Abstract
Identification of Tamil handwritten calligraphies at different levels such as character, word and paragraph is complicated when compared to other western language scripts. None of the existing methods provides efficient Tamil handwriting writer identification (THWI). Also offline Tamil handwritten identification at different levels still offers many motivating challenges to researchers. This paper employs a deep learning algorithm for handwriting image classification. Deep learning has its own dimensions to generate new features from a limited set of training dataset. Convolutional Neural Networks (CNNs) is one of deep, feed-forward artificial neural network is applied to THWI. The dataset collection and classification phase of CNN enables data access and automatic feature generation. Since the number of parameters is significantly reduced, training time to THWI is proportionally reduced. Understandably, the CNNs produced much higher identification rate compared with traditional ANN at different levels of handwriting.
Highlights
Writer identification can be defined to be the capability of a computer to accept and understand intelligible handwritten input received from sources like paper documents, photographs, touch-screens and other devices
Deep Neural Networks (DNN) models [10] have moved to possess multiple structures for diverse applications, inclusive of Multiple-Layer Perceptron’s (MLP), Convolutional Neural Networks (CNN), Deep Belief Networks (DBN) employed in image classification, recognition, and deep auto encoders utilized in writer classification
Identical to CNNs, Deconvolutional Neural Networks are in accordance with the concept of generation of feature hierarchies through the convolution of the input image by means of a set of filters present at every layer [24]
Summary
Writer identification can be defined to be the capability of a computer to accept and understand intelligible handwritten input received from sources like paper documents, photographs, touch-screens and other devices. Writer identification has become a huge challenge in the present day, as the character, word structure and orientation is dependent on different factors concerned with the persons who are writing it. Intelligent system that can perform the identification of Tamil writers is still an open challenge for the research personnel. Learning algorithms used for deep architectures revolve around the learning of resourceful representations of data, which better suit the task at present and are structured in a hierarchy having different levels. DNN models [10] have moved to possess multiple structures for diverse applications, inclusive of Multiple-Layer Perceptron’s (MLP), Convolutional Neural Networks (CNN), Deep Belief Networks (DBN) employed in image classification, recognition, and deep auto encoders utilized in writer classification. Deep Neural Networks (DNN) has been getting increased attention in the fields of machine learning and pattern identification. CNN is regarded to be well-prepared in overcoming the two important hurdles in THWI
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Periodicals of Engineering and Natural Sciences (PEN)
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
