<?xml version="1.0"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en-GB">
	<id>https://embryology.med.unsw.edu.au/embryology/index.php?action=history&amp;feed=atom&amp;title=Talk%3AEmbryology_Image_Tutorial</id>
	<title>Talk:Embryology Image Tutorial - Revision history</title>
	<link rel="self" type="application/atom+xml" href="https://embryology.med.unsw.edu.au/embryology/index.php?action=history&amp;feed=atom&amp;title=Talk%3AEmbryology_Image_Tutorial"/>
	<link rel="alternate" type="text/html" href="https://embryology.med.unsw.edu.au/embryology/index.php?title=Talk:Embryology_Image_Tutorial&amp;action=history"/>
	<updated>2026-11-19T04:48:20Z</updated>
	<subtitle>Revision history for this page on the wiki</subtitle>
	<generator>MediaWiki 1.39.10</generator>
	<entry>
		<id>https://embryology.med.unsw.edu.au/embryology/index.php?title=Talk:Embryology_Image_Tutorial&amp;diff=49437&amp;oldid=prev</id>
		<title>S8600021: /* Figure text extraction in biomedical literature */</title>
		<link rel="alternate" type="text/html" href="https://embryology.med.unsw.edu.au/embryology/index.php?title=Talk:Embryology_Image_Tutorial&amp;diff=49437&amp;oldid=prev"/>
		<updated>2011-02-20T04:42:58Z</updated>

		<summary type="html">&lt;p&gt;&lt;span dir=&quot;auto&quot;&gt;&lt;span class=&quot;autocomment&quot;&gt;Figure text extraction in biomedical literature&lt;/span&gt;&lt;/span&gt;&lt;/p&gt;
&lt;table style=&quot;background-color: #fff; color: #202122;&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;en-GB&quot;&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;← Older revision&lt;/td&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;Revision as of 15:42, 20 February 2011&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l16&quot;&gt;Line 16:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Line 16:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;RESULTS/CONCLUSIONS: The evaluation on 382 figures (9,643 figure texts in total) randomly selected from PubMed Central full-text articles shows that FigTExT performed with 84% precision, 98% recall, and 90% F1-score for text localization and with 62.5% precision, 51.0% recall and 56.2% F1-score for figure text extraction. When limiting figure texts to those judged by domain experts to be important content, FigTExT performed with 87.3% precision, 68.8% recall, and 77% F1-score. FigTExT significantly improved the performance of the off-the-shelf OCR tool we used, which on its own performed with 36.6% precision, 19.3% recall, and 25.3% F1-score for text extraction. In addition, our results show that FigTExT can extract texts that do not appear in figure captions or other associated text, further suggesting the potential utility of FigTExT for improving figure search.&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;RESULTS/CONCLUSIONS: The evaluation on 382 figures (9,643 figure texts in total) randomly selected from PubMed Central full-text articles shows that FigTExT performed with 84% precision, 98% recall, and 90% F1-score for text localization and with 62.5% precision, 51.0% recall and 56.2% F1-score for figure text extraction. When limiting figure texts to those judged by domain experts to be important content, FigTExT performed with 87.3% precision, 68.8% recall, and 77% F1-score. FigTExT significantly improved the performance of the off-the-shelf OCR tool we used, which on its own performed with 36.6% precision, 19.3% recall, and 25.3% F1-score for text extraction. In addition, our results show that FigTExT can extract texts that do not appear in figure captions or other associated text, further suggesting the potential utility of FigTExT for improving figure search.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;PMID: 21249186  &lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;PMID: &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;21249186&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-side-deleted&quot;&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;http://www.ncbi.nlm.nih.gov/pubmed/&lt;/ins&gt;21249186&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;==2010==&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;==2010==&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;

&lt;!-- diff cache key embryology:diff::1.12:old-49436:rev-49437 --&gt;
&lt;/table&gt;</summary>
		<author><name>S8600021</name></author>
	</entry>
	<entry>
		<id>https://embryology.med.unsw.edu.au/embryology/index.php?title=Talk:Embryology_Image_Tutorial&amp;diff=49436&amp;oldid=prev</id>
		<title>S8600021: Created page with &quot;{{Talk Page}} ==2011==  ===Figure text extraction in biomedical literature===  Kim D, Yu H.  PLoS One. 2011 Jan 13;6(1):e15338.  Abstract  BACKGROUND: Figures are ubiquitous in b...&quot;</title>
		<link rel="alternate" type="text/html" href="https://embryology.med.unsw.edu.au/embryology/index.php?title=Talk:Embryology_Image_Tutorial&amp;diff=49436&amp;oldid=prev"/>
		<updated>2011-02-20T04:42:39Z</updated>

