entangledstate-isbn 1.4.0 → 1.4.1
Sign up to get free protection for your applications and to get access to all the features.
- data/README +1 -1
- data/Rakefile +0 -18
- data/VERSION +1 -0
- data/isbn.gemspec +290 -7
- data/lib/isbn.rb +6 -6
- data/src/gocr-0.48/.cvsignore +6 -0
- data/src/gocr-0.48/AUTHORS +7 -0
- data/src/gocr-0.48/BUGS +55 -0
- data/src/gocr-0.48/CREDITS +17 -0
- data/src/gocr-0.48/HISTORY +243 -0
- data/src/gocr-0.48/INSTALL +83 -0
- data/src/gocr-0.48/Makefile +193 -0
- data/src/gocr-0.48/Makefile.in +193 -0
- data/src/gocr-0.48/README +165 -0
- data/src/gocr-0.48/READMEde.txt +80 -0
- data/src/gocr-0.48/REMARK.txt +18 -0
- data/src/gocr-0.48/REVIEW +538 -0
- data/src/gocr-0.48/TODO +65 -0
- data/src/gocr-0.48/bin/.cvsignore +2 -0
- data/src/gocr-0.48/bin/create_db +38 -0
- data/src/gocr-0.48/bin/gocr.tcl +527 -0
- data/src/gocr-0.48/bin/gocr_chk.sh +44 -0
- data/src/gocr-0.48/configure +4689 -0
- data/src/gocr-0.48/configure.in +71 -0
- data/src/gocr-0.48/doc/.#Makefile.1.6 +39 -0
- data/src/gocr-0.48/doc/.cvsignore +2 -0
- data/src/gocr-0.48/doc/Makefile +39 -0
- data/src/gocr-0.48/doc/Makefile.in +39 -0
- data/src/gocr-0.48/doc/example.dtd +53 -0
- data/src/gocr-0.48/doc/example.xml +21 -0
- data/src/gocr-0.48/doc/examples.txt +67 -0
- data/src/gocr-0.48/doc/gocr.html +578 -0
- data/src/gocr-0.48/doc/unicode.txt +57 -0
- data/src/gocr-0.48/examples/.#Makefile.1.22 +166 -0
- data/src/gocr-0.48/examples/4x6.png +0 -0
- data/src/gocr-0.48/examples/4x6.txt +2 -0
- data/src/gocr-0.48/examples/5x7.png +0 -0
- data/src/gocr-0.48/examples/5x7.png.txt +2 -0
- data/src/gocr-0.48/examples/5x8.png +0 -0
- data/src/gocr-0.48/examples/5x8.png.txt +2 -0
- data/src/gocr-0.48/examples/Makefile +166 -0
- data/src/gocr-0.48/examples/color.fig +20 -0
- data/src/gocr-0.48/examples/ex.fig +16 -0
- data/src/gocr-0.48/examples/font.tex +22 -0
- data/src/gocr-0.48/examples/font1.tex +46 -0
- data/src/gocr-0.48/examples/font2.fig +27 -0
- data/src/gocr-0.48/examples/font_nw.tex +24 -0
- data/src/gocr-0.48/examples/handwrt1.jpg +0 -0
- data/src/gocr-0.48/examples/handwrt1.txt +10 -0
- data/src/gocr-0.48/examples/inverse.fig +20 -0
- data/src/gocr-0.48/examples/matrix.jpg +0 -0
- data/src/gocr-0.48/examples/ocr-a-subset.png +0 -0
- data/src/gocr-0.48/examples/ocr-a-subset.png.txt +4 -0
- data/src/gocr-0.48/examples/ocr-a.png +0 -0
- data/src/gocr-0.48/examples/ocr-a.txt +6 -0
- data/src/gocr-0.48/examples/ocr-b.png +0 -0
- data/src/gocr-0.48/examples/ocr-b.png.txt +4 -0
- data/src/gocr-0.48/examples/polish.tex +28 -0
- data/src/gocr-0.48/examples/rotate45.fig +14 -0
- data/src/gocr-0.48/examples/score +36 -0
- data/src/gocr-0.48/examples/text.tex +28 -0
- data/src/gocr-0.48/gocr.spec +143 -0
- data/src/gocr-0.48/gpl.html +537 -0
- data/src/gocr-0.48/include/.cvsignore +2 -0
- data/src/gocr-0.48/include/config.h +36 -0
- data/src/gocr-0.48/include/config.h.in +36 -0
- data/src/gocr-0.48/include/version.h +2 -0
- data/src/gocr-0.48/install-sh +3 -0
- data/src/gocr-0.48/make.bat +57 -0
- data/src/gocr-0.48/man/.cvsignore +2 -0
- data/src/gocr-0.48/man/Makefile +29 -0
- data/src/gocr-0.48/man/Makefile.in +29 -0
- data/src/gocr-0.48/man/man1/gocr.1 +166 -0
- data/src/gocr-0.48/src/.cvsignore +4 -0
- data/src/gocr-0.48/src/Makefile +132 -0
- data/src/gocr-0.48/src/Makefile.in +132 -0
- data/src/gocr-0.48/src/amiga.h +31 -0
- data/src/gocr-0.48/src/barcode.c +846 -0
- data/src/gocr-0.48/src/barcode.c.orig +593 -0
- data/src/gocr-0.48/src/barcode.h +11 -0
- data/src/gocr-0.48/src/box.c +372 -0
- data/src/gocr-0.48/src/database.c +462 -0
- data/src/gocr-0.48/src/detect.c +943 -0
- data/src/gocr-0.48/src/gocr.c +373 -0
- data/src/gocr-0.48/src/gocr.h +288 -0
- data/src/gocr-0.48/src/jconv.c +168 -0
- data/src/gocr-0.48/src/job.c +84 -0
- data/src/gocr-0.48/src/lines.c +350 -0
- data/src/gocr-0.48/src/list.c +334 -0
- data/src/gocr-0.48/src/list.h +90 -0
- data/src/gocr-0.48/src/ocr0.c +6756 -0
- data/src/gocr-0.48/src/ocr0.h +63 -0
- data/src/gocr-0.48/src/ocr0n.c +1475 -0
