Finding word bounding boxes

[ ]

Aspose.OCR for .NET can automatically find the coordinates of image regions containing words. This can be useful for highlighting detected areas when previewing an image or extracting individual blocks of text.

To get bounding boxes of all words in images, provided in OcrInput object, use Aspose.OCR.AsposeOcr.DetectRectangles method. Specify Aspose.OCR.AreasType.WORDS as the areasType parameter of the method. detectAreas parameter of the method is ignored.

The method returns a list of Aspose.OCR.RectangleOutput objects containing coordinates of each word in each image.

Property Type Description
Rectangles List<Rectangle> Coordinates of each word of an image (top-left corner, width and height), returned as a list of Rectangle objects.
ImageIndex int Sequence number of the image on the page. When working with single-page images, this value is always 0.
Page int Page number. When working with single-page images, this value is always 0.
Source string The full path or URL of the source file. If the file is provided as a MemoryStream object, an array of pixels, or a Base64 string, this value will be empty.


The following code example shows how to detect words in multiple images:

Aspose.OCR.AsposeOcr recognitionEngine = new Aspose.OCR.AsposeOcr();
// Add images to OcrInput object
Aspose.OCR.OcrInput input = new Aspose.OCR.OcrInput(Aspose.OCR.InputType.SingleImage);
// Detect words
List<Aspose.OCR.RectangleOutput> results = recognitionEngine.DetectRectangles(input, Aspose.OCR.AreasType.WORDS);
foreach(Aspose.OCR.RecognitionResult result in results)
	foreach(Rectangle region in result.Rectangles) Console.WriteLine($"File: {result.Source} | {region.Top}, {region.Left}, {region.Width}, {region.Height}");