Below is some code that
- creates a directory
- uses MagickNet to covert a PDF into separate BMP images and stores it in a folder (ImagePath)
- Then it uses TessNet2 to scan each image in that folder to parse out information
I can't seem to get the foreach loop that scans the ImagePath folder. Any help?
The error right now is on the 'foreach' statement and it says "Cannot convert type 'char' to 'System.Drawing.Image'"
static void Main(string[] args)
{
string ImagePath = exePath + "\\Images";
if (!Directory.Exists(ImagePath))
{
Directory.CreateDirectory(ImagePath);
}
MagickReadSettings settings = new MagickReadSettings();
settings.Density = new MagickGeometry(300, 300);
using (MagickImageCollection images = new MagickImageCollection())
{
images.Read(@"D:\Test\ABStest.pdf",settings);
int page = 1;
foreach (MagickImage image in images)
{
image.Write(ImagePath + "\\ABS" + page + ".bmp");
page++;
}
}
foreach (Image item in ImagePath)
{
using (Bitmap bmp = new Bitmap(item))
{
tessnet2.Tesseract tessocr = new tessnet2.Tesseract();
tessocr.Init(@"C:\Users\Matt Taylor\Documents\Visual Studio 2012\Projects\TessNet2\TessNet2\bin\Debug\tessdata", "eng", false);
tessocr.GetThresholdedImage(bmp, Rectangle.Empty).Save("c:\\temp\\" + Guid.NewGuid().ToString() + ".bmp");
// Tessdata directory must be in the directory than this exe
Console.WriteLine("Multithread version");
ocr.DoOCRMultiThred(bmp, "eng");
//Console.WriteLine("Normal version");
//ocr.DoOCRNormal(bmp, "eng");
}
}
}