- data/src/gocr-0.48/src/ocr1.c +85 -0
- data/src/gocr-0.48/src/ocr1.h +3 -0
- data/src/gocr-0.48/src/otsu.c +289 -0
- data/src/gocr-0.48/src/otsu.h +23 -0
- data/src/gocr-0.48/src/output.c +289 -0
- data/src/gocr-0.48/src/output.h +37 -0
- data/src/gocr-0.48/src/pcx.c +153 -0
- data/src/gocr-0.48/src/pcx.h +9 -0
- data/src/gocr-0.48/src/pgm2asc.c +2893 -0
- data/src/gocr-0.48/src/pgm2asc.h +105 -0
- data/src/gocr-0.48/src/pixel.c +537 -0
- data/src/gocr-0.48/src/pnm.c +533 -0
- data/src/gocr-0.48/src/pnm.h +35 -0
- data/src/gocr-0.48/src/progress.c +87 -0
- data/src/gocr-0.48/src/progress.h +42 -0
- data/src/gocr-0.48/src/remove.c +703 -0
- data/src/gocr-0.48/src/tga.c +87 -0
- data/src/gocr-0.48/src/tga.h +6 -0
- data/src/gocr-0.48/src/unicode.c +1314 -0
- data/src/gocr-0.48/src/unicode.h +1257 -0
- data/src/jpeg-7/Makefile.am +133 -0
- data/src/jpeg-7/Makefile.in +1089 -0
- data/src/jpeg-7/README +322 -0
- data/src/jpeg-7/aclocal.m4 +8990 -0
- data/src/jpeg-7/ansi2knr.1 +36 -0
- data/src/jpeg-7/ansi2knr.c +739 -0
- data/src/jpeg-7/cderror.h +132 -0
- data/src/jpeg-7/cdjpeg.c +181 -0
- data/src/jpeg-7/cdjpeg.h +187 -0
- data/src/jpeg-7/change.log +270 -0
- data/src/jpeg-7/cjpeg.1 +325 -0
- data/src/jpeg-7/cjpeg.c +616 -0
- data/src/jpeg-7/ckconfig.c +402 -0
- data/src/jpeg-7/coderules.txt +118 -0
- data/src/jpeg-7/config.guess +1561 -0
- data/src/jpeg-7/config.sub +1686 -0
- data/src/jpeg-7/configure +17139 -0
- data/src/jpeg-7/configure.ac +317 -0
- data/src/jpeg-7/depcomp +630 -0
- data/src/jpeg-7/djpeg.1 +251 -0
- data/src/jpeg-7/djpeg.c +617 -0
- data/src/jpeg-7/example.c +433 -0
- data/src/jpeg-7/filelist.txt +215 -0
- data/src/jpeg-7/install-sh +520 -0
- data/src/jpeg-7/install.txt +1097 -0
- data/src/jpeg-7/jaricom.c +148 -0
- data/src/jpeg-7/jcapimin.c +282 -0
- data/src/jpeg-7/jcapistd.c +161 -0
- data/src/jpeg-7/jcarith.c +921 -0
- data/src/jpeg-7/jccoefct.c +453 -0
- data/src/jpeg-7/jccolor.c +459 -0
- data/src/jpeg-7/jcdctmgr.c +482 -0
- data/src/jpeg-7/jchuff.c +1612 -0
- data/src/jpeg-7/jcinit.c +65 -0
- data/src/jpeg-7/jcmainct.c +293 -0
- data/src/jpeg-7/jcmarker.c +667 -0
- data/src/jpeg-7/jcmaster.c +770 -0
- data/src/jpeg-7/jcomapi.c +106 -0
- data/src/jpeg-7/jconfig.bcc +48 -0
- data/src/jpeg-7/jconfig.cfg +45 -0
- data/src/jpeg-7/jconfig.dj +38 -0
- data/src/jpeg-7/jconfig.mac +43 -0
- data/src/jpeg-7/jconfig.manx +43 -0
- data/src/jpeg-7/jconfig.mc6 +52 -0
- data/src/jpeg-7/jconfig.sas +43 -0
- data/src/jpeg-7/jconfig.st +42 -0
- data/src/jpeg-7/jconfig.txt +155 -0
- data/src/jpeg-7/jconfig.vc +45 -0
- data/src/jpeg-7/jconfig.vms +37 -0
- data/src/jpeg-7/jconfig.wat +38 -0
- data/src/jpeg-7/jcparam.c +632 -0
- data/src/jpeg-7/jcprepct.c +358 -0
- data/src/jpeg-7/jcsample.c +545 -0
- data/src/jpeg-7/jctrans.c +381 -0
- data/src/jpeg-7/jdapimin.c +396 -0
- data/src/jpeg-7/jdapistd.c +275 -0
- data/src/jpeg-7/jdarith.c +762 -0
- data/src/jpeg-7/jdatadst.c +151 -0
- data/src/jpeg-7/jdatasrc.c +212 -0
- data/src/jpeg-7/jdcoefct.c +736 -0
- data/src/jpeg-7/jdcolor.c +396 -0
- data/src/jpeg-7/jdct.h +393 -0
- data/src/jpeg-7/jddctmgr.c +382 -0
- data/src/jpeg-7/jdhuff.c +1309 -0
- data/src/jpeg-7/jdinput.c +384 -0
- data/src/jpeg-7/jdmainct.c +512 -0
- data/src/jpeg-7/jdmarker.c +1360 -0
- data/src/jpeg-7/jdmaster.c +663 -0
- data/src/jpeg-7/jdmerge.c +400 -0
- data/src/jpeg-7/jdpostct.c +290 -0
- data/src/jpeg-7/jdsample.c +361 -0
- data/src/jpeg-7/jdtrans.c +136 -0
- data/src/jpeg-7/jerror.c +252 -0
- data/src/jpeg-7/jerror.h +304 -0
- data/src/jpeg-7/jfdctflt.c +174 -0
- data/src/jpeg-7/jfdctfst.c +230 -0
- data/src/jpeg-7/jfdctint.c +4348 -0
- data/src/jpeg-7/jidctflt.c +242 -0
- data/src/jpeg-7/jidctfst.c +368 -0
- data/src/jpeg-7/jidctint.c +5137 -0
- data/src/jpeg-7/jinclude.h +91 -0
- data/src/jpeg-7/jmemansi.c +167 -0
- data/src/jpeg-7/jmemdos.c +638 -0
- data/src/jpeg-7/jmemdosa.asm +379 -0
- data/src/jpeg-7/jmemmac.c +289 -0
- data/src/jpeg-7/jmemmgr.c +1118 -0
- data/src/jpeg-7/jmemname.c +276 -0
- data/src/jpeg-7/jmemnobs.c +109 -0
