OCR

566

Solutions

1K

Contributors

Optical character recognition (OCR) is the mechanical or electronic conversion of images of typed, handwritten or printed text into machine-encoded text. It is widely used as a form of data entry from printed paper data records, including passport documents, invoices, bank statements, computerized receipts, business cards, mail, printouts of static-data, or any suitable documentation. It is a common method of digitizing printed texts so that it can be electronically edited, searched, stored more compactly, displayed on-line, and used in machine processes such as machine translation, text-to-speech, key data and text mining. OCR is a field of research in pattern recognition, artificial intelligence and computer vision.

Share tech news, updates, or what's on your mind.

Sign up to Post

Dear Experts
We have project for 6 months where the data to be captured from the pdf document to captured and entered into excel and then imported into the application, it is found that the pdf documents in some sections are scanned some sections it is hand written, in some section it is table,  
1. looking for solution/software  please let us know the best solution to handle this work.
2.  also please suggest can we think of reading so that use some voice reorganization software if yes then please suggest the software
0
Starting with Angular 5
LVL 13
Starting with Angular 5

Learn the essential features and functions of the popular JavaScript framework for building mobile, desktop and web applications.

Hello and Good Evening Everyone,

        I am needing to scan a certificate and save it for editing purposes.  Specifically speaking, I have a name on a certificate that has been misspelled and in need of correction.  

        With respect to tools, I have an HP ENVY Photo 6255, a laptop running Windows 10, and Adobe Acrobat XI Pro.  If more information is needed, please feel free to let me know and it will be provided upon request.

         Thank you

         George
0
We are trying to integrate ABBYY SDK in our application.

ABBYY SDK support given javascript test code to convert image or non-searchable pdfs to Searchable PDFs. In the test code the file name and path were hardcoded. And the test code works good.

We modified the test code and give option to upload files. So now the upload file names are not hardcoded. When uploading the non-searchable pdfs in the modified code, it is NOT converting to seachable pdfs. But when uploading images, it is converting into searchable pdfs.

If anybody integrated ABBYY SDK in ColdFusion, please do reply.

Thanks for your assistance.
0
Here is our ColdFusion code for executing run.cmd programmatically:
<cfexecute timeout=1000
name = "C:\Windows\System32\cmd.exe"
arguments = "C:\ProgramData\ABBYY\SDK\12\""FineReader Engine""\Samples\Java\Hello\run.cmd"
outputFile = "C:\Temp\output.txt" >
</cfexecute>

Error Message:
The requested action did not complete in a timely manner. Timeout period expired without completion of C:\Windows\System32\cmd.exe.

When trying directly from command line, I still get the errors.

So in the command line, I entered up to the last folder cd C:\ProgramData\ABBYY\SDK\12\'FineReader Engine'\Samples\Java\Hello and run 'run.cmd' separately . So it runs correctly without any error.

So, how do I do the same in Coldfusion program ?
0
I need to read data from image , I am using ocr to read data but some images have background text due to which unable to get exact text.
For reference, attached below file "img.png" , from this I need only to read "+ 30s" as text
another image "onlyLive.png" from this only read "Live" as text

I tried to use imagemagick using "Live" hex code to black everything to black except "Live" but as seen in the image that other  background text is also white.
convert onlyLive.png  -fill black -fuzz 10% +opaque '#ECECEC' onlyLivee_black.png

I am using Python + openCv
img.png
onlyLive.png
0
We need to start digitizing some of our paper processes.

Basically, we'd like to print invoices and pack slips to PDF (or scan them), while automatically renaming the files based on PO number and/or order number (based on OCR?). Bonus if they automatically print after saving the PDF copy.

What can do this? Or is this even possible??

Thanks in advance!
0
Standalone open source or commerical software which uses Google OCR to be used.

Assume i bought and have the valid Google Vision API credentials and would like to know does any standalone open source or commercial client is available which is already integrated with Google Vision API which has other features as well.

Basically want to convert image to text....bulk conversion etc. via an application,

Thanks.
0
I'm trying to make a website compliant with the Americans with Disabilities Act. We want visually impaired people to be able to use OCR software more effectively with our college websites. Here is the site:
https://devallauth.dcccd.net/Pages/default.aspx
The OCR reads the page fine. Then when someone enters a search with its Google custom search, the site presents the results in an overlay div but the OCR does not read the search results in the overlay div. The OCR continues to read the original page elements. The overlay div gets added by the Google custom search code.
I then tried adding some code (in a test version of the site) to set the focus to the overlay div; but the OCR still didn't read the search results. Then I noticed that when I would hit the tab key or the enter key, the OCR would start reading the data on the overlay div so I added some JavaScript to force a tab keystroke; but that didn't work. I think that if I can just simulate a tab keystroke or an enter keystroke the right way then the OCR would start reading the overlay div. Here is the code I have for setting the focus on the overlay div wrapper and then forcing a keyboard enter press:
				visibleWrapper.setAttribute('tabindex', -1);	
				visibleWrapper.focus();
				keyUp = jQuery.Event("keyup", {keyCode: 13});
				jQuery(visibleWrapper).trigger(keyUp);

