此示例展示如何使用 IronTesseract 提取任何OCR文档中每个字符、单词、行或段落的图像及其坐标。
hOCR Export with IronOCR in C#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($"page{page.PageNumber}_word{word.WordNumber}.png", AnyBitmap.ImageFormat.Png);
}
}
Imports IronOcr
Imports IronSoftware.Drawing
Dim ocrTesseract = New IronTesseract()
Using ocrInput = New OcrInput()
ocrInput.LoadImage("images\image.png")
Dim ocrResult = ocrTesseract.Read(ocrInput)
For Each page In ocrResult.Pages
For Each word In page.Words
word.ToBitmap(ocrInput).SaveAs($"page{page.PageNumber}_word{word.WordNumber}.png", AnyBitmap.ImageFormat.Png)
Next
Next
End UsingImports IronOcr
Imports IronSoftware.Drawing
Dim ocrTesseract = New IronTesseract()
Using 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
Next
End Using
