Recent changes to Validation

Validation modified by Dmitry Katsubo

Dmitry Katsubo — Sun, 11 Jan 2015 00:19:00 -0000

--- v18
+++ v19
@@ -1,8 +1,6 @@
-  * A large validation set consisting of 5719 chemical structure images and associated MOL files is available for download. This set was produced from the US Patent Office Complex Work Units and contain one structure per image, ground truth MOL files and a simple [Perl](http://openbabel.org) script to benchmark the results of your chemical structure recognition software. The benchmark script takes two arguments - first the folder with ground truth files ("molfiles") and second with your generated files - the filenames of individual structures should be identical. It will compare the structures based on standard InChI. This validation set was made possible courtesy of collaboration with Dr. Steve Boyer and Dr. John Kinney. 
-
-This file has been updated courtesy of Aniko Valko and Keymodule Ltd., UK. The ground truth molfiles have been corrected and invalid images have been removed. 
-
-     Download zip archive [here](http://osra.sourceforge.net/uspto-validation-updated.zip). 
+  * A large validation set consisting of 5719 chemical structure images and associated MOL files is available for download. This set was produced from the US Patent Office Complex Work Units and contain one structure per image, ground truth MOL files and a simple [Perl script](http://downloads.sourceforge.net/project/osra/filtering/hq) to benchmark the results of your chemical structure recognition software. The benchmark script takes two arguments - first the folder with ground truth files ("molfiles") and second with your generated files - the filenames of individual structures should be identical. It will compare the structures based on standard InChI. This validation set was made possible courtesy of collaboration with Dr. Steve Boyer and Dr. John Kinney. 
+    This file has been updated courtesy of Aniko Valko and Keymodule Ltd., UK. The ground truth molfiles have been corrected and invalid images have been removed. 
+    Download zip archive [here](http://osra.sourceforge.net/uspto-validation-updated.zip).

   * A subset of 450 images from the Japanese Patent Office [Chem-Infty dataset](http://www.iapr-tc11.org/mediawiki/index.php/Chem-Infty_Dataset:_A_ground-truthed_dataset_of_Chemical_Structure_Images) containing only organic molecules can be downloaded here: [images](http://osra.sourceforge.net/images-organic.zip) and [ground truth](http://osra.sourceforge.net/molfiles-organic.zip).

Validation modified by Igor

Igor — Fri, 13 Jun 2014 11:18:20 -0000

--- v17
+++ v18
@@ -9,38 +9,22 @@
      This subset is distributed by permission from the original Chem-Infty dataset authors Koji Nakagawa, Akio Fujiyoshi, and Masakazu Suzuki. This work is licensed under a [Creative Commons Attribution-Noncommercial-No Derivative Works 2.1 Japan License](http://creativecommons.org/licenses/by-nc-nd/2.1/jp/deed.en).

 ### Recognition Results
-
-Set  Size  OSRA 1.4.0  [Imago 2.0](http://ggasoftware.com/opensource/imago) OSRA 2.0.0 
-
-[Image2Structure](https://wiki.ir-facility.org/index.php/Image2Structure_Task)
-1000 
-84.7% 
-90.2% 
-91.9% 
-
-[CLEF-2012](http://www.ifs.tuwien.ac.at/~clef-ip/download/2012/index.shtml)
-865 
-89.5% 
-67.0% 
-96.5% 
-
-[JPO](http://osra.sourceforge.net/images-organic.zip)
-450 
-56.2% 
-40.4% 
-62.6% 
-
-[USPTO](http://osra.sourceforge.net/uspto-validation-updated.zip)
-5719 
-81.5% 
-86.9% 
-88.0% 
-
-[Maybridge UoB](http://www.cs.bham.ac.uk/research/groupings/reasoning/sdag/chemical.php)
-5740 
-74.0% 
-63.5% 
-86.4% 
-
+
+
+
+
+ 
+
+ 
+
+
+  
+ 
+
+
+ 
+ 
+
+Set                                                                             Size OSRA 1.4.0 [Imago 2.0](http://ggasoftware.com/opensource/imago) OSRA 2.0.0
[Image2Structure](https://wiki.ir-facility.org/index.php/Image2Structure_Task)  1000 84.7% 90.2% 91.9%
[CLEF-2012](http://www.ifs.tuwien.ac.at/~clef-ip/download/2012/index.shtml)  865   89.5%   67.0% 96.5%
[JPO](http://osra.sourceforge.net/images-organic.zip)  450  56.2%  40.4%  62.6% 
[USPTO](http://osra.sourceforge.net/uspto-validation-updated.zip) 5719  81.5% 86.9% 88.0%
[Maybridge UoB](http://www.cs.bham.ac.uk/research/groupings/reasoning/sdag/chemical.php)  5740  74.0%  63.5%  86.4% 

