Journal ArticleDOI
Word spotting in historical documents using primitive codebook and dynamic programming
Reads0
Chats0
TLDR
This paper presents a novel approach towards word spotting using text line decomposition into character primitives and string matching, and shows that the method is robust in searching text in noisy documents.About:
This article is published in Image and Vision Computing.The article was published on 2015-12-01. It has received 17 citations till now. The article focuses on the topics: Approximate string matching & String searching algorithm.read more
Citations
More filters
Journal ArticleDOI
HMM word graph based keyword spotting in handwritten document images
TL;DR: The proposed approach achieves KWS results comparable to those obtained with the recently-introduced "BLSTM neural networks KWS" approach and clearly outperform the popular, state-of-the-art "Filler HMM" KWS method.
Journal ArticleDOI
HWNet v2: an efficient word image representation for handwritten documents
Praveen Krishnan,C. V. Jawahar +1 more
TL;DR: In this paper, the authors used a deep convolutional neural network with traditional classification loss to learn an efficient holistic representation for handwritten word images, which leads to state-of-the-art word spotting performance on standard handwritten datasets and historical manuscripts in different languages with minimal representation size.
Journal ArticleDOI
A Survey on handwritten documents word spotting
TL;DR: This paper gives an overview of published research efforts in the area of handwritten document image word spotting and on the technologies used in the field and describes a general model for document word spotting.
Posted Content
HWNet v2: An Efficient Word Image Representation for Handwritten Documents
Praveen Krishnan,C. V. Jawahar +1 more
TL;DR: The proposed framework for learning an efficient holistic representation for handwritten word images uses a deep convolutional neural network with traditional classification loss and leads to a state-of-the-art word spotting performance on standard handwritten datasets and historical manuscripts in different languages with minimal representation size.
Journal ArticleDOI
Optical character recognition on heterogeneous SoC for HD automatic number plate recognition system
Ali Farhat,Omar Hommos,Ali Al-Zawqari,Abdulhadi Al-Qahtani,Faycal Bensaali,Abbes Amira,Xiaojun Zhai +6 more
TL;DR: Four algorithms are proposed for the OCR stage of a real-time HD ANPR system based on feature extraction, zoning, combined zoning, and vector crossing techniques, and the best one has been selected for hardware implementation using a heterogeneous system on chip (SoC) platform.
References
More filters
Journal ArticleDOI
Shape matching and object recognition using shape contexts
TL;DR: This paper presents work on computing shape models that are computationally fast and invariant basic transformations like translation, scaling and rotation, and proposes shape detection using a feature called shape context, which is descriptive of the shape of the object.
Journal ArticleDOI
Invariant image recognition by Zernike moments
Alireza Khotanzad,Y.H. Hong +1 more
TL;DR: A systematic reconstruction-based method for deciding the highest-order ZERNike moments required in a classification problem is developed and the superiority of Zernike moment features over regular moments and moment invariants was experimentally verified.
Proceedings ArticleDOI
Creating efficient codebooks for visual recognition
Frédéric Jurie,Bill Triggs +1 more
TL;DR: It is shown that dense representations outperform equivalent keypoint based ones on these tasks and that SVM or mutual information based feature selection starting from a dense codebook further improves the performance.
Journal ArticleDOI
Algorithms for approximate string matching
TL;DR: An improved algorithm that works in time and in space O and algorithms that can be used in conjunction with extended edit operation sets, including, for example, transposition of adjacent characters.
Journal ArticleDOI
Approximate String Matching
TL;DR: Approximate matching of strings is reviewed with the aim of surveying techniques suitable for finding an item in a database when there may be a spelling mistake or other error in the keyword.
Related Papers (5)
Efficient segmentation-free keyword spotting in historical document collections
Using a statistical language model to improve the performance of an HMM-based cursive handwriting recognition systems
U.-V. Marti,Horst Bunke +1 more