If you have multiple image files in a folder, e.g. TIF, and those images are of the same format, e.g. Purchase Orders, then you can extract text from specific pre-defined areas of all the image files in a folder; and store the results, in a delimited file, one row of data for each record, to Text, XML, or an Excel file.
There are four steps to processing image files.
Step One: Define the zones within an image to process.
A Zone is an area of an image which you want to convert to text.
To define a zone, you need to select an image which is representative of all the image files in the folder; and define zones using that image.
For example, suppose you had a thousand Purchase Orders in a folder in TIF format. Suppose each Purchase Order contained a Name, Purchase Date, and an Order Number.
If those values were all located in the same area of the form for all the images files to be processed; you could define those zones in OCR Folder, so that OCRFolder would generate a text delimited file of those converted values.
Step Two. Process all Image Files in a Folder
After the regions have been defined, you select a folder that contains your image files, and OCRFolder will process the files converting your designated zones to text.
Step Three: Audit Processed Results
After your image files have been converted to text, an Audit screen will display your results. The Audit screen is used to proofread and correct the processed results. The converted text along with the original image file is displayed as a guide for verification.
Step Four: Save Processed Results to File
After you are satisfied with the accuracy of your results, you can store the results to file. We offer three means of exporting your data to file, Text Delimited Files, XML Files, or Excel Files.