I've got a large number of 3- and 6-column journal and newspaper pages that I want to OCR. I want to automate recognition of columns.
I've used tesseract (see a previous question) and Google Cloud Document AI (using the R package daiR) without great success.
These programs read the text very well, but do not do a good job of recognizing the column format of pages.
Here's a couple of examples from daiR:
Obviously these are complex images with some double columns and some tables inside columns. What I want is for the OCR to try to look for 6 columns.
I get good results if I preprocess images (for instance by cropping them into single columns or adding vertical lines), but I haven't found an efficient way to do this in large batches. Is there a way of preprocessing images or telling OCR programs to look for a given number of columns?
Related
[![enter image description here][4]][4][![enter image description here][5]][5]I have a PDF that has tabular data that runs over 50+ pages, i want to extract this table into an excel file using Automation Anywhere. (i am using community version of AA 11.3). I watched videos of the PDF integration command but haven't had any success trying this for tabular data.
Requesting assistance.
Thanks.
I am afraid that your case will be quite challenging... and the main reason for that are the values that contains multiple lines. You can still achieve what you need, and with good performance, but the code itself will not be pretty. You will also be facing challanges with Automation Anywhere, since it does not really provide the right tools to do such a thing and you may need to resort to scripting (VBScripts) or Metabots.
Solution 1
This one will try to use purely text extraction and Regular expressions. Mainly standard functionality, nothing too "dirty".
First you need to realise how do the exported data look like. You can see that you can export to Plain or Structured.
The Plain one is not useful at all as the data is all over the place, without any clear pattern.
The Structured one is much better as the data structure resembles the data from the original document. From looking at the data you can make these observations:
Each row contains 5 columns
All columns are always filled (at least in the visible sample set)
The last two columns can serve as a pattern "anchor" (identifier), because they contain a clear pattern (a number followed by minimum of two spaces followed by a dollar sign and another number)
Rows with data are separated by a blank row
The text columns may contain a multiline value, which will duplicate the rows (this one thing makes it especially tricky)
First wou need to ensure that the Structured data contain only the table, nothing else. You can probably use the Before-After string command for that.
Then you need to check if you can reliably identify the character width of every column. You can try this for yourself if you copy the text into Excel, use the Text to Columns with the Fixed Width option and try to play around with the sliders
The you need to try to find a way how to reliably identify each row and prepare it for the Split command in AA. For that you need to have a delimiter. But since each data row can actually consists of multiple text rows, you need to create a delimiter of your own. I used the Replace function with Regular Expression option and replace a specific pattern for a delimiter (pipe). See here.
Now that you have added a custom delimiter, you can use the Split command to add each row into a list and loop through it.
Because each data row may consists of several rows, you will need to use Split again, this time use the [ENTER] as delimiter. Now you need to loop through each of the text line of a single data line and use the Substring function to extract data based on column width and concatenate them to a single value that you store somewhere else.
All in all, a painful process.
Solution 2
This may not be applicable, but it's worth a try - open the PDF in Microsoft Word. It will give you a warning, ignore it. Word will attempt to open the document and, if you're lucky, it will recognise your table as a table. If it works, it will make the data extraction much easier an you will be able to use Macros/VBA or even simple Copy&Paste. I tried it on a random PDF of my own and it works quite well.
I am working on invoice parser which extracts data from invoices in pdf or image format.It works on simple pdf with non tabular data but gives lots of output data to process with pdf which contains tables.I am not able to get a working generic solution for this.I have tried the following libraries
Invoice2Data : It is based on templates.It has given fairly good results in json format till now.But Template creation for complex pdfs containing dynamic table is complex.
Tabula : Table extraction is based on coordinates of the table to be extracted.If the data in the table increases the table length increases and hence the coordinates changes.So in this case it gives wrong results.
Pdftotext : It converts any pdfs to text but with the format that needs lots of parsing which we do not want.
Aws_Textract and Elis_Rossum_Ai : Gives all the data in json format.But if the table column contains multiple line then json parsing becomes difficult.Even the json given is huge in size to parse.
Tesseract : Same as pdftotext.Complex pdfs are not parseable.
Other than all this or with combination of the above libraries has anyone been able to parse complex pdf data please help.
I am working on a similar business problem. since invoices don't have fixed format so you can't directly use any text parsing method.
To solve this problem you have to use Computer Vision (Deep Learning) for field detection and Pytesseract OCR for converting image into text. For better understanding here are the steps:
Convert invoices to image and annotate the images with fields like address, Amount etc using tools like labelImg. (For better results use different types of 500-1000 invoices)
After Generating XML files train any object detection model like YOLO or TF object detection API.