- data/src/jpeg-7/jmemsys.h +198 -0
- data/src/jpeg-7/jmorecfg.h +369 -0
- data/src/jpeg-7/jpegint.h +395 -0
- data/src/jpeg-7/jpeglib.h +1135 -0
- data/src/jpeg-7/jpegtran.1 +272 -0
- data/src/jpeg-7/jpegtran.c +546 -0
- data/src/jpeg-7/jquant1.c +856 -0
- data/src/jpeg-7/jquant2.c +1310 -0
- data/src/jpeg-7/jutils.c +179 -0
- data/src/jpeg-7/jversion.h +14 -0
- data/src/jpeg-7/libjpeg.map +4 -0
- data/src/jpeg-7/libjpeg.txt +3067 -0
- data/src/jpeg-7/ltmain.sh +8406 -0
- data/src/jpeg-7/makcjpeg.st +36 -0
- data/src/jpeg-7/makdjpeg.st +36 -0
- data/src/jpeg-7/makeadsw.vc6 +77 -0
- data/src/jpeg-7/makeasln.vc9 +33 -0
- data/src/jpeg-7/makecdep.vc6 +82 -0
- data/src/jpeg-7/makecdsp.vc6 +130 -0
- data/src/jpeg-7/makecmak.vc6 +159 -0
- data/src/jpeg-7/makecvcp.vc9 +186 -0
- data/src/jpeg-7/makeddep.vc6 +82 -0
- data/src/jpeg-7/makeddsp.vc6 +130 -0
- data/src/jpeg-7/makedmak.vc6 +159 -0
- data/src/jpeg-7/makedvcp.vc9 +186 -0
- data/src/jpeg-7/makefile.ansi +220 -0
- data/src/jpeg-7/makefile.bcc +291 -0
- data/src/jpeg-7/makefile.dj +226 -0
- data/src/jpeg-7/makefile.manx +220 -0
- data/src/jpeg-7/makefile.mc6 +255 -0
- data/src/jpeg-7/makefile.mms +224 -0
- data/src/jpeg-7/makefile.sas +258 -0
- data/src/jpeg-7/makefile.unix +234 -0
- data/src/jpeg-7/makefile.vc +217 -0
- data/src/jpeg-7/makefile.vms +142 -0
- data/src/jpeg-7/makefile.wat +239 -0
- data/src/jpeg-7/makejdep.vc6 +423 -0
- data/src/jpeg-7/makejdsp.vc6 +285 -0
- data/src/jpeg-7/makejdsw.vc6 +29 -0
- data/src/jpeg-7/makejmak.vc6 +425 -0
- data/src/jpeg-7/makejsln.vc9 +17 -0
- data/src/jpeg-7/makejvcp.vc9 +328 -0
- data/src/jpeg-7/makeproj.mac +213 -0
- data/src/jpeg-7/makerdep.vc6 +6 -0
- data/src/jpeg-7/makerdsp.vc6 +78 -0
- data/src/jpeg-7/makermak.vc6 +110 -0
- data/src/jpeg-7/makervcp.vc9 +133 -0
- data/src/jpeg-7/maketdep.vc6 +43 -0
- data/src/jpeg-7/maketdsp.vc6 +122 -0
- data/src/jpeg-7/maketmak.vc6 +131 -0
- data/src/jpeg-7/maketvcp.vc9 +178 -0
- data/src/jpeg-7/makewdep.vc6 +6 -0
- data/src/jpeg-7/makewdsp.vc6 +78 -0
- data/src/jpeg-7/makewmak.vc6 +110 -0
- data/src/jpeg-7/makewvcp.vc9 +133 -0
- data/src/jpeg-7/makljpeg.st +68 -0
- data/src/jpeg-7/maktjpeg.st +30 -0
- data/src/jpeg-7/makvms.opt +4 -0
- data/src/jpeg-7/missing +376 -0
- data/src/jpeg-7/rdbmp.c +439 -0
- data/src/jpeg-7/rdcolmap.c +253 -0
- data/src/jpeg-7/rdgif.c +38 -0
- data/src/jpeg-7/rdjpgcom.1 +63 -0
- data/src/jpeg-7/rdjpgcom.c +515 -0
- data/src/jpeg-7/rdppm.c +459 -0
- data/src/jpeg-7/rdrle.c +387 -0
- data/src/jpeg-7/rdswitch.c +365 -0
- data/src/jpeg-7/rdtarga.c +500 -0
- data/src/jpeg-7/structure.txt +945 -0
- data/src/jpeg-7/testimg.bmp +0 -0
- data/src/jpeg-7/testimg.jpg +0 -0
- data/src/jpeg-7/testimg.ppm +4 -0
- data/src/jpeg-7/testimgp.jpg +0 -0
- data/src/jpeg-7/testorig.jpg +0 -0
- data/src/jpeg-7/testprog.jpg +0 -0
- data/src/jpeg-7/transupp.c +1533 -0
- data/src/jpeg-7/transupp.h +205 -0
- data/src/jpeg-7/usage.txt +605 -0
- data/src/jpeg-7/wizard.txt +211 -0
- data/src/jpeg-7/wrbmp.c +442 -0
- data/src/jpeg-7/wrgif.c +399 -0
- data/src/jpeg-7/wrjpgcom.1 +103 -0
- data/src/jpeg-7/wrjpgcom.c +583 -0
- data/src/jpeg-7/wrppm.c +269 -0
- data/src/jpeg-7/wrrle.c +305 -0
- data/src/jpeg-7/wrtarga.c +253 -0
- metadata +287 -6
- data/LICENSE +0 -20
- data/VERSION.yml +0 -4
@@ -0,0 +1,17 @@
|
|
1
|
+
Thanks:
|
2
|
+
...to everyone who contributed to gocr. If you feel that your
|
3
|
+
name should be in this list, write mail to the author. These
|
4
|
+
are in no particular order:
|
5
|
+
|
6
|
+
G.Kugler for sending me first example files and testing. (MayMM)
|
7
|
+
Klaas Freitag for the libPgm2asc-patch <freitag@suse.de>
|
8
|
+
Ryan Dibble for the otsu.c file <dibbler@umich.edu>
|
9
|
+
Tim Waugh for the man page <twaugh@redhat.com>
|
10
|
+
David Pinson for the tkispell-patch <dpinson@materials.unsw.EDU.AU>
|
11
|
+
Martin Goldhahn for some patches <Martin.Goldhahn@Webcenter.no>
|
12
|
+
Eberhard Burkard for the gocr.tcl patch <E.Burkard@web.de>
|
13
|
+
James R. Van Zandt for lot of tips <jrv@vanzandt.mv.com>
|
14
|
+
...