		<summary type="html">&lt;p&gt;Created page with &amp;quot;{{Talk Page}} ==2011==  ===Figure text extraction in biomedical literature===  Kim D, Yu H.  PLoS One. 2011 Jan 13;6(1):e15338.  Abstract  BACKGROUND: Figures are ubiquitous in b...&amp;quot;&lt;/p&gt;
&lt;p&gt;&lt;b&gt;New page&lt;/b&gt;&lt;/p&gt;&lt;div&gt;{{Talk Page}}&lt;br /&gt;
==2011==&lt;br /&gt;
&lt;br /&gt;
===Figure text extraction in biomedical literature===&lt;br /&gt;
&lt;br /&gt;
Kim D, Yu H.&lt;br /&gt;
&lt;br /&gt;
PLoS One. 2011 Jan 13;6(1):e15338.&lt;br /&gt;
&lt;br /&gt;
Abstract&lt;br /&gt;
&lt;br /&gt;
BACKGROUND: Figures are ubiquitous in biomedical full-text articles, and they represent important biomedical knowledge. However, the sheer volume of biomedical publications has made it necessary to develop computational approaches for accessing figures. Therefore, we are developing the Biomedical Figure Search engine (http://figuresearch.askHERMES.org) to allow bioscientists to access figures efficiently. Since text frequently appears in figures, automatically extracting such text may assist the task of mining information from figures. Little research, however, has been conducted exploring text extraction from biomedical figures.&lt;br /&gt;
&lt;br /&gt;
METHODOLOGY: We first evaluated an off-the-shelf Optical Character Recognition (OCR) tool on its ability to extract text from figures appearing in biomedical full-text articles. We then developed a Figure Text Extraction Tool (FigTExT) to improve the performance of the OCR tool for figure text extraction through the use of three innovative components: image preprocessing, character recognition, and text correction. We first developed image preprocessing to enhance image quality and to improve text localization. Then we adapted the off-the-shelf OCR tool on the improved text localization for character recognition. Finally, we developed and evaluated a novel text correction framework by taking advantage of figure-specific lexicons.&lt;br /&gt;
&lt;br /&gt;
RESULTS/CONCLUSIONS: The evaluation on 382 figures (9,643 figure texts in total) randomly selected from PubMed Central full-text articles shows that FigTExT performed with 84% precision, 98% recall, and 90% F1-score for text localization and with 62.5% precision, 51.0% recall and 56.2% F1-score for figure text extraction. When limiting figure texts to those judged by domain experts to be important content, FigTExT performed with 87.3% precision, 68.8% recall, and 77% F1-score. FigTExT significantly improved the performance of the off-the-shelf OCR tool we used, which on its own performed with 36.6% precision, 19.3% recall, and 25.3% F1-score for text extraction. In addition, our results show that FigTExT can extract texts that do not appear in figure captions or other associated text, further suggesting the potential utility of FigTExT for improving figure search.&lt;br /&gt;
&lt;br /&gt;
PMID: 21249186 &lt;br /&gt;
&lt;br /&gt;
==2010==&lt;br /&gt;
===Automatic figure ranking and user interfacing for intelligent figure search===&lt;br /&gt;
Yu H, Liu F, Ramesh BP.&lt;br /&gt;
PLoS One. 2010 Oct 7;5(10):e12983.&lt;br /&gt;
PMID: 20949102&lt;br /&gt;
&lt;br /&gt;
==2009==&lt;br /&gt;
&lt;br /&gt;
===Are figure legends sufficient? Evaluating the contribution of associated text to biomedical figure comprehension===&lt;br /&gt;
Yu H, Agarwal S, Johnston M, Cohen A.&lt;br /&gt;
J Biomed Discov Collab. 2009 Jan 6;4:1.&lt;br /&gt;
PMID: 19126221&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===FigSum: automatically generating structured text summaries for figures in biomedical literature===&lt;br /&gt;
Agarwal S, Yu H.&lt;br /&gt;
AMIA Annu Symp Proc. 2009 Nov 14;2009:6-10.&lt;br /&gt;
PMID: 20351812&lt;/div&gt;</summary>
		<author><name>S8600021</name></author>
	</entry>
</feed>