Questions tagged [ocr]
Tag for questions on Optical Character Recognition (OCR), including the Mathematica function TextRecognize[].
62
questions
5
votes
1
answer
199
views
Is it possible to straighten lines of text in an image?
I have a great many images of text that I have created to obtain texts and abstracts from older literature (copyrights expired) for which pdf files are not available. Because of the shear number, I ...
- 1,943
3
votes
2
answers
205
views
Keys in the vicinity
What I want to do is to recognize keys in the image and create a list of keys around every key that fall within a pentagonal (or similar) region. These are the ones that can be accidentally pressed ...
- 56.2k
0
votes
0
answers
366
views
Extract equation as text from a screenshot
Is it possible to snip an equation from pc screen e.g. with windows snipping tool from edge or acrobat and paste it to wolfram math input online or Mathematica, like copy text from picture with ...
- 1
12
votes
4
answers
2k
views
Text recognition - extracting table of text from image
I want to extract table from the image bellow as a list of strings. I tried the following but it does not work.
...
- 21.3k
2
votes
1
answer
212
views
TextRecognize has a memory leak?
This code causes Mathematica to slowly accumulate memory until it hard crashes my operating system. It does this by overwriting OS memory (windows start going black, graphics drivers start crashing ...
- 2,501
1
vote
0
answers
78
views
Recognize text in image
I have the following image and I want to extract the text on the axes. I used the following code:
...
- 3,015
2
votes
1
answer
95
views
Does anyone know how to fix the issue not having the hydrogen atoms accounted for when converting to a .mol file?
Hi I am using moleculeRecognize function to upload structures from images and I am attempting to convert the structures in .mol files. However every time I convert to .mol files the hydrogen atoms in ...
0
votes
0
answers
101
views
Semantic Image Segment of grayscale Text Image
How to extract text and pictures from an image file
Consider this grayscale image, how to segment the handwriting part without using Color Information。
Q0:BoundingBox of different patterns:
text, &...
- 8,629
6
votes
1
answer
2k
views
How to import equations from a pdf
Here is a pdf I am trying to import: https://i.sstatic.net/J2e0z.png
Its a photo so that I can upload it here easily. I am trying to extract the formulas from this pdf but to no avail. Plaintext ...
- 657
8
votes
0
answers
5k
views
convert image of mathematical form to mathematical form (OCR)
I wish to convert images of mathematical form to mathematical form(and not the opposite).
I've found this tool which does a great job but I wondered if it's possible to enter an image directly to ...
- 181
3
votes
1
answer
91
views
Extracting information and adding more details to an imported image of a plot
I have the following image that has been created using another program.
Is there a way for Mathematica to load this image, "understand" the limits of the frame (horizontal axis between -1 ...
- 8,820
4
votes
0
answers
103
views
Why TextRecognize reads data organized in grid by column and not by row?
Why TextRecognize reads the text by column and not by line in the following scenarios?
The lines are perfect, the font is perfect, image quality is perfect so I do ...
- 21.3k
7
votes
1
answer
210
views
Alphabet recognition
I have a picture with some writings in it. It is written by computer in to me unknown alphabet.
Is there a way how to use Mathematica to tell me what alphabet was used or what language?
Here are two ...
- 21.3k
14
votes
2
answers
423
views
What's the principle behind the new MoleculeRecognize function?
I played a bit with the new MoleculeRecognize function implemented in the newly released WM 12.1:
which simply recognizes a molecule in image and returns it as a Molecule object.
...
- 265
6
votes
1
answer
162
views
How to TextRecognize sparse grid of tabular data?
I cannot give the actual image (contains private information) but the results of
...
- 43.1k
14
votes
3
answers
604
views
Importing a grid of numbers from an image (sudoku like)
Can anyone see a way to import a grid of numbers from
http://www.mit.edu/~puzzle/2019/puzzle/lantern_festival.html
into Mathematica? TextRecognize doesn't seem ...