|
15
|
+
|
16
|
+
... and everyone else who submitted bug-reports,
|
17
|
+
feature-requests, patches and lots of example files.
|
@@ -0,0 +1,243 @@
|
|
1
|
+
History: (Changes,ChangeLog)
|
2
|
+
0.48 Jul09
|
3
|
+
fix buffer overflow introduced in 0.46 for filenames
|
4
|
+
add codabar barcode
|
5
|
+
fix bug, removing melted serifs
|
6
|
+
add patch by Chris Lee, i25 barcode recognition + modifications
|
7
|
+
fix some false positive numbers "34" (video, gas meter)
|
8
|
+
fix problems with 2zZ4 for 10x10 screen font
|
9
|
+
better debug output for :;,.
|
10
|
+
remove examples, doc and libs part from configure (see below)
|
11
|
+
remove doc and examples from the (make install) part to reduce
|
12
|
+
dependencies (gs and transfig is not needed for rpm/ebuild)
|
13
|
+
gocr only may depend from netpbm, but can live without too
|
14
|
+
this will help to install gocr on "exotic" (nonlinux) platforms
|
15
|
+
fix gentoo app-text/gocr Bug 243250 src/Makefile: $(CC) $(LDFLAGS) ...
|
16
|
+
|
17
|
+
0.47 fix database recognition for certainty 100 (-a 100)
|
18
|
+
insert spaces with certainty 100 (old: 99) to let -a 100 work
|
19
|
+
new option -u string for unrecognized chars
|
20
|
+
fix: No contrast in image causes division by zero
|
21
|
+
reduced false positive recognition of scanned "a496" (Gutenberg Project)
|
22
|
+
"d as a" patch ID: 1556112
|
23
|
+
add "Windows Pipe Fix", but I hate extra code for bad environments
|
24
|
+
improve 7x10, sample 0811qemu1.png (ToDo: not finished)
|
25
|
+
change black:white from >4:1 to >3.5:1 as criteria of inversion
|
26
|
+
reintroduce static library libPgm2asc.a (make libs) for OSRA project
|
27
|
+
add dynamic library (make libs), unused but may help other projects
|
28
|
+
|
29
|
+
0.46 improved context correction (especially helvetica "Il")
|
30
|
+
improved recognition of tiny chars "$1", fat "s", "rw" ","
|
31
|
+
fix blank spaces problem in filenames
|
32
|
+
(http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=316511)
|
33
|
+
!!! please check on other platforms and report to me !!!
|
34
|
+
there are still problems with special chars (double quodes, backslash)
|
35
|
+
better use this way: djpeg -gray -pnm strangefilename.jpg | gocr -
|
36
|
+
fix possible problem with database and UTF8 input
|
37
|
+
fix hidden bug in pitch/spacing initialization
|
38
|
+
reactivate code for output of glued chars and strings
|
39
|
+
fix wrong close() call
|
40
|
+
remove creation of pgm2asc.a for simplicity (see SF-patch 1827477)
|
41
|
+
|
42
|
+
0.45 minor corrections for c and k
|
43
|
+
minus sign is filtered by option -C "--" now, ("\-" was parsed badly)
|
44
|
+
clean up old unused code for simplicity (api, frontend)
|
45
|
+
fix problem with low height barcodes and barcode removing
|
46
|
+
fix problem with readpgm (for multiple images) and database
|
47
|
+
PACKAGE_VERSION defined by configure.in AC_INIT + gocr.spec
|
48
|
+
|
49
|
+
0.44 add volume to boxes (negative means white areas inside black areas)
|
50
|
+
Fix overflow in despeckling routine (verbose mode, dust removing)
|
51
|
+
reactivate composed chars, fix merge_boxes
|
52
|
+
fix problems with uncertain line detection and not recognized "7"
|
53
|
+
option -a has an effect now for the output
|
54
|
+
adaptions to MICR E13-B font (see GnuMICR), ToDo: 4 extra-chars
|
55
|
+
fix num_boxes in merge_boxes (affects line detection)
|
56
|
+
reduce 2 prompts to one per char in database mode, ^A for skip all
|
57
|
+
fix problem with smaller headlines
|
58
|
+
fix problems with tall font (4)
|
59
|
+
fix includes for non-linux-platforms
|
60
|
+
|
61
|
+
0.43 fix problem with dark frame around image
|
62
|
+
support multiple images, ex: giftopnm -image=all a.gif | gocr -
|
63
|
+
invert if obviously white on black (black_mass>=4*white_mass)
|
64
|
+
improve thresholding for discrete histograms
|
65
|
+
(note: this can particularly lead to bad results, will be fixed later)
|
66
|
+
speedup for big boxes (especially dark background)
|
67
|
+
fix memory leak (setas(same string) + detect_barcode)
|
68
|
+
fix uninitialized variables after insert spaces (num_frames)
|
69
|
+
fix frame_vector for single pixels (twice + ERROR idx out of range)
|
70
|
+
|
71
|
+
0.42 further parts of recognition engine relaced by vector version
|
72
|
+
changed colored debug output for out??.png
|
73
|
+
division of glued chars replaced (slower but more accurate)
|
74
|
+
fix framing of small font
|
75
|
+
fix problem with uninitialized pnm_readpaminit call (CPS 21Nov06)
|
76
|
+
better progress output (see progress.[ch]), new image debug output
|
77
|
+
switch to the new improved rotation detection
|
78
|
+
|
79
|
+
0.41 (buggy if --with-netpbm=no, apply the pgm-patch!)