The model will detect the fields and gives you coordinates of Region Of Interest(ROI). like
Apply Pytessract OCR on the ROI coordinates. Click Here
Finally, use regex to validate the text in the extracted field and perform any manipulation/transformation that is necessary. At last store data to CSV OR Database.
Hope my answer helps you! Upvote answer so it reaches to maximum people.
I often work with scanned papers. The papers contain tables (similar to Excel tables) which I need to type into the computer manually. To make the task worse the tables can be of different number of columns. Manually entering them into Excel is mundane to say the least.
I thought I can save myself a week of work if I can put a program to OCR it. Would it be possible to detect headers text areas with the OpenCV and OCR the text behind the detected image coordinates.
Can I achieve this with the help of OpenCV or do I need entirely different approach?
Edit: Example table is really just a standard table similar to what you can see in Excel and other spread-sheet applications, see below.
This question seems a little old but i was also working on a similar problem and got my own solution which i am explaining here.
For reading text using any OCR engine there are many challanges in getting good accuracy which includes following main cases:
Presence of noise due to poor image quality / unwanted elements/blobs in the background region. This will require some pre-processing like noise removal which can be easily done using gaussian filter or normal median filter methods. These are also available in opencv.
Wrong orientation of image: Because of wrong orientation OCR engine fails to segment the lines and words in image correctly which gives the worst accuracy.
Presence of lines: While doing word or line segmentation OCR engine sometimes also tries to merge the words and lines together and thus processing wrong content and hence giving wrong results.
There are other issues also but these are the basic ones.
In this case i think the scan image quality is quite good and simple and following steps can be used solve the problem.
Simple image binarization will remove the background content leaving only necessary content as shown here.
Now we have to remove lines which in this case is tabular grid. This can also be identified using connected components and removing the large connected components. So our final image that is needed to be fed to OCR engine will look like this.
For OCR we can use Tesseract Open Source OCR Engine. I got following results from OCR:
Caption title
header! header2 header3
row1cell1 row1cell2 row1cell3
row2cell1 row2cell2 row2cell3
As we can see here that result is quite accurate but there are some issues like
header! which should be header1, this is because OCR engine misunderstood ! with 1. This problem can be solved by further processing the result using Regex based operations.
After post processing the OCR result it can be parsed to read the row and column values.
Also here in this case to classify the sheet title, heading and normal cell values their font information can be used.
I want to segment image of various forms which are handwritten, into separate sections and words. I don't want character recognition; just given an image I want to segment it into all the different handwritten words it contains and if it contains multiple sections (separated by lines), then a separation of those. What are the specific vision algorithms for this? Can I use any open code libraries for this. Language of the code is not a concern.
You will need a classifier combined with a parts based model. See this publication- A Shared Parts Model for Document Image Recognition - for more details.
Bear in mind, this is an active field of research.
In an experimental project I am playing with I want to be able to look at textual data and detect whether it contains data in a tabular format. Of course there are a lot of cases that could look like tabular data, so I was wondering what sort of algorithm I'd need to research to look for common features.
My first thought was to write a long switch/case statement that checked for data seperated by tabs, and then another case for data separated by pipe symbols and then yet another case for data separated in another way etc etc. Now of course I realize that I would have to come up with a list of different things to detect - but I wondered if there was a more intelligent way of detecting these features than doing a relatively slow search for each type.
I realize this question isn't especially eloquently put so I hope it makes some sense!
Any ideas?
(no idea how to tag this either - so help there is welcomed!)
The only reliable scheme would be to use machine-learning. You could, for example, train a perceptron classifier on a stack of examples of tabular and non-tabular materials.
A mixed solution might be appropriate, i.e. one whereby you handled the most common/obvious cases with simple heuristics (handled in "switch-like" manner) as you suggested, and to leave the harder cases, for automated-learning and other types of classifier-logic.
This assumes that you do not already have a defined types stored in the TSV.
A TSV file is typically
[Value1]\t[Value..N]\n
My suggestion would be to:
Count up all the tabs
Count up all of new lines
Count the total tabs in the first row
Divide the total number of tabs by the tabs in the first row
With the result of 4, if you get a remainder of 0 then you have a candidate of TSV files. From there you may either want to do the following things:
You can continue reading the data and ignoring the error of lines with less or more than the predicted tabs per line
You can scan each line before reading to make sure all are consistent
You can read up to the line that does not fit the format and then throw an error
Once you have a good prediction of the amount of tab separated values you can use a regular expression to parse out the values [as a group].