of factors such as gender, physical and mental health, and age among others. Also, the recent development in using individual peculiar features for forensic investigations in banks and other allied institutions either for signature verification or identification spelled the need to develop a smart system that can predict the age range with offline handwriting recognition. It is on this background that this research employed an optimized deep learning technique comprising of Gravitational Search Algorithm and Convolutional Neural Network (CNN-GSA) for offline handwriting age range prediction. A local database was populated with samples of the signature captured with a digital camera (5 megapixels), the CNN was employed for feature extraction, GSA was utilized to select optimal CNN parameters used for classification while the combined CNNGSA was utilized for an offline handwritten-based age prediction system. The performance evaluation of the approach proposed was done using sensitivity, specificity, precision, false positive rate, recognition accuracy, and processing time for all the variants, while the superiority of the system developed was ascertained by comparing it with the original CNN.

show abstract

“…Compared with InceptionV2, V3 uses n*1 and 1*n convolution cascades to replace the n*n convolution, effectively reducing the number of parameters. Since the introduction of InceptionV3, a large number of researchers have applied this network framework in various fields to help solve problems (Dif et al, 2021 ; Mahmood and Mahmood, 2021 ; Rahmanian and Shayegan, 2021 ; Tembhurne et al, 2021 ). In agriculture, Zaki et al ( 2021 ) used this algorithm to detect onion disease (purple spots).…”

Section: Disease Detection Algorithm For Retinal Oct Based On An Fnmentioning

confidence: 99%

FN-OCT: Disease Detection Algorithm for Retinal Optical Coherence Tomography Based on a Fusion Network

Huang

Feng

et al. 2022

Front. Neuroinform.

View full text Add to dashboard Cite

Optical coherence tomography (OCT) is a new type of tomography that has experienced rapid development and potential in recent years. It is playing an increasingly important role in retinopathy diagnoses. At present, due to the uneven distributions of medical resources in various regions, the uneven proficiency levels of doctors in grassroots and remote areas, and the development needs of rare disease diagnosis and precision medicine, artificial intelligence technology based on deep learning can provide fast, accurate, and effective solutions for the recognition and diagnosis of retinal OCT images. To prevent vision damage and blindness caused by the delayed discovery of retinopathy, a fusion network (FN)-based retinal OCT classification algorithm (FN-OCT) is proposed in this paper to improve upon the adaptability and accuracy of traditional classification algorithms. The InceptionV3, Inception-ResNet, and Xception deep learning algorithms are used as base classifiers, a convolutional block attention mechanism (CBAM) is added after each base classifier, and three different fusion strategies are used to merge the prediction results of the base classifiers to output the final prediction results (choroidal neovascularization (CNV), diabetic macular oedema (DME), drusen, normal). The results show that in a classification problem involving the UCSD common retinal OCT dataset (108,312 OCT images from 4,686 patients), compared with that of the InceptionV3 network model, the prediction accuracy of FN-OCT is improved by 5.3% (accuracy = 98.7%, area under the curve (AUC) = 99.1%). The predictive accuracy and AUC achieved on an external dataset for the classification of retinal OCT diseases are 92 and 94.5%, respectively, and gradient-weighted class activation mapping (Grad-CAM) is used as a visualization tool to verify the effectiveness of the proposed FNs. This finding indicates that the developed fusion algorithm can significantly improve the performance of classifiers while providing a powerful tool and theoretical support for assisting with the diagnosis of retinal OCT.

show abstract

Handwriting-based gender and handedness classification using convolutional neural networks

Cited by 26 publications

References 41 publications

Hybrid Features for Gender Classification System based on Pre-segmented Handwritten Gurumukhi Characters Using Machine Learning Algorithms

Hybrid Features for Gender Classification System based on Pre-segmented Handwritten Gurumukhi Characters Using Machine Learning Algorithms

An Offline Handwriting Age Range Prediction System Using an Optimized Deep Learning Technique

FN-OCT: Disease Detection Algorithm for Retinal Optical Coherence Tomography Based on a Fusion Network

Contact Info

Product

Resources

About