|
80
|
+
otsu.c concentrates now only on high contrast regions
|
81
|
+
fix pnm reads for 2 byte pixels (--with-libpbm=no)
|
82
|
+
update man-page (mail me your suggestions)
|
83
|
+
fix g++ warnings, float-OPs replaced by int-OPs
|
84
|
+
spacing reviewed; make distance() more sensitive
|
85
|
+
xml-objects (barcode, melted chars) now also handled with weights
|
86
|
+
fix division by zero bug for vertical positioned characters
|
87
|
+
default output is UTF8 now, UTF-encoding bug fixed
|
88
|
+
added certainty option
|
89
|
+
added uninstall to Makefile
|
90
|
+
debug image format changed to png (using pipe) or ppm (fall-back)
|
91
|
+
much better word spacing (line-by-line based)
|
92
|
+
better DOT_ABOVE recognition
|
93
|
+
fix output of char groups or strings stored in database, utf8 input
|
94
|
+
fix buffer overflow in barcode decode39
|
95
|
+
fix lost comma on end of line
|
96
|
+
internal vector format added for future use (faster, scalable, rotable)
|
97
|
+
line detection extended
|
98
|
+
internal list management rewritten to fix memory leaks and segfaults
|
99
|
+
|
100
|
+
0.40 update PNM file reader to maxval > 255
|
101
|
+
(make rpm) updated
|
102
|
+
barcode-patch UPC_addon by Michael van Rooyen
|
103
|
+
CAPITAL_LETTER_A_WITH_OGONEK added
|
104
|
+
no "(PICTURE)" output for UTF8+ASCII (better for Mobile OCR project)
|
105
|
+
smooth_borders() bug fixed and reworked
|
106
|
+
5x7 and prop10 font adaptions
|
107
|
+
objects now detected by flood-fill algorithm (better?)
|
108
|
+
XML-output changed
|
109
|
+
changed auto dust detection (not final)
|
110
|
+
|
111
|
+
0.39 XML output added (subject of change, suggestions are welcome)
|
112
|
+
netpbm-link-error fixed in gocr.c and configure.in:
|
113
|
+
gocr.c: <config.h> changed to "config.h"
|
114
|
+
configure-option --with-netpbm=PATH and --without-netpbm added
|
115
|
+
update configure.in according to autoconf 2.57
|
116
|
+
wchar_h miss-configuration fixed in pgm2asc.c
|
117
|
+
fix compiler warnings
|
118
|
+
char filter accepts abbreviations now, like "0-9A-F" (but slow)
|
119
|
+
update READMEde.txt
|
120
|
+
output barcode tags (also improved recognition)
|
121
|
+
fix pnm.c for files like example.eps.pbm
|
122
|
+
fix detect.c for barcodes
|
123
|
+
fix ocr0n.c 0<->8g
|
124
|
+
|
125
|
+
0.38 move UTF/HTML/TeX decoding to getTextLine, return (char *) now
|
126
|
+
out_format HTML step towards detailed XML output
|
127
|
+
correct line detection for footnotes (detect.c)
|
128
|
+
"y" now seen as vowel (pgm2asc.c), I<vowel> susbtituted by l<vowel>
|
129
|
+
é-detection, á-output fixed
|
130
|
+
default dust_size is -1 now (auto detection = mean_size/10)
|
131
|
+
char filter added
|
132
|
+
ex: -C 0123456789ABCDEF - recognize only hexcodes
|
133
|
+
man page updated (hopefully correct syntax)
|
134
|
+
database bug fixed (small fonts, example by Chris)
|
135
|
+
several bugs fixed by W. Webber (thanks)
|
136
|
+
speed improved by 3rd-pass matrix filter in pixel() (pixel.c) (code from W. Webber)
|
137
|
+
bug in remove_dust (remove.c) fixed
|
138
|
+
for fonts bigger than 20x40 smooth_borders() changed (b/w-scans)
|
139
|
+
bug in O0-detection fixed
|
140
|
+
|
141
|
+
0.37 best-fit generates probability, not perfect but better results
|
142
|
+
bug in line detection removed (happens for lot of small boxes)
|
143
|
+
progress output (option -x <fileID|fname>)
|
144
|
+
counting versions number as floating point now
|
145
|
+
MACRON and DOT_ABOVE (not complete) defined (latin2)
|
146
|
+
adaptions for 5x7 and 6x12 screen font
|
147
|
+
doc/ocr.tex changed to doc/gocr.html (now independent of LaTeX)
|
148
|
+
symbols {} added
|
149
|
+
OCR-B font tested succesfull
|
150
|
+
better headline/picture distinction
|
151
|
+
bug removed (struct box.modifier is wchar_t now)
|
152
|
+
|
153
|
+
known bugs: to much newlines
|
154
|
+
|
155
|
+
0.3.6
|
156
|
+
CARON and Omega defined,
|
157
|
+
output of not defined chars (HTML="&#xxx;", TeX="\symbol{xxx}")
|
158
|
+
system dependend bug: isupper(>255) SIGSEGV fixed
|
159
|
+
better line detection for lines with lowercase chars only
|
160
|
+
lot of possible SIGSEGV in list_del() fixed
|
161
|
+
barcode recognition (UPC,code128)
|
162
|
+
.ps .eps via pstopnm supported
|
163
|
+
-m 256 switches off the main ocr engine (usefull together with -m 2 for identical chars)
|
164
|
+
strings added to database ("ff","ft","special-symbol")
|
165
|
+
gocr.tcl adapted to gocr v0.3
|
166
|
+
internal detection probability introduced
|
167
|
+
|
168
|
+
0.3.5
|
169
|
+
minor and major fixes (string\0 bugs)
|
170
|
+
memory leak fixes by Duncan Edwards
|
171
|
+
layout analysis or zoning (-m 4) improved,
|
172
|
+
now it detects pictures and columns much better
|
173
|
+
the behavior of setting threshold (-l) is slightly changed
|
174
|
+
wcsdup defined for non-gnu-systems (BSD), further Problems?
|
175
|
+
better context correction for 10 (IO,lO)
|
176
|
+
Fixes for S.Koledin examples "GlS"
|
177
|
+
Euro-currency-sign detection added
|
178
|
+
better pitch estimation for proportional font (needs to be improved)
|
179
|
+
make install DESTDIR= instead configure --prefix= (better?)
|
180
|
+
use wchar_t by default, more simple code and -f works with nonLinuxOS
|
181
|
+
line detection more robust against vertical glued chars (js)
|
182
|
+
-f UTF8 added (usefull for xterm -u8), should be default?
