Difference between revisions of "Character discovery in the sub-word shapes"

From TC11
Jump to: navigation, search
 
(One intermediate revision by the same user not shown)
Line 12: Line 12:
 
|}
 
|}
  
 +
|}
 +
=Proposed By=
 +
{| border="0"
 +
|-
 +
| <pre>Prof Mohamed Cheriet
 +
Synchromedia Laboratory
 +
ETS, Montréal, (QC) Canada
 +
H3C 1K3
 +
E-mail: mohamed.cheriet@etsmtl.ca
 +
Tel: +1(514)396-8972
 +
Fax: +1(514)396-8595
 +
</pre>
 +
|
 +
| [[Image:Synchromedia logo.png|200px|thumb|[http://www.synchromedia.ca/web/ets/ '''Synchromedia Laboratory''']]]
 +
| [[Image:Ets logo.jpg|230px|thumb|[http://www.etsmtl.ca/ '''École de technologie supérieure''']]]
 
|}
 
|}
  
Line 34: Line 49:
  
 
=Related Dataset and Ground Truth Data=
 
=Related Dataset and Ground Truth Data=
* [[IBN SINA: A database for research on processing and understanding of Arabic manuscripts images]]
+
* [[IBN SINA: A database for research on processing and understanding of Arabic manuscripts images]] (originally proposed for v1.0 of the dataset)
  
 
=References=
 
=References=

Latest revision as of 16:29, 2 October 2011

Datasets -> Datasets List -> Current Page

Created: 2010-04-30
Last updated: 2011-10-02

Proposed By

Prof Mohamed Cheriet
 Synchromedia Laboratory
 ETS, Montréal, (QC) Canada
 H3C 1K3
 E-mail: mohamed.cheriet@etsmtl.ca
 Tel: +1(514)396-8972
 Fax: +1(514)396-8595

Description

Labels for 15 characters are provided in the ground truth. For each character, a classifier is required to predict the presence of that character in each shape. Output of the classifier is binary. The evaluation for each character is carried out separately. The Balanced Error Rate (BER) is used as the performance measure (please see below for the details).

As a reference, the results can be compared to the published results available in Table 2 in [1]. Evaluation Protocol A cross-validation technique is proposed for the evaluation of this task. The average BER for each character is computed by repeating the training process for 10 times. In each run, the database is split into a training set and test set randomly. The training set consists of 80 percent of the database. The proposed method is trained using the training data, and its performance is computed over the test data in terms of BER.

The BER is defined as:

BER = 0.5*(FP/(TN+FP) + FN/(FN+TP))

Where,

FP = False Positive
TP = True Positive
FN = False Negative
TN = True Negative

The average BER is calculated over the 10 runs.

Related Dataset and Ground Truth Data

References

  1. Reza Farrahi Moghaddam, Mohamed Cheriet, Mathias M. Adankon, Kostyantyn Filonenko, and Robert Wisnovsky, “IBN SINA: A database for research on processing and understanding of Arabic manuscripts images”, Proceedings of DAS’10, June 9-11, 2010, Boston, MA, USA



This page is editable only by TC11 Officers .