IS it possible to extract text from BMP/JPEG image..?

Discussion in 'QnA (read only)' started by mkmkmk, May 30, 2006.

Thread Status:
Not open for further replies.
  1. mkmkmk

    mkmkmk New Member

    Joined:
    Nov 10, 2005
    Messages:
    470
    Likes Received:
    0
    Trophy Points:
    0
    Location:
    pune
    hi

    very important for me......
    i have some scanned books ....now planing to make notes very shortly some lines from every page but scanned pages means images.in the form of jpeg and bmp.

    is there any way so i can extract text from scanned book pages.........

    so tell me is there any way to extract text from jpeg ..or bmp or or pdf ...

    tke a look of this link.....its bmp image ...i have to extract all texts or i have to convert this to word ....any how i have to make notes.....

    http://img423.imageshack.us/img423/4024/10oj1.jpg


    or is there any way so i can convert these bmp or jpeg images to pdf and then extract words

    plsss answer me,,this is very important for me.........
     
    Last edited: May 30, 2006
  2. martian

    martian New Member

    Joined:
    Dec 17, 2005
    Messages:
    75
    Likes Received:
    0
    Trophy Points:
    0
    Location:
    Mars!
    Extracting text from a scanned image can be easily done. All you need is a OCR (Optical Character Recognition) software! There are a lot of those in the market.. ones that come to my mind are Abbyy's FineReader, ReadIris, and Omnipage! See if you can get your hands on one of those! Trial version will do!
     
  3. Ramakrishnan

    Ramakrishnan The Researcher

    Joined:
    Mar 7, 2006
    Messages:
    1,154
    Likes Received:
    10
    Trophy Points:
    38
    Location:
    Mumbai
    The latest version of Abby'd finr reader includes an option to scan and read the screen!!! In the above case, load the jpeg file and from the screenshot, one can get import into word,excel etc. But remember one thing, the scanned images should have a DPI of at least 300. Otherwise you may not get your output correctly. This I am telling from practical experience.
     
  4. tarey_g

    tarey_g Hanging, since 2004..

    Joined:
    Aug 21, 2004
    Messages:
    3,360
    Likes Received:
    20
    Trophy Points:
    0
    Location:
    hanging..
    U can do this thru Microsoft office's document imaging , no need of abby fine reader for this little job . If u have lot of text to be converted from pic's then consider abby.
     
  5. khansdream

    khansdream New Member

    Joined:
    Nov 28, 2005
    Messages:
    126
    Likes Received:
    0
    Trophy Points:
    0
    Location:
    Skull Island
    Well, Abby Fine Reader will do your job. And the good thing is that Abbyy's trial pack counts days to expires:D so keep your system date behind 15th day of installation, or atleast change the date while opening the Abbyy.

    Be cautions, Abbyy's would recognize Equations, Formula etc.......!!!!

    As far as .jpg/.bmp/.tif to .pdf is concern, just google it and u will several sw/w for that purpose too.

    And note: No other s/w will do the job like ABBYY.
     
  6. OP
    OP
    mkmkmk

    mkmkmk New Member

    Joined:
    Nov 10, 2005
    Messages:
    470
    Likes Received:
    0
    Trophy Points:
    0
    Location:
    pune
    Thanks to.........martian............Ramakrishnan..........tarey_g......khansdream


    thank u very much guys.......
    u have solved my big problem...
    i would llike to meet all of u personally to say thanks.....

    i have did little job with trial version....and it made me much happy.......
    i cannt afford that much cost of abbyy ..what i will do is every 14 th day i will format machine and i will use trial version again......

    about ms office 2003....if its possible with it then its much good for me ..i will try this later on ...i have ms office 2002.......

    so thanking u again and again....

    with regards
    manoj
     
    Last edited: May 31, 2006
  7. OP
    OP
    mkmkmk

    mkmkmk New Member

    Joined:
    Nov 10, 2005
    Messages:
    470
    Likes Received:
    0
    Trophy Points:
    0
    Location:
    pune
    it will work with full functions for 14 days ..........or .........with limited functions.....?
     
  8. Ramakrishnan

    Ramakrishnan The Researcher

    Joined:
    Mar 7, 2006
    Messages:
    1,154
    Likes Received:
    10
    Trophy Points:
    38
    Location:
    Mumbai
    I scanned your uploaded jpg file, it came out all right. Abby will definitely work. I used both methods, through screen shot reader and image file open and read methods. In both of them it scanned the text almost with 100% accuracy.
     
  9. OP
    OP
    mkmkmk

    mkmkmk New Member

    Joined:
    Nov 10, 2005
    Messages:
    470
    Likes Received:
    0
    Trophy Points:
    0
    Location:
    pune
    would like to say thanks to u r helping spirit again Ramakrishan...u have pulled u r time and taken much interst to solve my problem..............

    now i will move on ...i have 31 books and nearly 25,000 pages ..i have to convert this to words then i will edit that.....

    its k every 14 day i will format machine . as compare to solution i got from all of u ..formatting every 14th day is very little headache for me.......
     
    Last edited: May 31, 2006
  10. khansdream

    khansdream New Member

    Joined:
    Nov 28, 2005
    Messages:
    126
    Likes Received:
    0
    Trophy Points:
    0
    Location:
    Skull Island
    25k pages are too much. But with abbyy u will get the result, 100% accuracy is not assured as it depends on the nature of raw text, if the raw text is dull try increase the resolution in abbyy so that it can read the text better.

    If u got the equations too, then abbyy will not work, it will convert all the equations to junk characters and u will have to remove it from doc.

    As far as, trial pack of abbyy is concern. U need not format ur harddisk every 15th day.

    I have already said that abbyy works on date system. When u install abbyy it will register the date of installation and will count for 15 (date+15), as soon as abbyy finds the date of registeration is more than 15 days it will expire and then u will have to format ur hdd. So in this case, u should note the date of installation and keep the system date behind the 15 days and it wouldn't expire. If u further need to work some date related s/w like tally etc. U can keep ur system date updated but always change accordingly while opening fine reader.

    And yes, an expired abbyy would do everything but transfer data to word.
     
  11. OP
    OP
    mkmkmk

    mkmkmk New Member

    Joined:
    Nov 10, 2005
    Messages:
    470
    Likes Received:
    0
    Trophy Points:
    0
    Location:
    pune
    Thanks khansdream for u r expert words.........

    i have kept everything in note.,,

    and i think u r right....."" if the raw text is dull try increase the resolution in abbyy so that it can read the text better.""

    becoz i might have scanned some pages at 200 dpi...and getting this error......
    http://img284.imageshack.us/img284/299/343423427dl.jpg

    http://img284.imageshack.us/img284/4836/scavvvv7op.jpg

    telll me what should be my settting of resoultion...tke a look.......
    http://img424.imageshack.us/img424/997/fdsfsd8jy.jpg

    current setting is....THIS IS SCANNED IMAGE 300 dpi
    I think i should change it ....OTHER RESOULTION.........DPI....

    tell me u r suggestion.......shall i make there 400-600 dpi.......


    thanking u
    manoj
     
    Last edited: May 31, 2006
Thread Status:
Not open for further replies.

Share This Page