|
183
|
+
handle vertical glued boxes (ex: g over T)
|
184
|
+
0.3.4
|
185
|
+
some BSD adaptions (no WCHAR?), tell me if there are still problems
|
186
|
+
use unicode in database (4-8 hex digits)
|
187
|
+
new option: -p database_path/
|
188
|
+
TILDE fixed, #, Æ, Å, etc. added (swedish,norwegian)
|
189
|
+
layout analysis improved
|
190
|
+
0.3.3
|
191
|
+
database (-m 2) bug fixed and interactive mode (-m 130) added
|
192
|
+
its not finished, but you can test it
|
193
|
+
result should be ok for machine generated images (no scans)
|
194
|
+
engine improved a bit
|
195
|
+
0.3.2
|
196
|
+
ocr-engine improved for screen fonts (thanks for examples)
|
197
|
+
option -f [HTML,TeX,...] added
|
198
|
+
0.3.1
|
199
|
+
make install updated
|
200
|
+
0.3.0 some parts of the code reviewed (most work done by Bruno Barberi Gnecco)
|
201
|
+
tkispell patch from David Pinson (exec bug fixed)
|
202
|
+
gnome frontend added (Dany De Bontrider)
|
203
|
+
acute, grave, circumflex ... detection
|
204
|
+
C++ parts rewritten into C, and much more (see REVIEW)
|
205
|
+
0.2.7 lib-patch from Klaas Freitag inserted, engine improved
|
206
|
+
option -n 1 detect only numbers, get threshold value by otsu.cc
|
207
|
+
xxx.pnm.bz2 can be used on linux systems bzip2 installed
|
208
|
+
0.2.6 pipes used on POSIX2-systems for easier use of jpg,gif,tiff,pnm.gz-files
|
209
|
+
example: gocr text.jpg; gocr text.pnm.gz
|
210
|
+
verbose output on stderr, text output on stdout,
|
211
|
+
redirection of output possible (-e, -o, example: -e /dev/stdout)
|
212
|
+
engine upgraded a bit (thx for the new sample files)
|
213
|
+
gocr.tcl upgraded (save options, save text)
|
214
|
+
DOS/WIN95-EXE created, download GOCREXE.ZIP (v0.2.5)
|
215
|
+
0.2.5 program convert renamed to jconv
|
216
|
+
you can choose stdin as input now, for using conversion tools
|
217
|
+
example: djpeg -pnm -gray text.jpg | gocr -i -
|
218
|
+
option "--help" added, some bugs removed
|
219
|
+
amiga.h added for SAS/C under AmigaOS (suggested by Uffe Holst)
|
220
|
+
line detection changed (faster?)
|
221
|
+
importing gocr in your C++ application is easier now (see fkt pgm2asc)
|
222
|
+
argument can be given instead of option -i (this is more natural)
|
223
|
+
some reorganization of code (not finished)
|
224
|
+
2000 downloads counted !!! Jun2000
|
225
|
+
SourceForge.net used for gocr (project: jocr, other gocr exist there)
|
226
|
+
bugs in dust removing, line detection and zoning fixed (rewritten)
|
227
|
+
first version of tcl/tk-GUI, test it!
|
228
|
+
rekursive function frame_nn() replaced by labyrint-algorithm (no extensiv stack used)
|
229
|
+
gluing of broken chars added, removing glued serifs (on small fonts)
|
230
|
+
new bugs added :;
|
231
|
+
0.2.4a2 some details are added (better dust removing and char division)
|
232
|
+
0.2.4 three char division (connected chars), dust removing
|
233
|
+
0.2.3 add layout analysis (very slowly, try -m 4), engine modified
|
234
|
+
better distance function, engine updated, database added for testing
|
235
|
+
1000 downloads counted !!! May2000
|
236
|
+
0.2.2 gocr_0_2.tgz expands into gocr_0_2 directory (thanks to zz99zz)
|
237
|
+
engine upgraded a bit, some bugs fixed (umlaut, thin lines)
|
238
|
+
short documentation added (ocr.tex)
|
239
|
+
colored output (out30.bmp) for test/development-mode
|
240
|
+
bug: read ASC-PBM and PCX (1 bit) fixed
|
241
|
+
0.2.1 first official release on freshmeat.net March 2000
|
242
|
+
0.2 line scanning added
|
243
|
+
0.1 project started (not documented), autumn 1998 - summer 1999
|
@@ -0,0 +1,83 @@
|
|
1
|
+
INSTALLING gOCR
|
2
|
+
|
3
|
+
|
4
|
+
INSTALLING BINARIES
|
5
|
+
-------------------
|
6
|
+
Be sure that you have all the libraries needed. To install a binary package,
|
7
|
+
do the following:
|
8
|
+
|
9
|
+
1. Unpack the archive if you have not done so already:
|
10
|
+
|
11
|
+
tar -xzf gocr[version].tar.gz
|
12
|
+
|
13
|
+
on older tar versions, the above line might not work. If so, try the following:
|
14
|
+
|
15
|
+
gzip -cd gocr[version].tgz | tar -xf -
|
16
|
+
|
17
|
+
This creates the directory ./gocr[version] containing the source from
|
18
|
+
the main archive.
|
19
|
+
|
20
|
+
2. Change to gocr directory and run make (use GNU Make).
|
21
|
+
|
22
|
+
cd gocr[version]; make install
|
23
|
+
|
24
|
+
That's it.
|
25
|
+
|
26
|
+
INSTALLING FROM SOURCE
|
27
|
+
----------------------
|
28
|
+
|
29
|
+
Requirements
|
30
|
+
------------
|
31
|
+
You'll need a compiler; we recommend gcc, but the code should compile in any
|
32
|
+
good one. gcc is available at http://gcc.gnu.org. I had some problems with gcc
|
33
|
+
2.95.1 (it consumed a LOT of memory while compiling ocr0.c). 2.95.2 seems to
|
34
|
+
be better.
|
35
|
+
|
36
|
+
gOCR provides some simple functions to read/write pnm archives. Though not
|
37
|
+
needed, we strongly suggest, however, that you install the NetPBM package. Its
|
38
|
+
official URL is: http://download.sourceforge.net/netpbm/.
|
39
|
+
|
40
|
+
Installing this package will add support to many different image formats.
|
41
|
+
If you have a NetPBM version older than August 2000, we suggest that you
|
42
|
+
download a more recent one, to take advantage of the new PAM functions.