 The recall results are shown (fraction of the original structure set returned correctly by the software). The identity match between the recognized structures and the originals was ascertained by standard [InChI](http://en.wikipedia.org/wiki/International_Chemical_Identifier).

Validation modified by Anonymous

Anonymous — Thu, 22 May 2014 11:00:15 -0000

--- v16
+++ v17
@@ -43,4 +43,4 @@
 86.4%

-The recall results are shown (portion of the original structures returned correctly by the software). The identity match between the recognized structures and the originals was ascertained by standard [InChI](http://en.wikipedia.org/wiki/International_Chemical_Identifier). 
+The recall results are shown (fraction of the original structure set returned correctly by the software). The identity match between the recognized structures and the originals was ascertained by standard [InChI](http://en.wikipedia.org/wiki/International_Chemical_Identifier).

Validation modified by Anonymous

Anonymous — Thu, 22 May 2014 11:00:15 -0000

--- v15
+++ v16
@@ -43,4 +43,4 @@
 86.4%

-The recall results are shown. The identity match between the recognized structure and the original was ascertained by standard [InChI](http://en.wikipedia.org/wiki/International_Chemical_Identifier). 
+The recall results are shown (portion of the original structures returned correctly by the software). The identity match between the recognized structures and the originals was ascertained by standard [InChI](http://en.wikipedia.org/wiki/International_Chemical_Identifier).

Validation modified by Anonymous

Anonymous — Thu, 22 May 2014 11:00:14 -0000

Validation modified by Anonymous

Anonymous — Thu, 22 May 2014 11:00:14 -0000

Validation modified by Anonymous

Anonymous — Thu, 22 May 2014 11:00:14 -0000

--- v12
+++ v13
@@ -10,7 +10,7 @@

 ### Recognition Results

-Set  Size  1.4.0  [Imago 2.0](http://ggasoftware.com/opensource/imago) OSRA 2.0.0 
+Set  Size  OSRA 1.4.0  [Imago 2.0](http://ggasoftware.com/opensource/imago) OSRA 2.0.0 

 [Image2Structure](https://wiki.ir-facility.org/index.php/Image2Structure_Task)
 1000

Validation modified by Anonymous

Anonymous — Thu, 22 May 2014 11:00:14 -0000

--- v11
+++ v12
@@ -7,3 +7,40 @@
   * A subset of 450 images from the Japanese Patent Office [Chem-Infty dataset](http://www.iapr-tc11.org/mediawiki/index.php/Chem-Infty_Dataset:_A_ground-truthed_dataset_of_Chemical_Structure_Images) containing only organic molecules can be downloaded here: [images](http://osra.sourceforge.net/images-organic.zip) and [ground truth](http://osra.sourceforge.net/molfiles-organic.zip).

