Filters








821 Hits in 6.1 sec

The Study of Handwriting Recognition Algorithms Based on Neural Networks

Barak Finkelstein, Athabasca University , Canada, Kaplan Kuncan, Athabasca University , Canada
2021 International Journal of Hybrid Information Technology  
First, using the modified CNN model and the Gabor filter that introduces curvature systems, extract the CNN and Gabor characteristics of the character image; Second, the characteristics of its progress  ...  of classification.  ...  At present, the classification algorithms used in handwritten number recognition are rough: proximity algorithm, SVM algorithm, BP neural network method, and so on.  ... 
doi:10.21742/ijhit.2021.14.1.05 fatcat:cdsakc65bngsxazidbbwkjqyai

A Contrast Measure based Approach to Binaries Handwritten Documents through MRF

Bharti Bansinge, R.K. Pateriya
2015 International Journal of Computer Applications  
This framework suggest to use Markov random function to evaluate contrast of pixel and try to overcome the problem of appearance of a single document that can vary greatly depending on factors such as  ...  In this paper a framework for digitations of historical physical document has been proposed.  ...  In this simulation the handwritten data set of DIBCO13-handwritten has been used. This data set also provides the images which should be a final result.  ... 
doi:10.5120/ijca2015905752 fatcat:lx5ewbk5trdplh3xlocwonhnjq

Scene Text Recognition using Artificial Neural Network: A Survey

Sunil Kumar, Krishan Kumar, Rahul Kumar
2016 International Journal of Computer Applications  
This review gives a detail survey of use of artificial neural network in scene text recognition.  ...  There are many reasons including various sources of variability, hypothesis and absence of hard-and-fast rules that define the appearance of a visual character.  ...  In classifying handwritten characters, the stages prior to the classification phase play a role as major as the classification itself.  ... 
doi:10.5120/ijca2016908804 fatcat:5ij5hkcw7ze53e4rvsl4dsrm6y

Optical Character Recognition [chapter]

2016 Practical Laboratory Automation  
The systems are characterized by reading only an extremely limited set of printed characters, usually numerals and a few special symbols.  ...  When hand-printed characters were considered, the character set was constrained to numerals and a few letters and symbols.  ... 
doi:10.1002/9783527801954.app2 fatcat:i7yhlctvwnh23fvgfyqubxsvhm

optical character recognition [chapter]

Martin H. Weik
2000 Computer Science and Communications Dictionary  
The systems are characterized by reading only an extremely limited set of printed characters, usually numerals and a few special symbols.  ...  When hand-printed characters were considered, the character set was constrained to numerals and a few letters and symbols.  ... 
doi:10.1007/1-4020-0613-6_12944 fatcat:6gd2qmtoxbdvjebz3mc6yeizia

Optical character recognition

1986 Computer Communications  
The systems are characterized by reading only an extremely limited set of printed characters, usually numerals and a few special symbols.  ...  When hand-printed characters were considered, the character set was constrained to numerals and a few letters and symbols.  ... 
doi:10.1016/0140-3664(86)90284-7 fatcat:gcuc2u2idrfzbbgbylafwv6rmm

Invariant behavioural based discrimination for individual representation

Wong Yee Leng, Siti Mariyam Shamsuddin, Nor Azman Hashim
2021 International Journal of Power Electronics and Drive Systems (IJPEDS)  
In this study, a novel approach of presenting cursive features of authors is presented.  ...  Recently, its main idea is in forensic investigation and biometric analysis as such the handwriting style can be used as individual behavioural adaptation for authenticating an author.  ...  The results of the experiments for data set using six discretization and four classification methods are summarized and reported into a single Table 5 .  ... 
doi:10.11591/ijece.v11i1.pp736-744 fatcat:byx5urr3gjfm7fsqne3yc5l5nu

Reading Systems: An Introduction to Digital Document Processing [chapter]

Lambert Schomaker
2007 Advances in Pattern Recognition  
As an introduction to the area of digital document processing we first take a few steps back and take a look at the purpose of digital document processing.  ...  Subsequently a detailed comparison between the human and the artificial reading system is made. Finally, the chapter provides an overview on the book as a whole.  ...  Using a data set of realistic samples from a bank, the study describes processing steps, feature choice and classification technology. The goal is to use discrete-HMM models for sub-words.  ... 
doi:10.1007/978-1-84628-726-8_1 fatcat:o5m3enb2ezapnkpuxktssjokqq

A TaLISMAN: Automatic Text and LIne Segmentation of historical MANuscripts [article]

