1. This site uses cookies. By continuing to use this site, you are agreeing to our use of cookies. Learn More.

[NEED HELP]Creating a java based OCR,need an expert guidance

Discussion in 'Other Languages' started by p4w4n, Aug 30, 2012.

  1. p4w4n

    p4w4n Registered Member

    Joined:
    Oct 8, 2011
    Messages:
    56
    Likes Received:
    51
    Location:
    In Your Mind ;-)
    hi,
    I am coding a java based OCR from last two months.I have given it some basic functionality like segmenting the image, recognizing the character by comparing form the database and giving the result.

    however its not much progress but atleast there is something.But,now I have struck at some points and want some expert guidance to walk through it.I love coding and can code anything if you can guide me.


    About my knowledge of java: more than a fresher but a bit less than an experienced.

    BHW is full of experienced people and if someone can come forward and can provide a helping hand,i will be thankful to him/her.If someone can help me you can contact anyway you like(replying here,pm or adding me on skype)

    my skype id is p4w4n08

    thanks :)
     
  2. lisper

    lisper Newbie

    Joined:
    Aug 23, 2012
    Messages:
    44
    Likes Received:
    24
    Occupation:
    Lead developer of some German research project
    Location:
    Currently Brussels, Belgium
    Hey mate, left you a skype contact request (my username is lisssper). Cheers
     
  3. s0ap

    s0ap Executive VIP Jr. VIP Premium Member

    Joined:
    Sep 23, 2008
    Messages:
    230
    Likes Received:
    810
    Occupation:
    :] guess
    Location:
    Congo/DRC
    OCR is not a trivial problem to solve, I suggest you look through some of the existing open-source OCR libs if you are looking for somewhere to start.
     
  4. p4w4n

    p4w4n Registered Member

    Joined:
    Oct 8, 2011
    Messages:
    56
    Likes Received:
    51
    Location:
    In Your Mind ;-)
    hi,
    thanks for your response,but i am not at the starting stage.My OCR is already working but its very simple.We inputs a binarized image,it segments and recognize the characters.I am looking forward to take it to the next level by adding more functionality like converting an image to binary,filtering,ribboning,saperating the attached characters to correctly recognize them,etc.
    I saw the video presentation by chad in which he explained re captcha decoding and got few ideas.It will be better if someone experienced in this field can guide me.

    And i don't want to use open source APIs,but i want to create the whole software by my own concepts.
    thanks