|
43
|
+
|
44
|
+
To create some of the examples provided, you'll need transfig.
|
45
|
+
This is completely optional.
|
46
|
+
|
47
|
+
Procedure
|
48
|
+
---------
|
49
|
+
1. Unpack the archive if you have not done so already:
|
50
|
+
|
51
|
+
tar -xzf gocr[version].tar.gz
|
52
|
+
|
53
|
+
on older tar versions, the above line might not work. If so, try the following:
|
54
|
+
|
55
|
+
gzip -cd gocr[version].tgz | tar -xf -
|
56
|
+
|
57
|
+
This creates the directory ./gocr[version] containing the source from
|
58
|
+
the main archive.
|
59
|
+
|
60
|
+
2. Change to gocr directory and run configure.
|
61
|
+
|
62
|
+
cd gocr[version]; ./configure
|
63
|
+
|
64
|
+
For a list of options, try ./configure --help.
|
65
|
+
If something goes wrong, try to run autoconf.
|
66
|
+
|
67
|
+
3. Run make (GNU Make). This can take a while.
|
68
|
+
|
69
|
+
make
|
70
|
+
|
71
|
+
4. gOCR comes with some examples, which are generated from xfig-files.
|
72
|
+
If you have transfig installed, you can make them:
|
73
|
+
|
74
|
+
make examples
|
75
|
+
|
76
|
+
5. Install the binaries. You may need to do this as root.
|
77
|
+
|
78
|
+
make install
|
79
|
+
|
80
|
+
6. Run gocr, or the frontend you chose.
|
81
|
+
|
82
|
+
gocr -h Shows help
|
83
|
+
gocr.tcl Runs Tcl GUI
|
@@ -0,0 +1,193 @@
|
|
1
|
+
#
|
2
|
+
# type "make help" for help
|
3
|
+
#
|
4
|
+
# TODO: examples
|
5
|
+
# add rpm to dist package, man page
|
6
|
+
#
|
7
|
+
# Changes:
|
8
|
+
# - be sure that configure is called after untgz, tar original file attributes
|
9
|
+
# - suggestion of Marcel Pol 6Dec2001:
|
10
|
+
# make install DESTDIR=$RPM_BUILD_ROOT
|
11
|
+
#
|
12
|
+
|
13
|
+
prefix = /usr/local
|
14
|
+
#bindir = $(prefix)/bin
|
15
|
+
bindir = /usr/local${exec_prefix}/bin
|
16
|
+
|
17
|
+
SHELL = /bin/sh
|
18
|
+
# this does not work on SuSE 6.0, why? (autoconf 2.12 do not set /bin/sh ?)
|
19
|
+
#SHELL = bash #
|
20
|
+
INSTALL = /usr/bin/install -c
|
21
|
+
CC = gcc
|
22
|
+
CFLAGS = -g -O2
|
23
|
+
# following DEFs are not used, but I play with it for training
|
24
|
+
CPPFLAGS = -Wall -g -fexceptions -DDO_DEBUG=1
|
25
|
+
DEFS = -DHAVE_CONFIG_H
|
26
|
+
includedir = ${prefix}/include
|
27
|
+
#
|
28
|
+
# -pedantic -ansi -Wall
|
29
|
+
LDFLAGS = -lm
|
30
|
+
LIBS = -lnetpbm
|
31
|
+
|
32
|
+
# RANLIB = @RANLIB@
|
33
|
+
# AR = @AR@
|
34
|
+
|
35
|
+
|
36
|
+
# files for devel.tgz
|
37
|
+
FILES = \
|
38
|
+
AUTHORS Makefile Makefile.in bin/ doc/ include/ examples/ man/ src/\
|
39
|
+
BUGS README make.bat CREDITS READMEde.txt REMARK.txt\
|
40
|
+
HISTORY REVIEW configure gpl.html INSTALL TODO configure.in\
|
41
|
+
install-sh gocr.spec .cvsignore
|
42
|
+
|
43
|
+
# files for distribution
|
44
|
+
AFILES = $(FILES) lib/
|
45
|
+
|
46
|
+
DIRS = doc/ include/ man/ examples/ bin/ src/ lib/
|
47
|
+
|
48
|
+
# export all make-variables to submakes - said to be not working on IRIS
|
49
|
+
|
50
|
+
# default rule
|
51
|
+
default: all
|
52
|
+
|
53
|
+
.PHONY : src doc examples help clean proper distclean dist tgz rpm libs
|
54
|
+
|
55
|
+
# example file generation takes lot of memory and time, do it explicitely
|
56
|
+
# by make examples
|
57
|
+
all: src Makefile
|
58
|
+
@echo " --- for help do: make help ---"
|
59
|
+
@echo " --- for documentation do: make doc ---"
|
60
|
+
@echo " --- for examples do: make examples ---"
|
61
|
+
|
62
|
+
include/config.h: include/config.h.in configure
|
63
|
+
./configure
|
64
|
+
|
65
|
+
configure: configure.in
|
66
|
+
autoconf
|
67
|
+
|
68
|
+
Makefile: Makefile.in configure
|
69
|
+
./configure
|
70
|
+
|
71
|
+
src/Makefile: src/Makefile.in configure
|
72
|
+
./configure
|
73
|
+
|
74
|
+
src: src/Makefile
|
75
|
+
$(MAKE) -C src all
|
76
|
+
|
77
|
+
libs: src/Makefile
|
78
|
+
$(MAKE) -C src libs
|
79
|
+
|
80
|
+
man:
|
81
|
+
$(MAKE) -C man all
|
82
|
+
|
83
|
+
doc:
|
84
|
+
$(MAKE) -C doc all
|
85
|
+
|
86
|
+
examples:
|
87
|
+
$(MAKE) -C examples all
|
88
|
+
|
89
|
+
help:
|
90
|
+
@printf "make - compile all\n"
|
91
|
+
@printf "make libs - compile libraries libPgm2asc.{a,so}\n"
|
92
|
+
@printf "make src - build lib and gocr\n"
|
93
|
+
@printf "make man - build manual\n"
|
94
|
+
@printf "make doc - make documentation\n"
|
95
|
+
@printf "make examples - create examples ./examples/\n"
|
96
|
+
@printf "make clean - erase temporary files\n"
