Articles written in Sadhana

    • A Comparative analysis for identification and classification of text segmentation challenges in Takri Script


      More Details Abstract Fulltext PDF

      Takri is an Indian regional class of scripts, used in hilly areas of north-west India which include Jammu and Kashmir (J & K), Himachal Pradesh (H.P.), Punjab and Uttarakhand. This script has immense variations; almost 13 identified in the whole region of North-west India. It has been observed that no work for text identification and recognition of Takri script has been done so far. Therefore, our work focuses on identifying and classifying the various challenges in the script based on comparative analysis of existing text segmentation approaches, as correct segmentation of text leads to more accurate machine recognition. As there were no metal fonts available for the script, it is required to collect the machine-printed form of data for solving the text identification problem in Takri script. The paper surveys for different text segmentation approaches andbased on the structural properties of the script, shows an implementation of these on Takri data in three steps-Gurmukhi segmentation technique, Connected Component segmentation approach, and Gurmukhi touching characters segmentation approach. Results are analyzed for Segmentation Accuracy and Challenges are identified along with their statistical analysis. Further, the challenges identified as half- forms, numerous types of touching characters, overlapping bounding boxes, are classified. The effectiveness of these challenges was evaluated using Naı¨ve-Bayesian machine learning algorithm. The results showed 80% accuracy in text identification and classification of Takri script.

    • Handwritten Indic scripts recognition using neuro-evolutionary adaptive PSO based convolutional neural networks


      More Details Abstract Fulltext PDF

      Although offline handwritten Indic script recognition has been explored for decades, it is still a challenging task to recognize handwritten characters and digits accurately because of complex structure and similar shaped characters in Indic scripts. Like other computer vision problems, handwritten Indic scriptsrecognition has achieved impressive state-of-the-art results using deep learning-based techniques. However, designing a successful handcrafted Deep Neural Network (DNN) right from scratch requires a lot of problem domain knowledge and involves a significant amount of trial and error. This approach intuitively appears to consume substantial time and computational resources. To solve this problem, we simplified the search process by using a meta-heuristics evolutionary technique to automatically evolve the optimal Convolutional NeuralNetwork (CNN) architecture. More specifically, this work proposes a novel framework based on improved and fast converging Adaptive Particle Swarm Optimization (APSO) to design CNN architecture without manual intervention. The computational experiments are subsequently carried out on eight handwritten isolated characters and digits datasets belonging to three popular Indic scripts, namely Bangla, Devanagari, and Dogri. The experimental results clearly show that the proposed APSO-CNN technique yields better performance than the state-of-the-art methods for all the datasets.

  • Sadhana | News

    • Editorial Note on Continuous Article Publication

      Posted on July 25, 2019

      Click here for Editorial Note on CAP Mode

© 2022-2023 Indian Academy of Sciences, Bengaluru.