Broadsize Newspaper Comparison

<body topmargin=0 leftmargin=0 marginheight=0 marginwidth=0> <table cellpadding=0 cellspacing=0 border=0><tr> <td valign="top" rowspan="2" width=10% BGCOLOR="#FFFBF0" TEXT="#080000" background="354767e3.jpg"> <div> <A HREF="index.htm" TARGET="_top" TITLE="SearchPDF Home Page"><U>Home</U></A></div> <div> <A HREF="products.htm" TARGET="_top" TITLE="SearchPDF Products"><U>Products</U></A></div> <div> <A HREF="store.htm" TARGET="_top" TITLE="SearchPDF Product Store"><U>Store</U></A></div> <div> <A HREF="studies.htm" TARGET="_top" TITLE="Case Studies"><U>Studies</U></A></div> <div> <A HREF="papers.htm" TARGET="_top" TITLE="Papers"><U>Papers</U></A></div> <div> <A HREF="partners.htm" TARGET="_top" TITLE="Partners"><U>Partners</U></A></div> <div> <A HREF="about.htm" TARGET="_top" TITLE="About SearchPDF"><U>About</U></A></div> <bR> <div> <B>PRODUCTS</B></div> <div> <A HREF="search.htm" TARGET="_top" TITLE="SearchPDF"><U>Search</U></A></div> <div> <A HREF="metamaker.htm" TARGET="_top" TITLE="PDFMetamaker"><U>Metamaker</U></A></div> <div> <A HREF="publish.htm" TARGET="_top" TITLE="PDFPublish"><U>Publish</U></A></div> <div> <A HREF="firstpage.htm" TARGET="_top" TITLE="JRA FirstPage"><U>FirstPage</U></A></div> <div> <A HREF="compress.htm" TARGET="_top" TITLE="Compression"><U>Compress</U></A></div> <div> <A HREF="support.htm" TARGET="_top" TITLE="Support"><U>Support</U></A></div> <div> <A HREF="services.htm" TARGET="_top" TITLE="Services"><U>Services</U></A></div> <bR> </td> <td valign="top" height=130 BGCOLOR="#FFFFFF" TEXT="#080000"> <div> <IMG SRC="96be83c0.jpg" border=0 width="488" height="60" ALT="SearchPDF.com" ALIGN="BOTTOM" HSPACE="0" VSPACE="0"></div> <div> <A HREF="index.htm" TARGET="_top" TITLE="SearchPDF Home Page"><U>Home</U></A><FONT SIZE="2" COLOR="#111111" FACE="Symbol" >   ·   </FONT><A HREF="products.htm" TARGET="_top" TITLE="SearchPDF Products"><U>Products</U></A><FONT SIZE="2" COLOR="#111111" FACE="Symbol" >   ·   </FONT><A HREF="store.htm" TARGET="_top" TITLE="SearchPDF Product Store"><U>Store</U></A><FONT SIZE="2" COLOR="#111111" FACE="Symbol" >   ·   </FONT><A HREF="studies.htm" TARGET="_top" TITLE="Case Studies"><U>Studies</U></A><FONT SIZE="2" COLOR="#111111" FACE="Symbol" >   ·   </FONT><A HREF="papers.htm" TARGET="_top" TITLE="Papers"><U>Papers</U></A><FONT SIZE="2" COLOR="#111111" FACE="Symbol" >   ·   </FONT><A HREF="partners.htm" TARGET="_top" TITLE="Partners"><U>Partners</U></A><FONT SIZE="2" COLOR="#111111" FACE="Symbol" >   ·   </FONT><A HREF="about.htm" TARGET="_top" TITLE="About SearchPDF"><U>About</U></A></div> <div> <A HREF="studies.htm" TARGET="_top" TITLE="Case Studies"><U>Back to Studies</U></A></div> </td> <td valign="top" rowspan="2" width=10% BGCOLOR="#FFFBF0" TEXT="#080000" bgproperties="fixed" background="354767e3.jpg"> <bR> <div> Questions?