CVISION Technologies

Question:Hi, I’m constantly scanning in more and more articles into our databases. However, our back logs are not text searchable which is hard for those looking for information. Do you know what the best text OCR software is?

Answer: OCR software is generally used for back logs, making this a very essential product for the office. In order to see which best text OCR software is best for your office setting, I suggest you download a couple of OCR demos. The demos allow you to play with the product to see which one is the best fit. CVISION is offering a free 30 day trial of their product that you can be downloaded at the link below. See which product is the best for backlog.

http://www.cvisiontech.com/download_main.html

Question: I work in a human resources department, and it takes a lot of time to handle form processing, especially when new workers come on-board. How can I help my HR department speed up forms processing?

Answer: A forms processing solution is available with our optical character recognition tool (OCR). Forms processing can be tedious and manual inputting usually comes with mistakes. Our OCR tool will eliminate large chunks of inputting time, and do it accurately for you, saving money and increasing efficiency. Check out our link to OCR products and make forms processing an easier task. 

www.cvisiontech.com/download_main.html

Question: I have been testing PdfCompressor with OCR, I OCR’d a RAW TIFF files and the results were good on the super accurate (not on the balanced). My colleague claims that you obtain better results when you OCR scanned documents with lower resolutions, I never heard of this. What can you tell me?

Answer: The lower DPI statement is not correct. The ideal DPI is 300 for good OCR accuracy. Also if the input file is a PDF try running the file in raster mode to see if you get better results.

If you would like to retest PdfCompressor, I have attached the link for the free trial below:

www.cvisiontech.com/download_main.html

Question: We are scanning our paper with the output file being a TIFF, we would like to take the TIFF documents and convert them to searchable PDFs. Do you provide a solution to convert scanned documents into searchable PDF files?

Answer: Yes, we have two products that will convert your captured documents into searchable PDFs.
There is PdfCompressor, which in addition to creating searchable PDFs with OCR, also compresses scanned documents to a fraction of their size. In addition to PdfCompressor, we have Maestro which produces searchable PDFs with our super-accurate OCR.

We offer a free trial of both of these software products; I have attached the link below:

www.cvisiontech.com/download_main.html

Question: Can I OCR my files and guarantee that each document has been OCRed correctly with a given confidence, e.g., 99.5% ?

Answer: Yes, sort of. OCR verificarion is really a semi-automated process. What can be expected from the OCR system is to i. correctly determine the reliability we have in each OCR ASCII assignment, and ii. flagging for human intervention all words in the document below the pre-assigned confidence level.

Getting an accurate OCR confidence measure is non-trivial. Most OCR packages return a confidence assignment to each word, but that measure is often unreliable. So it is important to run your files on a system with a somewhat reliable confidence measure. These measures often consider attributes that include “is this word returned by the OCR engine in the language dictionary?” and “does this word have a reasonable intra-document frequency?”. There are many other indicators that can be useful in obtaining an accurate confidence measure for each word.

At some point, any such OCR verification system needs to be semi-automated, with a human in the loop. Say that a document requires a recognition rate of 99.5%, then this recognition rate is with respect to human recognition, not machine recognition. For example, if there was a paragraph in the document that was completely unreadable to any human, e.g., a third generation scan, using some very small fonts in the text, then the words in this paragraph should not be counted us unrecognized since this text is beyond readability, and in an information theoretic sense this information is already lost, no fault of the OCR system. On the other hand, if a paragraph is small font and very difficult to read but still clearly human readable, but the OCR engine does not pick it up then these words must be counted as unrecognized.

To guarantee a certain minmum OCR accuracy, then, all document pages below the minimum OCR recognition threshold must be shown to a human to determine if these words are human readable. If so, then the human can manually correct any words with incorrect text assignments. The task of any OCR verification system is to semi-automate the recognition process such that, with minimal human intervention, a certain minimal OCR confidence level can be established for a collection of documents.

Question: I was online looking for some OCR solutions. I found a couple of different OCR software solutions. What is the difference between other OCR engines, and the OCR in PdfCompressor?

Answer: CVISION uses the latest OCR techniques while also discovering OCR methods of our own through our ongoing OCR research. CVISION’s PDF OCR engine provides remarkable speed and accuracy that one must experience to believe. Our PDF OCR and conversion creates a seamless pipeline for transitioning your existing documents and images into a more compact, more easily searchable format. With our watched folder and batch modes the process is practically work free.

The OCR engine within PdfCompressor also:
• Automates the OCR process with Watch Folders
• OCRs large volumes with Batch OCR
• Locates a single word with an entire multi-page document
• Takes less time rewriting text with super-accurate OCR
• Document Compression combined with OCR accuracy
• OCRs supported in 60+ languages
• Processes large document volumes fast
• Superior OCR results for color documents
• Perceptually lossless, web-optimized, searchable PDFs
• Multi-directional OCR

To try out the OCR click below:
http://www.cvisiontech.com/download_main.html

Question: Do you offer batch OCR process capabilities. I want to OCR large volumes of scanned files.

Answer: Yes, we do offer batch OCR capabilities. Most of our corporate clients are utilizing our batch OCR mode. To further automate the OCR & compression processes, PdfCompressor also offers watch folder capabilities.

I have attached a link to download a free trial of PdfCompressor with OCR.

http://www.cvisiontech.com/download_main.html

Question: Do you offer a free trial for your Optical Character Recognition Software? If so, can you forward me the link?

Answer: Yes, we do offer a free trial for our optical character recognition software. It is a 30 day trial. Our OCR is available in 60+ languages. The link to download is below:

http://www.cvisiontech.com/pdfpro40_download.html

There is a general tradeoff between OCR speed and accuracy. The accuracy is generally a function of the OCR engine speed. It is usually possible to obtain greater OCR accuracy by running the engine longer, or by deploying more OCR engines. The problem, however, becomes one of diminishing returns.

Let’s say the OCR engine has to run twice as long to diminish the remaining error rate by half. Say, for example, there’s an error rate of 2% when the OCR engine is run in normal mode, which might have a processing speed of 3 seconds per page. There might also be an accurate mode, with an error rate of 1% and a processing speed of 6 seconds per page. Let’s also assume there is a super-accurate mode with an error rate of 0.5 % and a processing speed of 12 seconds per page. This might correspond in some systems to the number of OCR engines that are run.

In any event, even assuming that there are as many as 10 OCR engines, or super-accurate modes, for most companies there is a point of diminishing returns, that is, a point at which it is not worth slowing down the OCR processing rate any more, even if the tradeoff is greater accuracy.

So what often needs to be established, sometimes empirically through trial and error, is what degree of accuracy is required for a given Company? How accurate is accurate enough? What processing rate is acceptable within a given workflow?

Sometimes greater OCR accuracy can be achieved without increasing processing time. This often involves either some form learning or optimizing for a given application domain.

Question: What Font/Size would you recommend to increase the accuracy of the OCR’ing? Will all upper case help or not?

Answer: The best font to use is “Courier” or “Times New Roman” and the size should be between 9 and 20.

If you are interested in evaluating PdfCompressor for free, click the link below:

http://www.cvisiontech.com/pdfpro40_download.html