- 8,041
3
votes
0
answers
329
views
Improving the accuracy of the bounding box detection of TextRecognize
My problem concerns the text position detection in a scan. My goal is to find the bounding boxes of the text.
...
- 8,629
2
votes
0
answers
78
views
Help find rectangles with numbers [closed]
I have this picture
1)
Result must be like that
2)
. But I can achieve it only if have good numbers with picture like that 3)
With first image I have result:
4)
I can't recognize numbers with ...
- 29
3
votes
2
answers
105
views
Is it possible or how to extract message string from binarized list?
Given message copied from Silvia's profile page, a binarized list could be found bellow.
...
- 2,469
1
vote
0
answers
225
views
18
votes
2
answers
1k
views
How to TextRecognize a screenshot of code?
Are there any specific tricks or options to help TextRecognize work on a screenshot of an Input Cell or code in general?
For example, here's a screenshot that ...
- 31.7k
3
votes
1
answer
401
views
Extract names from a document [closed]
If I have a document, any document, it can be a book, an article, etc, how could I extract people's names from there?
For example, if the input is an article, the output of the function would be the ...
- 101
1
vote
0
answers
165
views
TextRecognize giving corrupted results on some images - Bug CASE 4075220
Maybe the question sounds - is this a Mathematica error or what do I understand wrongly?
Im having troubles to learn using Textrecognize because Im getting repeatedly errors which when I analyse ...
- 81
1
vote
4
answers
147
views
setting size of images which are result of TextRecognize
Im learning Mathematica and the Wolfram language for shot time by myself. Its a pain for me that many settings are somehow hidden. Now I spent hours to find solution for something I already did with ...
- 81
1
vote
0
answers
245
views
can I train the Textrecognize (or the Tesseract behind) for real typewriter letters?
Can I improve result of the TextRecognize by training the machine which is behind? Id like to work with a lot of scanned texts from several (real) typewriters. It seems to me that TextRecognize gives ...
- 81
2
votes
0
answers
43
views
cannot recognize accented characters using TextRecognize
Im unable to force TextRecognize understanding Czech characters like "ě, š, č,..." . Adding " .. ; Language -> "Czech" " gives me exactly the same bad result as with "English" or "German". My setup - ...
- 81
2
votes
1
answer
242
views
Failed to load TesseractTools in Mathematica 11 running on Raspberry Pi
Version where this occurred:
Mathematica:
Version - 11.0.1.0
Platform - Linux ARM (32-bit)
Raspbian:
Version - September 2017
Release Date - 2017-09-07
Kernel Version - 4.9
Attempting to do OCR ...
- 21
91
votes
1
answer
14k
views
Crack CAPTCHA using deep learning
Deep convolutional neural networks are very good at computer vision related tasks. Optical Character Recognition (OCR) is one important branch of computer vision. In fact, the convolution neural ...
- 27.7k
4
votes
0
answers
246
views
Recognize text in an image
How can I use TextRecognize to recognize text in an following image?
- 8,998
2
votes
1
answer
639
views
How to import Robinhood screenshots?
I use an iPhone app called Robinhood to trade stocks and I wanted to play with the portfolio with Mathematica's finance tools. So I took some screenshots of the app and I'm trying to import the ...
- 31.7k
4
votes
2
answers
472
views
How to improve the recognition quality when TextRecognize work on single character
Bug introduced in 11.0 and persisting through 11.3
From this answer, I doubt the capability to work on single character. So I give some test to verify this possibility. You can get my test ...
- 27k
4
votes
1
answer
661
views
How can I separate a scanned text to its letters?
I am looking for a simple way to recognize musical Unicode text (written in byzantine musical notation). My idea is to compare each musical symbol with the scanned text and find all the coordinates(...
- 1,047
9
votes
1
answer
390
views
Providing an image or PDF file as an input to the Handwritten Math Recognition Engine
On Windows 7 and higher Mathematica supports Handwritten Math Recognition feature (it is available under the menu Window — Handwriting Input). The interface allows to use touchscreen to draw ...
