Intelligent Character Recognition (ICR) is used to recognize hand-written text and numbers. Assuming ICR support is unlocked, ICR can be performed whenever the LEADTOOLS OCR Module - OmniPage Engine is being used.
Recognize handwritten text and number by setting the OcrZoneType to OcrZoneType.Icr to create an ICR zone. Next, specify handwritten text and numbers by setting the OcrZoneCharacterFilters to be OcrZoneCharacterFilters.Numbers.
Note: Normally it is not recommended to use the character filters. However, it is recommended when performing ICR for hand written numbers only.
Keep in mind the following tips:
When using ICR, the better the hand writing, the better the results.
Use a block format so each letter is within its own container, preventing overlapping characters. For more information about the cell block format, refer to
The following example shows how to perform ICR recognition.
// Create an instance of the engine
IOcrEngine ocrEngine = OcrEngineManager.CreateEngine(OcrEngineType.OmniPage, false);
// Start the engine using default parameters
ocrEngine.Startup(null, null, null, @"C:\LEADTOOLS 20\Bin\Common\OcrOmniPageRuntime");
// Create an OCR document
using (IOcrDocument ocrDocument = ocrEngine.DocumentManager.CreateDocument())
RasterImage image = ocrEngine.RasterCodecsInstance.Load(input, 0, CodecsLoadByteOrder.Rgb, 1, -1);
// Add this image to the document
IOcrPage ocrPage = ocrDocument.Pages.AddPage(image, null);
// Perform default AutoZoning on the page
// Iterate through each zone in the document to make them ICR zones
for (int i = 0; i < ocrPage.Zones.Count; i++)
OcrZone zone = ocrPage.Zones[i];
zone.ZoneType = OcrZoneType.Icr;
ocrDocument.Save(output, DocumentFormat.Text, null);
Does your application require document recognition or conversion, but its implementation language is preventing you from using LEADTOOLS directly? Consider using the LEADTOOLS Cloud Services Web API instead. It is a high-powered and scalable Web API. Its hassle-free interface can be used to integrate advanced OCR, barcode, MICR, and document conversion into any application.
Medical Web Viewer .NET
.NET, Java, Android, and iOS/macOS Assemblies
C API/C++ Class Libraries