|
97
|
+
@printf "make proper - erase all created files\n"
|
98
|
+
@printf "make install - Really? Its development version!\n"
|
99
|
+
@printf "make uninstall - remove installed files from the system\n"
|
100
|
+
|
101
|
+
|
102
|
+
# you can override this variable by: make install DESTDIR=yourpath
|
103
|
+
DESTDIR=/usr/local
|
104
|
+
.PHONY : install uninstall test examples
|
105
|
+
install:
|
106
|
+
$(MAKE) -C src install
|
107
|
+
$(MAKE) -C man install
|
108
|
+
# following steps are not needed for end users, but cost dependencies
|
109
|
+
# therefore removed in 0.48
|
110
|
+
# $(MAKE) -C doc install
|
111
|
+
# $(MAKE) -C examples install
|
112
|
+
# $(MAKE) -C frontend install
|
113
|
+
|
114
|
+
uninstall:
|
115
|
+
$(MAKE) -C src uninstall
|
116
|
+
$(MAKE) -C man uninstall
|
117
|
+
# $(MAKE) -C doc uninstall
|
118
|
+
# $(MAKE) -C examples uninstall
|
119
|
+
# $(MAKE) -C frontend uninstall
|
120
|
+
|
121
|
+
# generate version file before packaging (most up to date)
|
122
|
+
# release is the date of the last modified src file (for bug reports)
|
123
|
+
# to distinguish different developper versions of same version number
|
124
|
+
include/version.h: src/*.[ch] Makefile
|
125
|
+
echo "#define version_string \"0.48\"" > $@
|
126
|
+
echo "#define release_string \"`date +%Y%m%d`\"" >> $@
|
127
|
+
|
128
|
+
dist: include/version.h
|
129
|
+
echo gocr-0.48 > .fname
|
130
|
+
-rm -rf `cat .fname`
|
131
|
+
mkdir `cat .fname`
|
132
|
+
# create subdirs, because cp -r bin/gocr.tcl jocr => jocr/gocr.tcl
|
133
|
+
(cd `cat .fname`; mkdir $(DIRS))
|
134
|
+
cp -r -p -d $(AFILES) `cat .fname`
|
135
|
+
$(MAKE) -C `cat .fname` proper
|
136
|
+
# for Win, DOS and Mac no configure available, reset config.h
|
137
|
+
cp `cat .fname`/include/config.h.in `cat .fname`/include/config.h
|
138
|
+
touch `cat .fname`/configure # Makefile will be updated
|
139
|
+
tar chzf ../`cat .fname`.tar.gz `cat .fname`
|
140
|
+
-gpg -ab --default-key 0x53BDFBE3 ../`cat .fname`.tar.gz # .asc
|
141
|
+
ls -l ../`cat .fname`.tar.gz{,.asc}
|
142
|
+
-rm -rf `cat .fname` .fname
|
143
|
+
|
144
|
+
|
145
|
+
# the tgz-option is only for the author, to carry the sources home
|
146
|
+
tgz: include/version.h
|
147
|
+
mkdir jocr # causes an error if exist
|
148
|
+
# create subdirs, because cp -r bin/gocr.tcl jocr => jocr/gocr.tcl
|
149
|
+
(cd jocr; mkdir $(DIRS))
|
150
|
+
-cp -rup -d $(FILES) CVS jocr
|
151
|
+
$(MAKE) -C jocr proper
|
152
|
+
if test -d jocr/src/api; then echo "--- rm -r jocr/src/api ---"; fi
|
153
|
+
-rm -rf jocr/src/api
|
154
|
+
# -rm -rf jocr/CVS jocr/*/CVS jocr/*/*/CVS # CVS tree
|
155
|
+
-rm -rf jocr/Makefile jocr/src/Makefile jocr/include/config.h
|
156
|
+
tar chzf ../jocr.tgz jocr
|
157
|
+
-gpg -ab --default-key 0x53BDFBE3 ../jocr.tgz # .asc
|
158
|
+
-cp ../jocr.tgz ../jocr.tgz.`date +%y%m%d` # backup, remove later
|
159
|
+
ls -l ../jocr.tgz{,.asc}
|
160
|
+
-rm -rf jocr
|
161
|
+
|
162
|
+
# the rpm option is for the author, to create simple rpm packages
|
163
|
+
TRPM = $(HOME)/tmp_gocr_build
|
164
|
+
# only gocr?
|
165
|
+
#VERSION=$(shell sed -e '/version_string/!d' -e 's/[^0-9.]*\([0-9.]*\).*/\1/' -e q src/gocr.c)
|
166
|
+
rpm:
|
167
|
+
echo "%_topdir $(TRPM)" > ~/.rpmmacros
|
168
|
+
mkdir -p $(TRPM)/{SOURCES,SPECS,BUILD,RPMS,SRPMS}
|
169
|
+
sed "s/version.*[0-9]\.[0-9]*/version 0.48/"\
|
170
|
+
gocr.spec >$(TRPM)/SPECS/gocr.spec
|
171
|
+
cp ../gocr-0.48.tar.gz $(TRPM)/SOURCES
|
172
|
+
#rpmbuild -ba --nobuild gocr.spec # bin+src-rpm
|
173
|
+
(cd $(TRPM)/SPECS; rpmbuild -bb gocr.spec)
|
174
|
+
rpm -qil -p $(TRPM)/RPMS/i?86/gocr-0.48-*.i?86.rpm
|
175
|
+
|
176
|
+
# PHONY = don't look at file clean, -rm = start rm and ignore errors
|
177
|
+
.PHONY : clean proper
|
178
|
+
clean:
|
179
|
+
-rm -f config.cache config.status config.log
|
180
|
+
-rm -f *.aux *.log *.dvi *.ps *.lj *~ gocr.ini out.txt
|
181
|
+
-rm -f convert.cc convert convert.o # remove v0.2.4 rests
|
182
|
+
$(MAKE) -C src clean
|
183
|
+
$(MAKE) -C doc clean
|
184
|
+
$(MAKE) -C examples/ clean
|
185
|
+
|
186
|
+
|
187
|
+
distclean: proper
|
188
|
+
|
189
|
+
proper: clean
|
190
|
+
$(MAKE) -C src/ proper
|
191
|
+
$(MAKE) -C doc proper
|
192
|
+
$(MAKE) -C examples/ proper
|
193
|
+
-rm -f gocr bin/gocr libPgm2asc.* out??.bmp
|