Ruggero Pintus, Ying Yang, Enrico Gobbetti, Holly Rushmeier
2014 Eurographics Workshop on Graphics and Cultural Heritage  
In this paper, we present a completely automatic algorithm to perform a robust text segmentation of old handwritten manuscripts on a per-book basis, and we show how to exploit this outcome to find two  ...  Historical and artistic handwritten books are valuable cultural heritage (CH) items, as they provide information about tangible and intangible cultural aspects from the past.  ...  We use this rough classification to automatically train a Support Vector Machine (SVM) with Radial Basis Function (RBF), and we then re-launch a prediction step to all original SIFTs to obtain a fine text  ... 
doi:10.2312/gch.20141302 fatcat:bzzmqmaafncp7nw4phy3nipbby

Towards Semi-supervised Transcription of Handwritten Historical Weather Reports

Jan Richarz, Szil´rd Vajda, Gernot A. Fink
2012 2012 10th IAPR International Workshop on Document Analysis Systems  
The detected table serves as query for retrieving and fitting a structural template, which is then used to extract handwritten text fields.  ...  The effectiveness of the proposed approach is demonstrated experimentally on a set of historical weather reports.  ...  For multi-class classification with the RVM, a 1-vs-1 majority voting setup was used. The concensus sample set and labels obtained by unanimity voting were used for training.  ... 
doi:10.1109/das.2012.91 dblp:conf/das/RicharzVF12 fatcat:xfd6kbjabfgvlczwb6w7xfhg4q

A hierarchically combined classifier for license plate recognition

Lihong Zheng, Xiangjian He, Qiang Wu, Wenjing Jia, Bijan Samali, Marimuthu Palaniswami
2008 2008 8th IEEE International Conference on Computer and Information Technology  
Then the SVM method is used for character classification in individual groups. Both start from a collection of samples of characters from license plates.  ...  After a training process using some known samples in advance, the inductive learning rules are extracted for rough classification and the parameters used for SVM-based classification are obtained.  ...  Using these particular range blocks we can divide characters into different groups in first stage. Through training process, rule set is generated from the samples in the training set.  ... 
doi:10.1109/cit.2008.4594704 dblp:conf/IEEEcit/ZhengHWJSP08 fatcat:load5oqcpjbfncwq6sagzjysve

ATHENA

Ruggero Pintus, Ying Yang, Holly Rushmeier
2015 ACM Journal on Computing and Cultural Heritage  
Our experimental results demonstrate that these two new methods are efficient and reliable, even when applied to very noisy and damaged old handwritten manuscripts.  ...  Our proposed methods have been evaluated on a huge heterogeneous corpus of illuminated medieval manuscripts of different writing styles and with various problematic attributes, such as holes, spots, ink  ...  The authors would also like to thank Chang Liu for her assistance in preparing the groundtruth data used in this paper.  ... 
doi:10.1145/2659020 fatcat:v5gduzuc3fer5pvumatgd55nxe

English Feature Recognition Based on GA-BP Neural Network Algorithm and Data Mining

Dan Wu, Yuanjun Shen, Syed Hassan Ahmed
2021 Computational Intelligence and Neuroscience  
After training, the recognition of handwritten letters can be realized.  ...  In the life around us, there is information in English all the time.  ...  In terms of quantization of English character images, only standard characters are assumed to be recognized, without considering the situation of handwritten characters.  ... 
doi:10.1155/2021/1890120 pmid:34504519 pmcid:PMC8423560 fatcat:2bj6bl3oejd2rm4w6ydut25eqi

Efficient and accurate document image classification algorithms for low-end copy pipelines

Wen-Hsiung Huang, Yung-Yao Chen, Pei-Yu Lin, Che-Hao Hsu, Kai-Lung Hua
2016 EURASIP Journal on Image and Video Processing  
To classify the scanned image without expensive hardware and reduce the running time, in this article, we designed an efficient automatic method for classifying a document image using a probabilistic decision  ...  In addition, we incorporate a new classification module to help avoid moiré patterns by identifying periodic halftone noise.  ...  The article [11] using multiple instance learning (MIL) to reduce the training instances for handwritten and printed documents classifications.  ... 
doi:10.1186/s13640-016-0135-4 fatcat:u7zlcznqvjdt3d2pnkydri376m

A system for licence plate recognition using a hierarchically combined classifier

Lihong Zheng, Xiangjian He, Qiang Wu, Bijan Samali
2011 International Journal of Intelligent Systems Technologies and Applications  
Then, the SVM approach is used for character classification in individual groups.  ...  After the training process, the inductive learning rules are extracted for rough classification and the parameters used for SVM-based classification are obtained.  ...  The overall classification accuracy cannot be guaranteed. The hierarchical model is a mixture of the previous two types. Different classifiers are used for the same set of samples.  ... 
doi:10.1504/ijista.2011.039019 fatcat:zurb5erdfbhkfluw6gnzbzzoyu
« Previous Showing results 1 — 15 out of 821 results