A
Ayatullah Faruk Mollah
Researcher at Aliah University
Publications - 56
Citations - 443
Ayatullah Faruk Mollah is an academic researcher from Aliah University. The author has contributed to research in topics: Computer science & Pattern recognition (psychology). The author has an hindex of 10, co-authored 44 publications receiving 295 citations. Previous affiliations of Ayatullah Faruk Mollah include Jadavpur University.
Papers
More filters
Posted Content
Design of an Optical Character Recognition System for Camera- based Handheld Devices
TL;DR: A complete Optical Character Recognition system for camera captured image/graphics embedded textual documents for handheld devices that is computationally efficient and consumes low memory so as to be applicable on handheld devices.
Posted Content
Handwritten Arabic Numeral Recognition using a Multi Layer Perceptron
TL;DR: A feature set of 88 features is designed to represent samples of handwritten Arabic numerals designed to include 72 shadow and 16 octant features and can be extended to include OCR of handwritten characters of Arabic alphabet.
Journal ArticleDOI
Multi-lingual scene text detection and language identification
Shaswata Saha,Neelotpal Chakraborty,Soumyadeep Kundu,Sayantan Paul,Ayatullah Faruk Mollah,Subhadip Basu,Ram Sarkar +6 more
TL;DR: This work proposes an end-to-end system for scene text detection, localization and language identification to combine feature-based and deep learning-based approaches and achieves satisfactory results.
Posted Content
Text/Graphics Separation for Business Card Images for Mobile Devices
TL;DR: A novel text/graphics separation technique for business card images captured with a cell-phone camera that is computationally efficient and consumes low memory so as to be applicable on mobile devices.
Journal ArticleDOI
Handwritten Arabic numerals recognition using convolutional neural network
Pratik Ahamed,Soumyadeep Kundu,Tauseef Khan,Vikrant Bhateja,Ram Sarkar,Ayatullah Faruk Mollah +5 more
TL;DR: A modification of previously proposed CNN architecture has given an accuracy of 98.91% and the proposed architecture has produced 99.76%, which is comparable to state-of-the-art results found in the domain of handwritten Arabic numeral recognition.