Handwriting Detection using Neural Network

Please use this identifier to cite or link to this item: http://ir.juit.ac.in:8080/jspui/jspui/handle/123456789/6970

Full metadata record

DC Field	Value	Language
dc.contributor.author	Nijhawan, Manik	-
dc.contributor.author	Singal, Paras	-
dc.contributor.author	Jindal, Himanshu [Guided by]	-
dc.date.accessioned	2022-09-29T05:09:30Z	-
dc.date.available	2022-09-29T05:09:30Z	-
dc.date.issued	2019	-
dc.identifier.uri	http://ir.juit.ac.in:8080/jspui/jspui/handle/123456789/6970	-
dc.description.abstract	This undertaking report compares three models for handwriting detection using MNIST and EMNIST dataset. The result is a system which can recognize any handwritten number or alphabet. The 3 models which we compared are artificial neural network, random forest and XGBoost. We additionally experimented with different hyperparameters to maximize test accuracy and reduce overfitting as much as we could. MNIST and EMNIST are most common dataset available on the internet for handwriting detection. MNIST dataset contains 60000 training images and 10000 test images. EMNIST dataset contains 124800 training images and 20800 test images.	en_US
dc.language.iso	en	en_US
dc.publisher	Jaypee University of Information Technology, Solan, H.P.	en_US
dc.subject	MNIST dataset	en_US
dc.subject	Image of handwriting	en_US
dc.subject	Neural network	en_US
dc.title	Handwriting Detection using Neural Network	en_US
dc.type	Project Report	en_US
Appears in Collections:	B.Tech. Project Reports

Files in This Item:

File	Description	Size	Format
Handwriting Detection using Neural Network.pdf		1.95 MB	Adobe PDF	View/Open