In recent data, Optical character recognition (OCR) systems have laid hands in the field of most popular language recognitions. Unlike other languages, the Tamil language is more complex to recognize, and hence considerable efforts have been laid in literature. However, the models are not yet well-organized for precise recognition of Tamil characters. Thus, the current research work develops a novel Tamil Handwritten Character Recognition approach by following two major processes, viz. pre-processing and recognition. The pre-processing phase encloses RGB to grayscale conversion, binarization with thresholding, image complementation, morphological operations, and linearization. Subsequently, the pre-processed image after linearization is subjected to recognition via an optimally configured Convolutional Neural Network (CNN). More particularly, the fully connected layer and weights are fine-tuned by a new Self Adaptive Lion Algorithm (SALA) that is the conceptual improvement of the standard Lion Algorithm (LA). The performance of the proposed work is compared and proved over other state-of-the-art models with respect to certain performance measures.

No abstract

The paper describes the excellent method to get first-rate accuracy and performance in the discipline of Tamil character recognition in a handwritten mode. However, the subject is still at a nascent stage and grossly lacks adequate accuracy in the Tamil language, even though several studies have been conducted within the discipline of handwritten character recognition. This paper draws the attention to the offline handwritten recognition for the Tamil language using the Inception-v3 based transfer learning method. The proposed work is conducted on the readily available HP Tamil handwritten character offline dataset (Hewlett-Packard Lab: hpl-tamil-iso-char-offline-1.0.). It reveals that with the suitable arrangement of transfer learning approach with Inception-v3, the pre-trained model can achieve the recognition accuracy of 93.1%, overtaking the former deep learning designs. The achieved accuracy is due to the use of a pre-trained version with transfer learning that regularly hastens the method of the training process on a new task. Overall, this results in higher accuracy and a more capable version.

No abstract

No abstract