ImageEn, unit ievision

TIEVisionNNet.detectTexts

TIEVisionNNet.detectTexts


Declaration

function detectTexts(model: int32_t; image: TIEVisionImage; out confidences: TIEVisionVectorDouble; out detections: TIEVisionVectorRotatedRect): bool32; safecall;


Description

Detects text in the specified input image and returns the text values, confidences and bounding boxes.
Returns True on success (both input and model valid).


Parameter Description
model Model type. 0 = EAST, 1 = DB
image Input image
confidences Output array of confidences per text block detected
detections Output array rotated rectangles per text block detected

Note: This method only detects the location of text. To "Recognize" the text, use OCR


Example

// Detect all text blocks inside TImageEnView using DB_IC15_resnet18.onnx pretrained model
var
  nnet: TIEVisionNNet;
  rrects: TIEVisionVectorRotatedRect;
  confidences: TIEVisionVectorDouble;
  i: integer;
  r: TIEVisionRect;
begin
  OCR := IEVisionLib.createOCR(IEOCRLanguageList[OCR_English_language].Code);
  nnet := IEVisionLib.createNNet('models\DB\DB_IC15_resnet18.onnx');
  nnet.setInputSize(1280, 736);
  nnet.setInputScale(1.0/255);
  nnet.detectTexts(1, ImageEnView1.IEBitmap.GetIEVisionImage(), confidences, rrects);
  for i := 0 to rrects.size() - 1 do
  begin
    r := IEVisionRect( rrects.getRect(i) );
    // Note: With the East model in can be useful to inflate the text boxes to improve detection
    s := OCR.recognize( ImageEnView1.IEBitmap.GetIEVisionImage(), r ).c_str();
    Memo1.Lines.Add( s );
  end;
end;