Open in new window

Maybe I should trigger the key event from the <body> or the window? Is there a better route? Any suggestions are appreciated. Thanks.
0
Trying to build a mini PC that is capable of doing OCR with a limited list of characters (17 total).  Currently working on OCR but QR code could be a option.
It will need to scan for input and save the data (along with location, time and a few other pieces of data) to a online database via wifi (not hard wired).
We have done some testing with a Pi but it does not have the processing power needed.  Results are 20%-44% accurate.
So I am looking for suggestions on a mini computer we could do testing on that could handle everything with 99.9% accuracy.
Device requirements:
1) small 4"x3" ish size
2) On board WiFi
3) Attachable mini camera for data scaning
4) Attachable mini touchscreen (4"x3")
5) On board GPS
We are looking at LattePanda or odroid xu4.  But I need some feedback on if either of them will work or if there are other options.
0
Is it possible to program the Raspberry PI camera to do OCR?
Need it to recognize a list of characters and when seen, write the info to a file.  
Need the following info with each entry;
Captured data
Date and time (down to the second)
Location (can be GPS or user entry)

And once a day (or at user request) upload data to a online database.
0
Exploring ASP.NET Core: Fundamentals
LVL 13
Exploring ASP.NET Core: Fundamentals

Learn to build web apps and services, IoT apps, and mobile backends by covering the fundamentals of ASP.NET Core and  exploring the core foundations for app libraries.

i included opencv and tesseract ocr in visual studio
#include<opencv2\core\core.hpp>
#include<opencv2\highgui\highgui.hpp>
#include "opencv2/imgproc/imgproc.hpp"
#include<baseapi.h>
#include<allheaders.h>
#include<iostream>
#include <vector>
#include <fstream>
#define _CRT_SECURE_NO_WARNINGS
using namespace cv;
using namespace std;
tesseract::TessBaseAPI ocr;

int main()
{
   Mat input = imread("C:\\eurotext.tif",1);
   cvtColor( input, input, CV_BGR2GRAY );

  ocr.Init(NULL, "eng", tesseract::OEM_TESSERACT_ONLY);
 
  ocr.SetPageSegMode(tesseract::PSM_SINGLE_BLOCK);
  ocr.SetImage(input.data, input.cols, input.rows, 1, input.step);
  char* text = ocr.GetUTF8Text();
  cout << "Text:" << endl;
  cout << text << endl;
  cout << "Confidence: " << ocr.MeanTextConf() << endl << endl;
  

}

Open in new window

the build was succeeded but when running

erreur_run.PNG
and


erreur_run2.PNG
0
I have some python code that takes in an image of an A4 printed letter, then draws bounding boxes around each character.

I want to know how to save each bounding box as an image, so essentially it's taking every character it detects and saving it. Preferable as a .png resized to 20x20


Here is my code:
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
from scipy.misc import imread,imresize
from skimage.segmentation import clear_border
from skimage.morphology import label
from skimage.measure import regionprops


image = imread('./ocr/testing/adobe.png',1)

#apply threshold in order to make the image binary
bw = image < 120

# remove artifacts connected to image border
cleared = bw.copy()
clear_border(cleared)

# label image regions
label_image = label(cleared,neighbors=8)
borders = np.logical_xor(bw, cleared)
label_image[borders] = -1

print label_image.max()

fig, ax = plt.subplots(ncols=1, nrows=1, figsize=(6, 6))
ax.imshow(bw, cmap='jet')



for region in regionprops(label_image, ['Area', 'BoundingBox']):
    # skip small images
    if region['Area'] > 50:

        # draw rectangle around segmented characters
        minr, minc, maxr, maxc = region['BoundingBox']
        rect = mpatches.Rectangle((minc, minr), maxc - minc, maxr - minr,
                              fill=False, edgecolor='red', linewidth=2)
        ax.add_patch(rect)

plt.show()

Open in new window


I've tried a few solutions such as adding the following in my for loop

image_patch = img[minc:maxc, minr:maxr]  # get region of interest (slice)
plt.imsave("filename.png", image_patch)

But that doesn't obtain the right boundaries for some reason.
The hard part is already done, (Drawing the boundries around the characters) I literally just want to save each boundry as an image now but I have no idea how.
0

OCR

566

Solutions

1K

Contributors

Optical character recognition (OCR) is the mechanical or electronic conversion of images of typed, handwritten or printed text into machine-encoded text. It is widely used as a form of data entry from printed paper data records, including passport documents, invoices, bank statements, computerized receipts, business cards, mail, printouts of static-data, or any suitable documentation. It is a common method of digitizing printed texts so that it can be electronically edited, searched, stored more compactly, displayed on-line, and used in machine processes such as machine translation, text-to-speech, key data and text mining. OCR is a field of research in pattern recognition, artificial intelligence and computer vision.

Top Experts In
OCR
<
Monthly
>