</div> <div> <A HREF="mailto:sales@searchpdf.com" TARGET="_top" TITLE="mailto:sales@searchpdf.com"><U><IMG SRC="24a3c150.png" border=0 width="60" height="21" ALT="E-Mail SearchPDF" ALIGN="BOTTOM" HSPACE="0" VSPACE="0"></U></A></div> <div> (610) 983-3682</div> </td> </tr><tr> <td valign="top" height=350 BGCOLOR="#FFFFFF" TEXT="#080000" bgproperties="fixed" background="16880803.png"> <bR> <div> <TABLE BORDER="1" CELLPADDING="12" CELLSPACING="1" WIDTH="588" BORDERCOLORLIGHT="#C0C0C0" BORDERCOLORDARK="#808080" FRAME="BOX" RULES="ALL" HSPACE="0" VSPACE="0" BGCOLOR=#FFFBF0 > <tR> <tD VALIGN=TOP HEIGHT= 1499 WIDTH="558"><div> Broadsize Newspaper Comparison</div> <div> This is a comparison of a broadside newspaper scanned as a bitonal, 300 dpi image with automatic halftoning.</div> <bR> <div> The newspaper page is rendered as a searchable-image file in three formats:</div> <bR> <div> PDF Searchable Image with regular CCITT G4 compression</div> <div> PDF Searchable Image with new JBIG2-PDF compression</div> <div> DjVu Searchable Image</div> <bR> <div> In the table below, click the size to open that file:</div> <bR> <div> <TABLE BORDER="2" CELLPADDING="2" CELLSPACING="1" WIDTH="425" BORDERCOLORLIGHT="#C0C0C0" BORDERCOLORDARK="#808080" FRAME="BOX" RULES="ALL" HSPACE="0" VSPACE="0" > <tR> <tD VALIGN=TOP BGCOLOR=#CCFFFF HEIGHT= 16 ><NOBR><div> PDF Searchable Image - CCITT G4</div> </NOBR></tD> <tD VALIGN=TOP BGCOLOR=#CCFFCC WIDTH="123"><div> <A HREF="http://www.searchpdf.com/studies/broadsize/arabscan_jrapublish.pdf" TARGET="_top" TITLE="http://www.searchpdf.com/studies/broadsi"><U>0.990 Mb</U></A></div> </tD> </tR> <tR> <tD VALIGN=TOP BGCOLOR=#CCFFFF HEIGHT= 16 WIDTH="283"><div> PDF Searchable Image - JBIG2</div> </tD> <tD VALIGN=TOP BGCOLOR=#CCFFCC WIDTH="123"><div> <A HREF="http://www.searchpdf.com/studies/broadsize/arabscan_jrapublish_jbig2.pdf" TARGET="_top" TITLE="http://www.searchpdf.com/studies/broadsi"><U>0.463 Mb</U></A></div> </tD> </tR> <tR> <tD VALIGN=TOP BGCOLOR=#CCFFFF HEIGHT= 33 WIDTH="283"><div> DjVu - Searchable Bitonal (JB2 compression)</div> </tD> <tD VALIGN=TOP BGCOLOR=#CCFFCC WIDTH="123"><div> <A HREF="http://www.searchpdf.com/studies/broadsize/arabscan_jrapublish.djvu" TARGET="_top" TITLE="http://www.searchpdf.com/studies/broadsi"><U>0.410 Mb</U></A></div> </tD> </tR> </TABLE></div> <bR> <div> These files were created with the JRAPublish application.</div> <bR> <div> Acrobat Reader 5.0 or above is required to view the JBIG2-PDF</div> <div> DjVu Plug-In is required to view the DjVu file.</div> <bR> <div> Working with text that has a shaded background</div> <div> When a newspaper page has text that is placed on a shaded background, and the page is scanned as an enhanced bitonal image, then the shaded background is rendered as a set of dot patterns that simulate the shading.  