Yeliyur Hanumanthaiah, Sharath Kumar
Unknown Affiliation

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

Novel hybrid generative adversarial network for synthesizing image from sketch Murthy, Pavithra Narasimha; Yeliyur Hanumanthaiah, Sharath Kumar
International Journal of Electrical and Computer Engineering (IJECE) Vol 13, No 6: December 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v13i6.pp6293-6301

Abstract

In the area of sketch-based image retrieval process, there is a potential difference between retrieving the match images from defined dataset and constructing the synthesized image. The former process is quite easier while the latter process requires more faster, accurate, and intellectual decision making by the processor. After reviewing open-end research problems from existing approaches, the proposed scheme introduces a computational framework of hybrid generative adversarial network (GAN) as a solution to address the identified research problem. The model takes the input of query image which is processed by generator module running 3 different deep learning modes of ResNet, MobileNet, and U-Net. The discriminator module processes the input of real images as well as output from generator. With a novel interactive communication between generator and discriminator, the proposed model offers optimal retrieval performance along with an inclusion of optimizer. The study outcome shows significant performance improvement.
CRNN model for text detection and classification from natural scenes Prakash, Puneeth; Yeliyur Hanumanthaiah, Sharath Kumar; Bannur Mayigowda, Somashekhar
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 1: March 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i1.pp839-849

Abstract

In the emerging field of computer vision, text recognition in natural settings remains a significant challenge due to variables like font, text size, and background complexity. This study introduces a method focusing on the automatic detection and classification of cursive text in multiple languages: English, Hindi, Tamil, and Kannada using a deep convolutional recurrent neural network (CRNN). The architecture combines convolutional neural networks (CNN) and long short-term memory (LSTM) networks for effective spatial and temporal learning. We employed pre-trained CNN models like VGG-16 and ResNet-18 for feature extraction and evaluated their performance. The method outperformed existing techniques, achieving an accuracy of 95.0%, 96.3%, and 96.2% on ICDAR 2015, ICDAR 2017, and a custom dataset (PDT2023), respectively. The findings not only push the boundaries of text detection technology but also offer promising prospects for practical applications.
A comparative analysis of optical character recognition models for extracting and classifying texts in natural scenes Prakash, Puneeth; Yeliyur Hanumanthaiah, Sharath Kumar
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 2: April 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i2.pp1290-1301

Abstract

This research introduces prior-guided dynamic tunable network (PDTNet), an efficient model designed to improve the detection and recognition of text in complex environments. PDTNet’s architecture combines advanced preprocessing techniques and deep learning methods to enhance accuracy and reliability. The study comprehensively evaluates various optical character recognition (OCR) models, demonstrating PDTNet’s superior performance in terms of adaptability, accuracy, and reliability across different environmental conditions. The results emphasize the need for a context-aware approach in selecting OCR models for specific applications. This research advocates for the development of hybrid OCR systems that leverages multiple models, aiming to arrive at a higher accuracy and adaptability in practical applications. With a precision of 85%, the proposed model showed an improved performance of 1.7% over existing state of the arts model. These findings contribute valuable insights into addressing the technical challenges of text extraction and optimizing OCR model selection for real-world scenarios.