UNIPEN project of on-line data exchange and recognizer benchmarks

Guyon, Isabelle; Schomaker, Lambert; Plamondon, Réjean; Liberman, Mark; Janet, Stanley

doi:10.1109/icpr.1994.576870

Cited by 290 publications

(153 citation statements)

References 6 publications

Supporting

Mentioning

149

Contrasting

Unclassified

Order By: Relevance

“…The simple nearest neighbor (NN) classifier can be applied to this problem and provide excellent recognition accuracy. For example, as we show in the experiments, a simple NN classifier using Dynamic Time Warping (DTW) [8] decreases the recognition error from 2.90% to 1.90% compared to the sophisticated CSDTW method [2] on the UNIPEN digits database [5]. As another example, a simple NN classifier using Shape Context (SC) [3] gave state-of-the-art recognition error of 0.63% on the MNIST database of handwritten digits [10].…”

Section: Introductionmentioning

confidence: 96%

“…In order to evaluate our classification method we conducted experiments with two OCR databases; the UNIPEN online handwriting database [5], and the MNIST database [10], using respectively DTW and the Hungarian method for alignment. The tradeoff between recognition speed and recognition error is used to evaluate the performance of the proposed method.…”

Section: Methodsmentioning

confidence: 99%

“…In this experiment we used the isolated digits benchmark (category 1a) of the UNIPEN Train-R01/V07 online handwriting database [5], which consists of 15, 953 digit examples. Data preprocessing and feature extraction is carried out exactly as described in [2] Section 2.…”

Section: Experiments 1: Unipen Databasementioning

confidence: 99%

See 2 more Smart Citations

Online and offline character recognition using alignment to prototypes

Alon

Athitsos

Sclaroff

2005

Eighth International Conference on Document Analysis and Recognition (ICDAR'05)

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 96%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Online and offline character recognition using alignment to prototypes

Alon

Athitsos

Sclaroff

2005

Eighth International Conference on Document Analysis and Recognition (ICDAR'05)

View full text Add to dashboard Cite

show abstract

“…The UNIPEN format is a common data format, easy to exchange (Guyon et al, 1994 (Agrawal et al, 2005). It allows the user to easily add specific information to ink files to suit the needs of the application.…”

Section: Standards For Online Data Representationmentioning

confidence: 99%

Preprocessing of online handwritten Telugu character recognition

Inuganti¹,

Ramisetty

2017

Int. j. adv. appl. sci.

View full text Add to dashboard Cite

Online Handwritten Character Recognition (OHCR) is the method of recognizing characters by a machine while the user writes, in which the handheld devices record (x, y) coordinates of the track of the character. With the advent of handheld devices, there is a great attention towards OHCR of regional languages. Preprocessing is the main phase, in OHCR, as it increases the performance of succeeding phases, by removing the inconsistency or the redundancy present in the data collected in real-world environment. In this paper, we depict the model of Preprocessing of Online Handwritten Telugu Strokes. The preprocessing steps we address in our article are Normalization, Smoothing, Duplicate Point Removal, Interpolation, Dehooking and Resampling. Preprocessing data performance is evaluated through parameters namely recognition accuracy, recognition speed, false acceptance rate and false rejection rate over HP labs dataset hpl-Telugu-ISO-char-online-1.0. The dataset contains samples of the 166 character classes collected of different writers on ACECAD Digimemo (A4 sized) using an AcecadDigi memo DCT application. It consists of 270 samples on average for each of 166 Telugu "characters" written by native Telugu writers.

show abstract

“…The format was then tested independently by members of the working group, soon followed by many other volunteers. A second iteration of the test was organized in autumn 1993 to check the changes and additions to the format [4]. In parallel, a set of tools to parse the format and browse the data were developed at NICI (with the sponsorship of HP) and at AT&T. .…”

Section: History Of Unipenmentioning

confidence: 99%

Data Sets for Ocr and Document Image Understanding Research

Guyon¹,

Haralick²,

Hull³

1997

Handbook of Character Recognition and Document Image Analysis

View full text Add to dashboard Cite

Several significant sets of labeled samples of image data are surveyed that can be used in the development of algorithms for offline and online handwriting recognition as well as for machine printed text recognition. The method used to gather each data set, the numbers of samples they contain, and the associated truth data are discussed. In the domain of offline handwriting, the CEDAR, NIST, and CENPARMI data sets are presented. These contain primarily isolated digits and alphabetic characters. The UNIPEN data set of online handwriting was collected from a number of independent sources and it contains individual characters as well as handwritten phrases. The University of Washington document image databases are also discussed. They contain a large number of English and Japanese document images that were selected from a range of publications.

show abstract

UNIPEN project of on-line data exchange and recognizer benchmarks

Abstract: We report the status of the UNIPEN project of data

Cited by 290 publications

References 6 publications

Online and offline character recognition using alignment to prototypes

Online and offline character recognition using alignment to prototypes

Preprocessing of online handwritten Telugu character recognition

Data Sets for Ocr and Document Image Understanding Research

Contact Info

Product

Resources

About