Automatic Text Extraction System for Complex Images
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2016, Vol 18, Issue 3
Abstract
Abstract : The Intelligent text extraction system automatically identifies and extracts the text present in different types of images. The growth of digital world Detection and Extraction of text regions in an image are well known problems in the area of image processing. The growth of digital world and the usage of multimedia generated a new era with a classic problem of pattern recognition. Thus Automatic text extraction from images and videos serves an important role in indexing and efficient retrieval of multimedia. The existing techniquessuch as region based, texture based techniques for the text extraction are not able to compact with all the applications of text extraction. The proposed Intelligent Text Extraction system automatically identifies and extracts the text present in different types of images. The system consists of different stages which include the localization, segmentation, extraction and recognition of text from the images. In the proposed system we use the discrete wavelet transform for the localization of text. The morphological operations are used whichenhances the identification of correct text portions. The text part is segmented and is recognized using an efficient system. The advantage of the system is that the extracted text is shown in the .txt file. The proposed system also allows the modification of the recognized text from the image. This method shows better efficiency, precision and recall compared to the existing techniques. This shows the possibility of using this technique in more new and advanced applications.
Authors and Affiliations
R. Janani , T. Sheela
Keywords
Related Articles
- EP ID EP90666
- DOI -
- Views 144
- Downloads 0
Research on Industrial Robot Teaching Pendant based on Android and its Realization
Abstract: As the current industrial robots teaching systems have some disadvantages including high maintenance cost, poor portability and operational complexity, an industrial robot teaching system based on Android platf...
Feature Selection And Vectorization In Legal Case DocumentsUsing Chi-Square Statistical Analysis And Naïve BayesApproaches
Abstract : Most machine learning techniques employed in the area of text classification require the features ofthe documents to be effectively selected owing to the large chunk of data encountered in the classifica...
Unsupervised Clustering Classify theCancer Data withtheHelp of FCM Algorithm
There is structure in nature; also it is believed that there is an underlying structure in most of phenomena, to be understood. in image recognition ,mole biology applications such as protein folding and 3D &nbs...
A Parallel Hybrid Technique for Multi-Noise Removal from Grayscale Medical Images
Abstract: Medical imaging is the technique used to create images of the human body or parts of it for clinical purposes. Medical images always have large sizes and they are commonly corrupted by single or multiple noise...
Paralyzing Bioinformatics Applications Using Conducive Hadoop Cluster
Bioinformatics may be defined as the application of computer science to molecular biology in the form of statistics and analytics. The bioinformatics applications deal with bulk amount of data. Researchers are no...