- 7,303
7
votes
3
answers
4k
views
Crack it if you can? But in the best way
From the Wolfram Community posted by Helen:
A little while ago I was asked to solve this "safe cracker" puzzle, a sweet example of a coffee table puzzle. The basic gist of this puzzle is ...
3
votes
1
answer
3k
views
How do I remove text from an image?
I want to remove "the worst of times" from this image. How do I do that? I don't have a preference to how it's done.
- 31
8
votes
2
answers
456
views
problem to recognize a table through a png image
This is I think an already asked question but I at the margin there are some new points
I have this file found on internet
and now I want to recognize the table with the following commands
...
- 4,612
4
votes
1
answer
270
views
Recognizing characters with accent marks
I have written code to recognize some words, but I get errors in the recognition of some characters with accent marks. Is there any solution?
...
- 9,263
37
votes
2
answers
2k
views
Handwriting recognition with Mathematica
I am trying to teach Mathematica to read my handwriting. Since I don't want to ruin my reputation by showing my own handwriting, I am going to use a font called blackjack.
Lets say this is a ...
- 16k
5
votes
0
answers
144
views
Geographic text recognition [closed]
I would like to process an image from this Wikipedia page to get the structured data out
Like so
<| "New York" -> 28, ... |>
Not sure where to start.
- 31.7k
5
votes
1
answer
206
views
Finding position of text returned with TextRecognize
I am trying to extract data from images (using some of the methods presented in [1524]), and would like to have a way to selectively cover/remove text from axes and legends.
...
- 1,543
11
votes
2
answers
2k
views
Recognizing integers in an image
This is the picture I want Mathematica to read
I want Mathematica to recognize these numbers and put them in a list. I know that there is a function TextRecognize, ...
- 183
0
votes
0
answers
139
views
Recognizing text and Mathematica special characters when copying expressions from a PDF
I could not find something relevant.
Last days I am reading Leonid Shifrin's masterpiece but I cannot copy-paste either from the pdf or from the electronic version.
Consider the function ...
- 4,874
18
votes
1
answer
2k
views
Can I OCR Mathematica code on an image?
There's no doubt that one should always post the Mathematica code text rather than its screenshot when asking questions in this site, but every time I saw someone posting a screenshot, I can't help ...
- 67.7k
2
votes
0
answers
549
views
How to do text recognition in a language that doesn't use the roman alphabet [closed]
I am trying to reconize a single letter or character from a non-roman character set by edge detection. I want to extract single characters from a text image. When I identify that letter or character I ...
- 41
2
votes
2
answers
427
views
Extracting coordinates from a ListLinePlot
I used an iterative method to resolve equations, then i plotted the results using ListLinePlot.
Unfortunately, now I need to use some of the data that was plot.
I know the X-coordinate, and need to ...
- 21
13
votes
1
answer
635
views
Why does cropping an image improve TextRecognize so much?
I am trying to use the TextRecognize function to extract data from certain screenshots. This is already a cropped version.
Using TextRecognize on this yields ...
- 407
1
vote
0
answers
414
views
How can I detect certain letters by shape in an image? [closed]
I have a website where people can post Flipbook animations, called Flipnotes.
Unfortunately, most of the Popular flipnotes are in the following categories:
MV (Music Video)
AV (Audio Video)
AMV (...
- 325
0
votes
1
answer
408
views
Character segmentation in poor quality grayscale
Given grayscale lines from a receipt like this:
,
in which parts of the letters sometimes appear almost as light as the background, my goal is to determine the $x$-positions of the centres of the ...
- 680
8
votes
1
answer
549
views
Detect implicit grid in image with monospaced characters
I'm trying to detect the monospaced-grid in a possibly slightly deformed image of a receipt. Example input (full size here)
My idea is to obtain the centroids or bounding boxes of all components and ...
- 680
8
votes
0
answers
198
views
Ways to overcome failure of TextRecognize on relatively simple price tag?
I would like to perform OCR on this sample image.
TextRecognize[Import["RedBox.jpg"], Language -> "German"]
returns
...
- 285