Journal ArticleDOI
A Fuzzy Matching based Image Classification System for Printed and Handwritten Text Documents
Shalini Puri,Satya Prakash Singh +1 more
Reads0
Chats0
TLDR
This article proposes a system that performs better than existing systems, and shows the results of experiments on this and other proposed systems.Abstract:
Thisarticleproposesabi-leveledimageclassificationsystemtoclassifyprintedandhandwritten Englishdocumentsintomutuallyexclusivepredefinedcategories.Theproposedsystemfollowsthe stepsofpreprocessing, segmentation, featureextraction, andSVMbasedcharacterclassification atlevel1,andwordassociationandfuzzymatchingbaseddocumentclassificationatlevel2.The systemarchitectureanditsmodularstructurediscussvarioustaskstagesandtheirfunctionalities. Further,acasestudyondocumentclassificationisdiscussedtoshowtheinternalscorecomputations ofwordsandkeywordswithfuzzymatching.Theexperimentsonproposedsystemillustratethatthe systemachievespromisingresultsinthetime-efficientmannerandachievesbetteraccuracywith lesscomputation timeforprinteddocuments thanhandwrittenones.Finally, theperformanceof theproposedsystemiscomparedwiththeexistingsystemsanditisobservedthatproposedsystem performsbetterthanmanyothersystems. KeywoRDS Confidence Computation, Document Image, Fuzzy Matching, Handwritten Documents, Performance Analysis, Printed Documents, SVM, Text Image Classification, Word Associationread more
Citations
More filters
Journal ArticleDOI
Intelligent Recognition and Teaching of English Fuzzy Texts Based on Fuzzy Computing and Big Data
Ling Liu,Sang-Bing Tsai +1 more
TL;DR: In this paper, in-depth research and analysis is conducted on the intelligent recognition and teaching of English fuzzy text through parallel projection and region expansion and the substring representation in the model ensures the generation of unregistered word vectors.
Applications of Text Detection and its Challenges: A Review
M. P. Nevetha,A. Baskar +1 more
TL;DR: In this article, the authors present a survey of text detection and recognition from images to a large extent, including general documents such as newspapers, books and magazines, forms, scientific documents, maps, architectural and engineering drawings, and scene images with textual information.
Journal ArticleDOI
Advanced Applications on Bilingual Document Analysis and Processing Systems
Shalini Puri,Satya Prakash Singh +1 more
TL;DR: A journey of bilingual NLP and image-based document classification systems is discussed and an overview of their methods, feature extraction techniques, document sets, classifiers, and accuracy for English-Hindi and other language pairs is provided.
Journal ArticleDOI
Opinion Classification of Product Reviews Using Naïve Bayes, Logistic Regression and Sentiwordnet: Challenges and Survey
A Dadhich,B Thankachan +1 more
TL;DR: A detailed review and comparative analysis of various existing sentiment analysis algorithms especially for the Amazon products, which have worked upon the supervised learning techniques called Naïve Bayes, logistic regression and SentiWordNet are presented.
References
More filters
Journal ArticleDOI
Multi-oriented touching text character segmentation in graphical documents using dynamic programming
TL;DR: This paper presents a scheme towards the segmentation of English multi-oriented touching strings into individual characters and shows that the method is efficient in segmenting touching characters of arbitrary orientations and sizes.
Proceedings ArticleDOI
Automatic Discrimination between Printed and Handwritten Text in Documents
TL;DR: This paper addresses the problem of identifying each type of text in scanned documents by addressing the use of data mining techniques on the decision step and proposes a new set of features extracted of each word.
Journal ArticleDOI
Comparison Between Neural Network and Support Vector Machine in Optical Character Recognition
TL;DR: This experiment achieves the highest accuracy of 94.43% using Support Vector Machine (SVM) classifier with the feature extraction algorithms are projection profile and the combination of zoning + projection profile.
Journal ArticleDOI
Fuzzy-Zoning-Based Classification for Handwritten Characters
Giuseppe Pirlo,Donato Impedovo +1 more
TL;DR: A real-coded genetic algorithm is presented to find, in a single optimization procedure, the optimal FMF, together with the optimal zoning described by Voronoi tessellation, and the experimental results indicate that optimalFMF performs better than other membership functions based on abstract-level, ranked- level, and measurement-level weighting models, which can be found in the literature.
Journal ArticleDOI
Statistical script independent word spotting in offline handwritten documents
TL;DR: A statistical script independent line based word spotting framework for offline handwritten documents based on Hidden Markov Models and an exhaustive study of filler models and background models for better representation of background or non-keyword text.