IronOCR 和 AWS Textract OCR 之間的比較

using Amazon.Textract;
using Amazon.Textract.Model;

Imports Amazon.Textract
Imports Amazon.Textract.Model

var Ocr = new IronTesseract();
using (var input = new OcrInput())
{
    input.AddPdf("example.pdf", "password");
    // We can also select specific PDF page numbers to OCR
    var Result = Ocr.Read(input);
    Console.WriteLine(Result.Text);
    Console.WriteLine($"{Result.Pages.Count()} Pages");
    // Read every page of the PDF
}

Dim Ocr = New IronTesseract()
Using input = New OcrInput()
	input.AddPdf("example.pdf", "password")
	' We can also select specific PDF page numbers to OCR
	Dim Result = Ocr.Read(input)
	Console.WriteLine(Result.Text)
	Console.WriteLine($"{Result.Pages.Count()} Pages")
	' Read every page of the PDF
End Using

public static async void ReturnResult()
{
    AmazonTextractClient client = new AmazonTextractClient("your_access_key_id", "your_secret_access_key", Amazon.RegionEndpoint.AFSouth1);
    var request = new StartDocumentTextDetectionRequest();
    request.DocumentLocation = new DocumentLocation
    {
        S3Object = new S3Object
        {
            Bucket = "your_bucket_name",
            Name = "your_bucket_key"
        }
    };
    var id = await client.StartDocumentTextDetectionAsync(request);
    var jobId = id.JobId;
    var response = client.GetDocumentTextDetectionAsync(new GetDocumentTextDetectionRequest{
        JobId = jobId
    });
    response.Wait();
    if (response.Result.JobStatus.Equals("SUCCEEDED"))
    {
        foreach (var block in response.Result.Blocks)
        {
            if (block.BlockType == "WORD" || block.BlockType == "PAGE" || block.BlockType == "LINE")
            {
                Console.WriteLine(block.Text);
            }
        }
    }
}

static void Main(String[] args)
{
    ReturnResult();
}

Public Shared Async Sub ReturnResult()
	Dim client As New AmazonTextractClient("your_access_key_id", "your_secret_access_key", Amazon.RegionEndpoint.AFSouth1)
	Dim request = New StartDocumentTextDetectionRequest()
	request.DocumentLocation = New DocumentLocation With {
		.S3Object = New S3Object With {
			.Bucket = "your_bucket_name",
			.Name = "your_bucket_key"
		}
	}
	Dim id = Await client.StartDocumentTextDetectionAsync(request)
	Dim jobId = id.JobId
	Dim response = client.GetDocumentTextDetectionAsync(New GetDocumentTextDetectionRequest With {.JobId = jobId})
	response.Wait()
	If response.Result.JobStatus.Equals("SUCCEEDED") Then
		For Each block In response.Result.Blocks
			If block.BlockType = "WORD" OrElse block.BlockType = "PAGE" OrElse block.BlockType = "LINE" Then
				Console.WriteLine(block.Text)
			End If
		Next block
	End If
End Sub

Shared Sub Main(ByVal args() As String)
	ReturnResult()
End Sub

var Ocr = new IronTesseract();
using (var Input = new OcrInput())
{
    Input.AddImage("test-files/redacted-employmentapp.png");
    //... you can add any number of images
    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

Dim Ocr = New IronTesseract()
Using Input = New OcrInput()
	Input.AddImage("test-files/redacted-employmentapp.png")
	'... you can add any number of images
	Dim Result = Ocr.Read(Input)
	Console.WriteLine(Result.Text)
End Using

public static async void ReturnResult()
{
    AmazonTextractClient client = new AmazonTextractClient("your_access_key_id", "your_secret_access_key", Amazon.RegionEndpoint.AFSouth1);
    var request = new DetectDocumentTextRequest();
    request.Document = new Document
    {
        Bytes = new MemoryStream(File.ReadAllBytes(@"test-files/redacted-employmentapp.png"))
    };    
    var result = await client.DetectDocumentTextAsync(request);
    foreach (var block in result.Blocks)
    {
        if (block.BlockType == "WORD")
        {
            Console.WriteLine(block.Text);
        }
    }
}

static void Main(String[] args)
{
    ReturnResult();
}

Public Shared Async Sub ReturnResult()
	Dim client As New AmazonTextractClient("your_access_key_id", "your_secret_access_key", Amazon.RegionEndpoint.AFSouth1)
	Dim request = New DetectDocumentTextRequest()
	request.Document = New Document With {.Bytes = New MemoryStream(File.ReadAllBytes("test-files/redacted-employmentapp.png"))}
	Dim result = Await client.DetectDocumentTextAsync(request)
	For Each block In result.Blocks
		If block.BlockType = "WORD" Then
			Console.WriteLine(block.Text)
		End If
	Next block
End Sub

Shared Sub Main(ByVal args() As String)
	ReturnResult()
End Sub