Thanks Elmer for your answer. I have your same problem, i have read in real time a sequence of number. I tried to binarize an image of plate in black and white using gimp with a statical threshold but with bad results. What filters you have used to clear the image? and the quality of your image is poor as mine?
On 10 Mag, 22:32, Elmer Fittery <[email protected]> wrote: > This is what I am doing now! > > I take a 72x72 resolution screen shot of a section of my screen. > > In one case the picture is black background and white foreground. > In the other case the screen shot is a white background with a black > foreground. > > The only thing I am trying to process is $.,0123456789 > > In general, with preprocessing of the .tif file with Imagick's convert > program, I have no problems with using tesseract to convert the image to > text. > > So, my observation about the 72x72 pixels/inch being too poor for > tessseract to process is: > > It is not true. > > Also you can use the Imagick command: > > convert <input-file-name> -resample 300x300 <output-file-name> > > and your output file will have a 300x300 resolution. > > If you don't believe it, use the command: > > tiffinfo <file-basename>.tif > > NOTE: you really need to preprocess the .tif file to make it a > black/white .tif file - i.e. get rid of any RGB colors. > > The real key to getting good results with tesseract is to clean the file > up with a graphic program prior to trying to convert it to text. > > I spent the last 2 weeks developing code to in real time take screen > shots of numbers; cleaning up screen shot; converting to numbers; > passing the numbers to a math routine to do statistical calculations. > > It can be done, but it is a pain. If I didn't have tesseract and > Imagick, it would be impossible. > > good luck > > > > On Mon, 2010-05-10 at 23:11 +0530, Sriranga(77yrsold) wrote: > > Tif file if very poor resolution and background is not deep black and > > white Tesseract will not support such type of tif. sorry. > > > On Mon, May 10, 2010 at 5:55 PM, faster589 <[email protected]> > > wrote: > > Thanks for your answer. I using ubuntu 9.10 for run tesseract. > > I have upload the two file t0.tif e t0.box in the section file > > that i > > use for training tesseract. > > the two link are: > > > > > http://tesseract-ocr.googlegroups.com/web/t1.box?gda=OJOMSDgAAADSWFpg... > > > > > http://tesseract-ocr.googlegroups.com/web/t1.tif?gda=WGUDjzgAAADSWFpg... > > > image resolution is too low to using with tesseract? > > I have create manually the file .box because tesseract with > > the > > command "tesseract fontfile.tif fontfile batch.nochop makebox" > > return > > an empty file. > > > On 10 Mag, 04:01, "Sriranga(77yrsold)" > > <[email protected]> > > wrote: > > > > Which OS is using? It appears that resolution=72 is poor - > > it should be more > > > than 300 dpi - try again. > > > One more thing the commandline should be like this > > > "tesseract fontfile.tif fontfile nobatch box.train.stderr", > > if you are using > > > tesseract svn-319 otherwise is OK. > > > please upload sample tif file with its box. > > > Cheers. > > > > On Mon, May 10, 2010 at 12:44 AM, faster589 > > <[email protected]> wrote: > > > > Hi ! I'm training tesseract for character plate > > recognition. I have > > > > create the two file image.tif and image.box for training > > tesseract but > > > > when i lunch the command tesseract fontfile.tif junk > > nobatch > > > > box.train.stderr tesseract return this error: > > > > > Tesseract Open Source OCR Engine > > > > Image has 8 * 3 bits per pixel, and size (640,480) > > > > Resolution=72 > > > > APPLY_BOXES: boxfile 1/1/C ((188,216),(218,272)): FAILURE! > > box > > > > overlaps no blobs or blobs in multiple rows > > > > APPLY_BOXES: boxfile 1/2/C ((220,216),(253,272)): FAILURE! > > box > > > > overlaps no blobs or blobs in multiple rows > > > > APPLY_BOXES: boxfile 1/3/1 ((274,215),(299,273)): FAILURE! > > box > > > > overlaps no blobs or blobs in multiple rows > > > > APPLY_BOXES: boxfile 1/4/5 ((304,217),(337,274)): FAILURE! > > box > > > > overlaps no blobs or blobs in multiple rows > > > > APPLY_BOXES: boxfile 1/5/4 ((337,217),(367,273)): FAILURE! > > box > > > > overlaps no blobs or blobs in multiple rows > > > > APPLY_BOXES: boxfile 1/6/B ((369,215),(401,273)): FAILURE! > > box > > > > overlaps no blobs or blobs in multiple rows > > > > APPLY_BOXES: boxfile 2/1/E ((399,216),(434,274)): FAILURE! > > box > > > > overlaps no blobs or blobs in multiple rows > > > > APPLY_BOXES: More than one block?? > > > > APPLY_BOXES: FATALITY - 0 labelled samples of "C" - target > > is 2: > > > > C:[43] > > > > APPLY_BOXES: FATALITY - 0 labelled samples of "1" - target > > is 1: > > > > 1:[31] > > > > APPLY_BOXES: FATALITY - 0 labelled samples of "5" - target > > is 1: > > > > 5:[35] > > > > APPLY_BOXES: FATALITY - 0 labelled samples of "4" - target > > is 1: > > > > 4:[34] > > > > APPLY_BOXES: FATALITY - 0 labelled samples of "B" - target > > is 1: > > > > B:[42] > > > > APPLY_BOXES: FATALITY - 0 labelled samples of "E" - target > > is 1: > > > > E:[45] > > > > APPLY_BOXES: > > > > Boxes read from boxfile: 7 > > > > Initially labelled blobs: 0 in 0 rows > > > > Box failures detected: 7 > > > > Duped blobs for rebalance: 0 > > > > "C" has fewest samples: 0 > > > > Total unlabelled words: > > 0 > > > > Final labelled words: > > 0 > > > > Generating training data > > > > Generated training data for 0 blobs > > > > > How can i solve? > > > > > -- > > > > You received this message because you are subscribed to > > the Google Groups > > > > "tesseract-ocr" group. > > > > To post to this group, send email to > > [email protected]. > > > > To unsubscribe from this group, send email to > > > > > [email protected]<tesseract-ocr% > > [email protected]> > > > > . > > > > For more options, visit this group at > > > >http://groups.google.com/group/tesseract-ocr?hl=en. > > > > -- > > > You received this message because you are subscribed to the > > Google Groups "tesseract-ocr" group. > > > To post to this group, send email to > > [email protected]. > > > To unsubscribe from this group, send email to tesseract-ocr > > [email protected]. > > > > For more options, visit this group > > athttp://groups.google.com/group/tesseract-ocr?hl=en. > > > -- > > > You received this message because you are subscribed to the > > Google Groups "tesseract-ocr" group. > > To post to this group, send email to > > [email protected]. > > To unsubscribe from this group, send email to tesseract-ocr > > [email protected]. > > For more options, visit this group at > > http://groups.google.com/group/tesseract-ocr?hl=en. > > > -- > > You received this message because you are subscribed to the Google > > Groups "tesseract-ocr" group. > > To post to this group, send email to [email protected]. > > To unsubscribe from this group, send email to tesseract-ocr > > [email protected]. > > For more options, visit this group at > >http://groups.google.com/group/tesseract-ocr?hl=en. > > -- > You received this message because you are subscribed to the Google Groups > "tesseract-ocr" group. > To post to this group, send email to [email protected]. > To unsubscribe from this group, send email to > [email protected]. > For more options, visit this group > athttp://groups.google.com/group/tesseract-ocr?hl=en. -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected]. To unsubscribe from this group, send email to [email protected]. For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en.
