Package org.opencv.dnn
Class TextDetectionModel
java.lang.Object
org.opencv.dnn.Model
org.opencv.dnn.TextDetectionModel
- Direct Known Subclasses:
TextDetectionModel_DB
,TextDetectionModel_EAST
Base class for text detection networks
-
Field Summary
-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionstatic TextDetectionModel
__fromPtr__
(long addr) void
detect
(Mat frame, List<MatOfPoint> detections) void
detect
(Mat frame, List<MatOfPoint> detections, MatOfFloat confidences) Performs detection Given the inputframe
, prepare network input, run network inference, post-process network output and return result detections.void
detectTextRectangles
(Mat frame, MatOfRotatedRect detections) void
detectTextRectangles
(Mat frame, MatOfRotatedRect detections, MatOfFloat confidences) Performs detection Given the inputframe
, prepare network input, run network inference, post-process network output and return result detections.protected void
finalize()
Methods inherited from class org.opencv.dnn.Model
enableWinograd, getNativeObjAddr, predict, setInputCrop, setInputMean, setInputParams, setInputParams, setInputParams, setInputParams, setInputParams, setInputParams, setInputScale, setInputSize, setInputSize, setInputSwapRB, setOutputNames, setPreferableBackend, setPreferableTarget
-
Constructor Details
-
TextDetectionModel
protected TextDetectionModel(long addr)
-
-
Method Details
-
__fromPtr__
-
detect
Performs detection Given the inputframe
, prepare network input, run network inference, post-process network output and return result detections. Each result is quadrangle's 4 points in this order: - bottom-left - top-left - top-right - bottom-right Use cv::getPerspectiveTransform function to retrieve image region without perspective transformations. Note: If DL model doesn't support that kind of output then result may be derived from detectTextRectangles() output.- Parameters:
frame
- The input imagedetections
- array with detections' quadrangles (4 points per result)confidences
- array with detection confidences
-
detect
-
detectTextRectangles
Performs detection Given the inputframe
, prepare network input, run network inference, post-process network output and return result detections. Each result is rotated rectangle. Note: Result may be inaccurate in case of strong perspective transformations.- Parameters:
frame
- the input imagedetections
- array with detections' RotationRect resultsconfidences
- array with detection confidences
-
detectTextRectangles
-
finalize
-