Character discovery in the sub-word shapes - Revision history

Dimos at 16:29, 2 October 2011

2011-10-02T16:29:06Z

2011-10-02T16:14:57Z

‎Related Dataset and Ground Truth Data

2011-10-02T15:48:44Z

2011-01-27T18:06:19Z

2010-05-13T02:59:21Z

‎Description

2010-05-13T02:47:58Z

‎Description

2010-05-13T02:47:32Z

‎Description

2010-05-13T02:46:32Z

‎Related Ground Truth Data

2010-05-13T02:45:42Z

‎Related Dataset

2010-05-13T02:42:22Z

‎References

← Older revision		Revision as of 16:29, 2 October 2011
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 34: @@
 =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=

@@ Line 33: / Line 33: @@
 The average BER is calculated over the 10 runs.
-=Related Dataset=
+=Related Dataset and Ground Truth Data=
 * [[IBN SINA: A database for research on processing and understanding of Arabic manuscripts images]]
 =References=

← Older revision		Revision as of 18:06, 27 January 2011
Line 1:		Line 1:
−	[[Datasets]] -> Current Page	+	[[Datasets]] -> [[Datasets List]] -> Current Page

	{\| style="width: 100%"		{\| style="width: 100%"

@@ Line 18: / Line 18: @@
 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].
+As a reference, the results can be compared to the published results available in Table 2 in [[#References|[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.

@@ Line 22: / Line 22: @@
 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:<br>
+The BER is defined as:
-BER = 0.5*(FP/(TN+FP) + FN/(FN+TP))
+ BER = 0.5*(FP/(TN+FP) + FN/(FN+TP))
-Where,<br>
+Where,
-FP = False Positive
+ FP = False Positive
-TP = True Positive
+ TP = True Positive
-FN = False Negative
+ FN = False Negative
-TN = True Negative
+ TN = True Negative
 The average BER is calculated over the 10 runs.

@@ Line 37: / Line 37: @@
 =Related Ground Truth Data=
-[link to GT page]
+* [[Shape Labels for the IBN SINA Dataset]]
 =References=

@@ Line 40: / Line 40: @@
 =References=
-#. 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
+# 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 [[IAPR-TC11:Reading_Systems#TC11_Officers|TC11 Officers ]].