In EDS ansehen

Enhancing Security: Devanagari Handwritten CAPTCHA Generation using Digital Handwritten Devanagari Character Dataset.

Gespeichert in:
Bibliographische Detailangaben
Titel: Enhancing Security: Devanagari Handwritten CAPTCHA Generation using Digital Handwritten Devanagari Character Dataset.
Autoren: Pate, Sanjay E., Ramteke, Rakesh J.
Quelle: Grenze International Journal of Engineering & Technology (GIJET); Jan2025, Vol. 11 Issue Part1, p645-653, 9p
Schlagwörter: SPECKLE interference, LINGUISTIC context, TURING test, LINGUISTIC landscapes, GRAYSCALE model
Abstract: CAPTCHA, Automated Public Turing Tests, serves as a critical mechanism for human and machine identification online. However, the prevalence of primarily English textbased CAPTCHA poses a significant barrier for individuals in rural India. To address this challenge, we introduce a new Devanagari script text-based CAPTCHA designed to increase accessibility for users in diverse linguistic contexts. Our approach involves the creation of a Devanagari handwritten dataset, consisting of 44,000 images featuring 34 alphabets and 10 numerals. Each grayscale character has a resolution of 65 by 65 pixels. The dataset is publicly available on IEEE and Mendeley data ports. The algorithm for Devanagari Handwritten CAPTCHA generation is implemented on Python's Anaconda Jupiter platform, adhering to CAPTCHA standard guidelines. This includes image resizing, enhancement, wrapping, dilation, and the introduction of background noise such as arcs, lines, dots, and clutter with Gaussian, Salt and Pepper, Poisson, and Speckle noise to bolster resistance against image-breaking techniques. Each CAPTCHA image is standardized at 250 X 90 pixels, resulting in the generation of nine distinct CAPTCHA types, with 10,000 images of each type, contributing to a dataset of 90,000 images. This dataset, now available on Mendeley Data, serves as a valuable resource for researchers to test and enhance CAPTCHA recognition systems in a diverse linguistic landscape. [ABSTRACT FROM AUTHOR]
Copyright of Grenze International Journal of Engineering & Technology (GIJET) is the property of GRENZE Scientific Society and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Datenbank: Complementary Index
Beschreibung
Abstract:CAPTCHA, Automated Public Turing Tests, serves as a critical mechanism for human and machine identification online. However, the prevalence of primarily English textbased CAPTCHA poses a significant barrier for individuals in rural India. To address this challenge, we introduce a new Devanagari script text-based CAPTCHA designed to increase accessibility for users in diverse linguistic contexts. Our approach involves the creation of a Devanagari handwritten dataset, consisting of 44,000 images featuring 34 alphabets and 10 numerals. Each grayscale character has a resolution of 65 by 65 pixels. The dataset is publicly available on IEEE and Mendeley data ports. The algorithm for Devanagari Handwritten CAPTCHA generation is implemented on Python's Anaconda Jupiter platform, adhering to CAPTCHA standard guidelines. This includes image resizing, enhancement, wrapping, dilation, and the introduction of background noise such as arcs, lines, dots, and clutter with Gaussian, Salt and Pepper, Poisson, and Speckle noise to bolster resistance against image-breaking techniques. Each CAPTCHA image is standardized at 250 X 90 pixels, resulting in the generation of nine distinct CAPTCHA types, with 10,000 images of each type, contributing to a dataset of 90,000 images. This dataset, now available on Mendeley Data, serves as a valuable resource for researchers to test and enhance CAPTCHA recognition systems in a diverse linguistic landscape. [ABSTRACT FROM AUTHOR]
ISSN:23955287