Exporting Images of OCR Elements
This example show how IronTesseract can extract the Image and coordinates for every character, word, line, or paragraph of text in any OCR document.
using IronOcr;
using IronSoftware.Drawing;
var ocrTesseract = new IronTesseract();
using var ocrInput = new OcrInput();
ocrInput.LoadImage(@"images\image.png");
var ocrResult = ocrTesseract.Read(ocrInput);
foreach (var page in ocrResult.Pages)
{
foreach (var word in page.Words)
{
word.ToBitmap(ocrInput).SaveAs($"page{page.PageNumber}_word{word.WordNumber}.png", AnyBitmap.ImageFormat.Png);
}
}Imports IronOcr
Imports IronSoftware.Drawing
Private ocrTesseract = New IronTesseract()
Private ocrInput = New OcrInput()
ocrInput.LoadImage("images\image.png")
Dim ocrResult = ocrTesseract.Read(ocrInput)
For Each page In ocrResult.Pages
For Each word In page.Words
word.ToBitmap(ocrInput).SaveAs($"page{page.PageNumber}_word{word.WordNumber}.png", AnyBitmap.ImageFormat.Png)
Next word
Next page
