An Enhanced Approach Towards Object Detection Using Deep Learning Techniques
S.Priyadarsini
, G. vijipriya , Dr. E.S.Shamila , Ms.A.Praveena , Ms.A.Rathika
Key words: Deep learning, Image processing, ORC, HOG, LBP.
Text recognition in images and videos have advanced as an active research area over last few years. Text detection from the scene image is a process by which text regions are segmented from non-textual ones and they are organized in accordance with their correct direction of reading. Different text patterns and variant background interferences are the challenges that affect the consistency of text character extraction. Digitization of text documents is frequently united with the progress of optical character recognition (OCR). OCR tool gives good outcomes obtained to read the text from an image. The objective study of this paper is to propose a text recognition model that is designed using rich supervision to accelerate training and achieve state-of-the-art performance on several benchmark datasets. A deep neural network based system is used to read scene text and show that scene text reading can be effectively applied for the purpose of retrieving objects. In this paper, we examine a modest but powerful approach to make robust use of HOG and LBP features for text recognition. Histograms of Oriented Gradients (HOGs) and Local Binary Patterns (LBPs) have proven to be an effective descriptor for object recognition in general and text recognition in specific. Experimental results over the ICDAR 2013 and SVT 2010 dataset demonstrate the efficiency of the proposed approach.
"An Enhanced Approach Towards Object Detection Using Deep Learning Techniques", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.3, Issue 11, page no.442 - 445, November-2018, Available :https://ijsdr.org/papers/IJSDR1811079.pdf
Volume 3
Issue 11,
November-2018
Pages : 442 - 445
Paper Reg. ID: IJSDR_180854
Published Paper Id: IJSDR1811079
Downloads: 000347186
Research Area: Engineering
Country: Tirupur, Tamil Nadu, India
ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJSDR(IJ Publication) Janvi Wave
