LabVIEW

cancel
Showing results for 
Search instead for 
Did you mean: 

please help me out in designing a sub vi for line segmentation in OCR (optical character recognition)

Here is the brief discription of the sub vi. there is a sub vi in red colour please help me in getting it. 

The procedure is as follows:

1. Input is a two dimensional array

2. scan the array horrizontally.

3. remember the first on pixel as y1 and continue scanning  

4. remember the value of the next pixel before an off pixel as y2 

5clip the array from y1 to y2 

and the output is given to the further circuit

 

Screenshot (48).png

Message 1 of 8
(3,828 Views)

HI

 

Can you clearly explain the algorithm which you want execute in SubVI.

 

Best Regards,

Edgar Shadyan.

 

0 Kudos
Message 2 of 8
(3,794 Views)

So you are showing is a screenshot of an acrobat document containing a picture of a horible blick diagram. Why not eliminate the confusion and attach the actual VI instead? Also include typical input array data. Why not attach the pdf document? Who wrote it?

 

Just looking at that code picture, It seems to be written by someone who does not understand LabVIEW. I would delete all code and start from scratch, hopefully after doing some basic LabVIEW tutorials.

 

Here are some problems, there are probably many more once we have the full code.:

  • The faultiy use of a WHILE loop as a FOR loop substitute  (autoindexing on an array and terminating one ieration too late.
  • Comparison with zero is ill advised on DBL datatype, especially if it is real acquired data.
  • All the code remembers is the data of the last iteration. Isn't there more to it? Shouldn't there be e.g. a shift register somewhere?
  • The code in the TRUE case is probably more interesting, but we cannot see it.
  • The picture scale is not 1:1 pixelwise, and it is impossible to tell 1D from 2D arrays.
  • Duplicate tunnels. Typicaly you want to branch the wire inside the structure.
  • What does the red subVI do? Please attach that too.
  • The input seems to the integer, why are you converting to DBL?
  • Why are all outputs of the wrong datatype?
  • Why does the "size(s)" wire go right-to-left?
0 Kudos
Message 3 of 8
(3,760 Views)

Sir ,

                  Thank you for your reply  Please find the attachment of the project I have choosen for detailed explanation 

 I would be glad if u reply as early as possible.

 

With regards ,

Sowmya

0 Kudos
Message 4 of 8
(3,684 Views)

Sir ,

              Thank you for your reply  Please find the attachment of the project I have choosen for detailed explanation 

              I am very new to lab view software and persuing final year project in it .I took it from a journel and trying to solve it and i am not really aware of the exact structure But I will give a brief Over view of my project.

Steps Involved:

1.Take a Scanned Image containing text .

2.Resize the image into required size and convert into binary image by thresholding

3.Clip each line in the image 

4.clip each word in the image 

5.then clip each Word into characters

6.Store all the required details of each character (A-Z)and(a-z) like Number of On pixels and OFF in them ,ASCII value in the pre defined library .

7. Compare Each character properties with the store ones and determine the character .

8.This text which is converted into machine readable format which in text document  undergoes speech synthesis and then the final out put is speech (here for text to speech conversion we should have TTS synthesiser or Any Speech SDK in the system.

              Please reply as early as possible.Any small clue will be a great boon to us

 

 

With Regards,

Sowmya

0 Kudos
Message 5 of 8
(3,678 Views)

We won't do your homework for you.  But if you show us some code like you're actually trying, we would certainly be able to help.  Not a picture.  A vi.

Bill
CLD
(Mid-Level minion.)
My support system ensures that I don't look totally incompetent.
Proud to say that I've progressed beyond knowing just enough to be dangerous. I now know enough to know that I have no clue about anything at all.
Humble author of the CLAD Nugget.
0 Kudos
Message 6 of 8
(3,658 Views)

Instad of attaching an article, you could just link to it.

 

 

I have read the article and there is really no much useful information. All I can say that if I would have been reviewer, I would have rejected it immediately. None of the LabVIEW code pictures show any useful information, except to tell us that the programmer has virtually no working knowledge or experience with LabVIEW. While they published this in 2014, they are using a LabVIEW (7.1) version that was outdated by almost 10 years at the time of publication. (Nothing wrong with that per se, though).

 

So what do you want to reproduce from the article? Maybe a better idea would be to contact the original authors. Have you tried?

 

0 Kudos
Message 7 of 8
(3,634 Views)

Hi, can you found the solution please, I'm looking for the same SubVi. 

 

With regards, 

Houda. 


@sow123 wrote:

Sir ,

              Thank you for your reply  Please find the attachment of the project I have choosen for detailed explanation 

              I am very new to lab view software and persuing final year project in it .I took it from a journel and trying to solve it and i am not really aware of the exact structure But I will give a brief Over view of my project.

Steps Involved:

1.Take a Scanned Image containing text .

2.Resize the image into required size and convert into binary image by thresholding

3.Clip each line in the image 

4.clip each word in the image 

5.then clip each Word into characters

6.Store all the required details of each character (A-Z)and(a-z) like Number of On pixels and OFF in them ,ASCII value in the pre defined library .

7. Compare Each character properties with the store ones and determine the character .

8.This text which is converted into machine readable format which in text document  undergoes speech synthesis and then the final out put is speech (here for text to speech conversion we should have TTS synthesiser or Any Speech SDK in the system.

              Please reply as early as possible.Any small clue will be a great boon to us

 

 

With Regards,

Sowmya



@sow123 wrote:

Sir ,

              Thank you for your reply  Please find the attachment of the project I have choosen for detailed explanation 

              I am very new to lab view software and persuing final year project in it .I took it from a journel and trying to solve it and i am not really aware of the exact structure But I will give a brief Over view of my project.

Steps Involved:

1.Take a Scanned Image containing text .

2.Resize the image into required size and convert into binary image by thresholding

3.Clip each line in the image 

4.clip each word in the image 

5.then clip each Word into characters

6.Store all the required details of each character (A-Z)and(a-z) like Number of On pixels and OFF in them ,ASCII value in the pre defined library .

7. Compare Each character properties with the store ones and determine the character .

8.This text which is converted into machine readable format which in text document  undergoes speech synthesis and then the final out put is speech (here for text to speech conversion we should have TTS synthesiser or Any Speech SDK in the system.

              Please reply as early as possible.Any small clue will be a great boon to us

 

 

With Regards,

Sowmya


 

0 Kudos
Message 8 of 8
(1,820 Views)