public void Recognize(TesseractOcrSettings settings, VintasoftImage image)
{
using (TesseractOcr tesseractOcr = new TesseractOcr())
{
tesseractOcr.Init(settings);
tesseractOcr.SetImage(image);
OcrPage ocrResult = tesseractOcr.Recognize();
_editor.EditorResult(ocrResult);
}
}
public void CreateTesseractEngine()
{
string tesseractOcrDllPath = @"G:\Programm\vintasoft\Bin\TesseractOCR";
using (TesseractOcr tesseractOcr = new TesseractOcr(tesseractOcrDllPath))
{
OcrLanguage language = OcrLanguage.Russian;
TesseractOcrSettings settings = new TesseractOcrSettings(language);
tesseractOcr.Init(settings);
tesseractOcr.Shutdown();
}
}
public static bool UpdateOcrRendition(Record record)
{
bool success = false;
string extractedFilePath = string.Empty;
string ocrFilePath = string.Empty;
try
{
// get a temp working location on disk
var rootDirectory = Path.Combine(Path.GetTempPath(), "cmramble_ocr");
if (!Directory.Exists(rootDirectory))
{
Directory.CreateDirectory(rootDirectory);
}
// formulate file name to extract, delete if exists for some reason
extractedFilePath = Path.Combine(rootDirectory, $"{record.Uri}.{record.Extension}");
ocrFilePath = Path.Combine(rootDirectory, $"{record.Uri}.txt");
FileHelper.Delete(extractedFilePath);
FileHelper.Delete(ocrFilePath);
// fetch document
Log.Debug($"Extracting Record {record.Number}: {extractedFilePath}");
record.GetDocument(extractedFilePath, false, "OCR", string.Empty);
// get the OCR text
Log.Debug($"Tesseract Ocr Record {record.Number}: {extractedFilePath}");
ocrFilePath = TesseractOcr.ExtractFromFile(extractedFilePath);
// use record extension method that removes existing OCR rendition (if exists)
record.AddOcrRendition(ocrFilePath);
Log.Debug($"Saving Record {record.Number}");
record.Save();
Log.Debug($"Saved Record {record.Number}");
success = true;
}
catch (Exception ex)
{
Log.Error(ex);
}
finally
{
FileHelper.Delete(extractedFilePath);
FileHelper.Delete(ocrFilePath);
}
return(success);
}
public static bool GenerateOcrRendition(Record record, RecordRendition sourceRendition)
{
bool success = false;
string extractedFilePath = string.Empty;
string ocrFilePath = string.Empty;
try
{
// get a temp working location on disk
var rootDirectory = Path.Combine(Path.GetTempPath(), "cmramble_ocr");
if (!Directory.Exists(rootDirectory))
{
Directory.CreateDirectory(rootDirectory);
}
// formulate file name to extract, delete if exists for some reason
extractedFilePath = Path.Combine(rootDirectory, $"{sourceRendition.Uri}.{sourceRendition.Extension}");
ocrFilePath = Path.Combine(rootDirectory, $"{sourceRendition.Uri}.txt");
FileHelper.Delete(extractedFilePath);
FileHelper.Delete(ocrFilePath);
// fetch document
var extract = sourceRendition.GetExtractDocument();
extract.FileName = Path.GetFileName(extractedFilePath);
extract.DoExtract(Path.GetDirectoryName(extractedFilePath), true, false, "");
if (!String.IsNullOrWhiteSpace(extract.FileName) && File.Exists(extractedFilePath))
{
ocrFilePath = TesseractOcr.ExtractFromFile(extractedFilePath);
// use record extension method that removes existing OCR rendition (if exists)
record.AddOcrRendition(ocrFilePath);
record.Save();
success = true;
}
}
catch (Exception ex)
{
}
finally
{
FileHelper.Delete(extractedFilePath);
FileHelper.Delete(ocrFilePath);
}
return(success);
}
static void Main(string[] args)
{
var stopwatch = new Stopwatch();
stopwatch.Start();
// Handle input arguments
byte[] image;
if (args.Length == 0)
{
Console.WriteLine($"Using file: {TestImageFilePath}");
try
{
image = File.ReadAllBytes(TestImageFilePath);
}
catch (Exception e)
{
Console.WriteLine($"Error when loading image: {e.Message}");
return;
}
}
else
{
var possibleUrl = args[0];
Console.WriteLine($"Using url from args: {possibleUrl}");
try
{
using (var webClient = new WebClient())
{
image = webClient.DownloadData(possibleUrl);
}
}
catch (Exception e)
{
Console.WriteLine($"Error when loading image from URL: {e.Message}");
return;
}
}
// Classify
//var classificationResults = new TensorFlowClassificator().ClassifyImage(image);
var classificationResults = new WebClassificator().ClassifyImage(image);
// OCR
var text = TesseractOcr.ParseText();
// Print
Console.WriteLine("------------------------");
Console.WriteLine("OBJECT CLASSIFICATION");
Console.WriteLine("------------------------");
foreach (var classification in classificationResults.OrderByDescending(x => x.Value))
{
Console.WriteLine($"{classification.Key, 15} => {Math.Round((classification.Value * 100.0), 3)}%");
}
Console.WriteLine("------------------------");
Console.WriteLine("OCR WEIGHT FINDER RESUTLS");
Console.WriteLine("------------------------");
text = text.Trim().Replace("\r\n", " ").Replace("\n", " ");
var regexWeightFinder = new RegexMetricWeightSubstringFinder();
var octResult = regexWeightFinder.FindWeightSpecifier(text);
Console.WriteLine(octResult);
Console.WriteLine("------------------------");
Console.WriteLine("OCR KEYWORDS");
Console.WriteLine("------------------------");
var keywords = text.Split(' ')
.Where(word => !string.IsNullOrWhiteSpace(word))
.Where(word => OcrKeywords.Any(keyword => word.ToLower().Contains(keyword)));
foreach (var keyword in keywords)
{
Console.WriteLine(keyword);
}
Console.WriteLine("------------------------");
stopwatch.Stop();
Console.WriteLine($"Total time: {stopwatch.Elapsed}");
}