      This subset is distributed by permission from the original Chem-Infty dataset authors Koji Nakagawa, Akio Fujiyoshi, and Masakazu Suzuki. This work is licensed under a [Creative Commons Attribution-Noncommercial-No Derivative Works 2.1 Japan License](http://creativecommons.org/licenses/by-nc-nd/2.1/jp/deed.en). 
+
+### Recognition Results
+
+Set  Size  1.4.0  [Imago 2.0](http://ggasoftware.com/opensource/imago) OSRA 2.0.0 
+
+[Image2Structure](https://wiki.ir-facility.org/index.php/Image2Structure_Task)
+1000 
+84.7% 
+90.2% 
+91.9% 
+
+[CLEF-2012](http://www.ifs.tuwien.ac.at/~clef-ip/download/2012/index.shtml)
+865 
+89.5% 
+67.0% 
+96.5% 
+
+[JPO](http://osra.sourceforge.net/images-organic.zip)
+450 
+56.2% 
+40.4% 
+62.6% 
+
+[USPTO](http://osra.sourceforge.net/uspto-validation-updated.zip)
+5719 
+81.5% 
+86.9% 
+88.0% 
+
+[Maybridge UoB](http://www.cs.bham.ac.uk/research/groupings/reasoning/sdag/chemical.php)
+5740 
+74.0% 
+63.5% 
+86.4% 
+
+  
+The recall results are shown. The identity match between the recognized structure and the original was ascertained by standard [InChI](http://en.wikipedia.org/wiki/International_Chemical_Identifier).

Validation modified by Anonymous

Anonymous — Thu, 22 May 2014 11:00:14 -0000

--- v10
+++ v11
@@ -2,7 +2,7 @@

 This file has been updated courtesy of Aniko Valko and Keymodule Ltd., UK. The ground truth molfiles have been corrected and invalid images have been removed. 

-     Download zip archive [uspto-validation-updated.zip](Validation/attachment/uspto-validation-updated.zip). 
+     Download zip archive [here](http://osra.sourceforge.net/uspto-validation-updated.zip). 

   * A subset of 450 images from the Japanese Patent Office [Chem-Infty dataset](http://www.iapr-tc11.org/mediawiki/index.php/Chem-Infty_Dataset:_A_ground-truthed_dataset_of_Chemical_Structure_Images) containing only organic molecules can be downloaded here: [images](http://osra.sourceforge.net/images-organic.zip) and [ground truth](http://osra.sourceforge.net/molfiles-organic.zip).

Validation modified by Anonymous

Anonymous — Thu, 22 May 2014 11:00:14 -0000

--- v9
+++ v10
@@ -2,7 +2,7 @@

 This file has been updated courtesy of Aniko Valko and Keymodule Ltd., UK. The ground truth molfiles have been corrected and invalid images have been removed. 

-     Download zip archive [[Media:uspto-validation-updated.zip] here]. 
+     Download zip archive [uspto-validation-updated.zip](Validation/attachment/uspto-validation-updated.zip). 

   * A subset of 450 images from the Japanese Patent Office [Chem-Infty dataset](http://www.iapr-tc11.org/mediawiki/index.php/Chem-Infty_Dataset:_A_ground-truthed_dataset_of_Chemical_Structure_Images) containing only organic molecules can be downloaded here: [images](http://osra.sourceforge.net/images-organic.zip) and [ground truth](http://osra.sourceforge.net/molfiles-organic.zip).

Set	Size	OSRA 1.4.0	[Imago 2.0](http://ggasoftware.com/opensource/imago)	OSRA 2.0.0
[Image2Structure](https://wiki.ir-facility.org/index.php/Image2Structure_Task)	1000	84.7%	90.2%	91.9%
[CLEF-2012](http://www.ifs.tuwien.ac.at/~clef-ip/download/2012/index.shtml)	865	89.5%	67.0%	96.5%
[JPO](http://osra.sourceforge.net/images-organic.zip)	450	56.2%	40.4%	62.6%
[USPTO](http://osra.sourceforge.net/uspto-validation-updated.zip)	5719	81.5%	86.9%	88.0%
[Maybridge UoB](http://www.cs.bham.ac.uk/research/groupings/reasoning/sdag/chemical.php)	5740	74.0%	63.5%	86.4%