While this works well for simulating gray-shades when the image is viewed or printed, it interferes with OCR because the OCR engine cannot distinguish or isolate the text from the dot pattern that surrounds it.</div> <bR> <div> This problem can be overcome by scanning the page in grayscale or color.  Then the OCR engine can properly isolate the text from the shaded background, which now is not a dot pattern but is instead a different color or true gray-shade.</div> <bR> <div> This OCR problem is exhibited in the sample files above, on the right-side of the image.  Try to select the text that is in the side bar and you will see that little or no text was recognized.</div> <bR> <div> Now we are presenting a second test below in which we took a section of a newspaper page with a shaded background, and we scanned it as bitonal, color, enhanced color and as grayscale.  You will see that all of the text was correctly OCRed in all the versions that were not bitonal. In the bitonal version, the dot-shading prevented effective OCR.</div> <bR> <div> <TABLE BORDER="2" CELLPADDING="2" CELLSPACING="1" WIDTH="453" BORDERCOLORLIGHT="#C0C0C0" BORDERCOLORDARK="#808080" FRAME="BOX" RULES="ALL" HSPACE="0" VSPACE="0" > <tR> <tD VALIGN=TOP BGCOLOR=#FFFFFF HEIGHT= 16 WIDTH="247"><div> <B>Image Depth</B></div> </tD> <tD VALIGN=TOP BGCOLOR=#FFFFFF WIDTH="90"><div> <B>PDF</B></div> </tD> <tD VALIGN=TOP BGCOLOR=#FFFFFF WIDTH="90"><div> <B>DjVu</B></div> </tD> </tR> <tR> <tD VALIGN=TOP BGCOLOR=#CCFFFF HEIGHT= 16 WIDTH="247"><div>   Bitonal</div> </tD> <tD VALIGN=TOP BGCOLOR=#CCFFCC WIDTH="90"><div> <A HREF="http://www.searchpdf.com/studies/broadsize/newsbar1_bitonal.pdf" TARGET="_top" TITLE="http://www.searchpdf.com/studies/broadsi"><U>0.764 Mb</U></A></div> </tD> <tD VALIGN=TOP BGCOLOR=#CCFFCC WIDTH="90"><div> <A HREF="http://www.searchpdf.com/studies/broadsize/newsbar1_bitonal.djvu" TARGET="_top" TITLE="http://www.searchpdf.com/studies/broadsi"><U>0.503 Mb</U></A></div> </tD> </tR> <tR> <tD VALIGN=TOP BGCOLOR=#CCFFFF HEIGHT= 16 WIDTH="247"><div>   Color</div> </tD> <tD VALIGN=TOP BGCOLOR=#CCFFCC WIDTH="90"><div> <A HREF="http://www.searchpdf.com/studies/broadsize/newsbar1_color.pdf" TARGET="_top" TITLE="http://www.searchpdf.com/studies/broadsi"><U>1.380 Mb</U></A></div> </tD> <tD VALIGN=TOP BGCOLOR=#CCFFCC WIDTH="90"><div> <A HREF="http://www.searchpdf.com/studies/broadsize/newsbar1_color.pdf" TARGET="_top" TITLE="http://www.searchpdf.com/studies/broadsi"><U>0.063 Mb</U></A></div> </tD> </tR> <tR> <tD VALIGN=TOP BGCOLOR=#CCFFFF HEIGHT= 16 WIDTH="247"><div>   Enhanced Color</div> </tD> <tD VALIGN=TOP BGCOLOR=#CCFFCC WIDTH="90"><div> <A HREF="http://www.searchpdf.com/studies/broadsize/newsbar1_color_enhanced.pdf" TARGET="_top" TITLE="http://www.searchpdf.com/studies/broadsi"><U>1.430 Mb</U></A></div> </tD> <tD VALIGN=TOP BGCOLOR=#CCFFCC WIDTH="90"><div> <A