View Image

The Fuzzy Mining Tool (FMT) is based on Internet technologies, and allows you to search for misspelled words in a document and return the phrase, sentence, or paragraph where the misspelled word is located. It is great for large documents that were scanned and converted into text using optical character recognition (OCR) which may result in wrong letters or missing letters in words. Applications include law firms and others who need to find content in OCR and other documents that may have spelling errors.

FMT also can be used for large documents that have no spelling errors. Being able to find that needle in the haystack is not trivial exercise. But FMT is here to help us when we need its great services.

When searching, it looks and feels like an Internet Search engine but the data and processing is kept and performed local on your computer. Blocks of text are returned and color coded for easy review.

FMT works on the fly. In other words it does not create an index. That way your computer is not bogged down while you are doing other tasks. FMT works only when you press the submit button. FMT also lets you save your previous analysis sessions so that you can quickly duplicate then modify your analysis. FMT is also fast.

To begin mining an OCR document that may have errors, browse to the document location, enter the search word using correct spelling, and press Mine Now. Use the Spelling Errors and Letters Lost settings to expand or narrow your search. Increasing the numbers will provide more returns but may lead to more false positives. Reducing the numbers will provide less returns but will also reduce the false positives. Use the other buttons to enable and disable different views of the results.

FMT has two libraries: Mining Source and Previous Analysis. Create and manage your directories within these libraries as desired. Use your windows explorer to move your files to the mining source directory. Save your previous analysis sessions into Previous Analysis. Do this by using your browser file save options. Save as HTML page only, there is no need to save the whole HTML page which includes the images.

FMT like all CassBeth software tools are available to try for free using demo keys. In the demo version the user is presented with small book images Sustainable Development Possible with Creative System Engineering and Systems Practices as Common Sense. The books are available from Amazon and other destinations. When the software is purchased, keys are provided to suppress the images and links to the books.