HREF="http://www.searchpdf.com/studies/broadsize/newsbar1_color_enhanced.djvu" TARGET="_top" TITLE="http://www.searchpdf.com/studies/broadsi"><U>0.075 Mb</U></A></div> </tD> </tR> <tR> <tD VALIGN=TOP BGCOLOR=#CCFFFF HEIGHT= 16 WIDTH="247"><div>   Grayscale</div> </tD> <tD VALIGN=TOP BGCOLOR=#CCFFCC WIDTH="90"><div> <A HREF="http://www.searchpdf.com/studies/broadsize/newsbar1_grayscale.pdf" TARGET="_top" TITLE="http://www.searchpdf.com/studies/broadsi"><U>0.959 Mb</U></A></div> </tD> <tD VALIGN=TOP BGCOLOR=#CCFFCC WIDTH="90"><div> <A HREF="http://www.searchpdf.com/studies/broadsize/newsbar1_grayscale.pdf" TARGET="_top" TITLE="http://www.searchpdf.com/studies/broadsi"><U>0.058 Mb</U></A></div> </tD> </tR> </TABLE></div> <bR> <div> Now in a further test, we took the bitonal scan, and proccessed with the dot-shading removal of ScanFix from TMSSequoia.  This effectively removed the shading from around the text.  Finally, we show the resulting bitonal PDF file with normal CCITT-G4 compression and with the new JBIG2-PDF compression.</div> <bR> <div> <TABLE BORDER="2" CELLPADDING="2" CELLSPACING="1" WIDTH="396" BORDERCOLORLIGHT="#C0C0C0" BORDERCOLORDARK="#808080" FRAME="BOX" RULES="ALL" HSPACE="0" VSPACE="0" > <tR> <tD VALIGN=TOP BGCOLOR=#FFFFFF HEIGHT= 16 WIDTH="287"><div> <B>File Type</B></div> </tD> <tD VALIGN=TOP BGCOLOR=#FFFFFF WIDTH="90"><div> <B>PDF</B></div> </tD> </tR> <tR> <tD VALIGN=TOP BGCOLOR=#CCFFFF HEIGHT= 16 WIDTH="287"><div>   Bitonal - with dot shading</div> </tD> <tD VALIGN=TOP BGCOLOR=#CCFFCC WIDTH="90"><div> <A HREF="http://www.searchpdf.com/studies/broadsize/bitonal_dot.pdf" TARGET="_top" TITLE="http://www.searchpdf.com/studies/broadsi"><U>0.375 Mb</U></A></div> </tD> </tR> <tR> <tD VALIGN=TOP BGCOLOR=#CCFFFF HEIGHT= 16 WIDTH="287"><div>   Bitonal - dot shading removed</div> </tD> <tD VALIGN=TOP BGCOLOR=#CCFFCC WIDTH="90"><div> <A HREF="http://www.searchpdf.com/studies/broadsize/bitonal_nodot.pdf" TARGET="_top" TITLE="http://www.searchpdf.com/studies/broadsi"><U>0.164 Mb</U></A></div> </tD> </tR> <tR> <tD VALIGN=TOP BGCOLOR=#CCFFFF HEIGHT= 16 ><NOBR><div>   Bitonal - with dot shading - JBIG2</div> </NOBR></tD> <tD VALIGN=TOP BGCOLOR=#CCFFCC WIDTH="90"><div> <A HREF="http://www.searchpdf.com/studies/broadsize/bitonal_dot_jbig2.pdf" TARGET="_top" TITLE="http://www.searchpdf.com/studies/broadsi"><U>0.208 Mb</U></A></div> </tD> </tR> <tR> <tD VALIGN=TOP BGCOLOR=#CCFFFF HEIGHT= 16 ><NOBR><div>   Bitonal - dot shading removed - JBIG2</div> </NOBR></tD> <tD VALIGN=TOP BGCOLOR=#CCFFCC WIDTH="90"><div> <A HREF="http://www.searchpdf.com/studies/broadsize/bitonal_nodot_jbig2.pdf" TARGET="_top" TITLE="http://www.searchpdf.com/studies/broadsi"><U>0.100 Mb</U></A></div> </tD> </tR> </TABLE></div> <bR> <bR> <bR> <bR> <bR> <bR> <bR> <bR> </tD> </tR> </TABLE></div> <bR> </td> </tr></table></body>