dnn_TextDetectionModel

Deep neural networksclassOpenCV 5.0.0

import { dnn_TextDetectionModel } from '@banou/opencv-wasm'

Use after await initOpenCV(). See the initialization and named imports guide.

ARGUMENTSConstructor or factory

CLASSdnn_TextDetectionModel

RETURN TYPEOwned native handle

Call structure. A void return can still write to destination arguments. The parameter descriptions define inputs, outputs and ownership.

Native object: release it with using or delete(). Factories can return null; check before calling methods. Inherits dnn_Model.

Base class for text detection networks

Upstream declaration ↗

Constructors and members

clone

Create another handle to the same native object. This retains the object without copying its pixels or algorithm state; dispose both handles separately.

clone(): this;

Returns

The this result.

detect

Performs detection

Given the input frame, 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.

detect(frame: Mat, detections: PointVectorVector, confidences: FloatVector): void;

frame: The input image
detections: Output destination, filled by the native operation. array with detections' quadrangles (4 points per result)
confidences: Output destination, filled by the native operation. array with detection confidences

Upstream declaration ↗

detect1

Performs detection

Given the input frame, 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.

detect1(frame: Mat, detections: PointVectorVector): void;

frame: The input image
detections: Output destination, filled by the native operation. array with detections' quadrangles (4 points per result)

Upstream declaration ↗

detectTextRectangles

Performs detection

Given the input frame, 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.

detectTextRectangles(frame: Mat, detections: RotatedRectVector, confidences: FloatVector): void;

frame: the input image
detections: Output destination, filled by the native operation. array with detections' RotationRect results
confidences: Output destination, filled by the native operation. array with detection confidences

Upstream declaration ↗

detectTextRectangles1

Performs detection

Given the input frame, 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.

detectTextRectangles1(frame: Mat, detections: RotatedRectVector): void;

frame: the input image
detections: Output destination, filled by the native operation. array with detections' RotationRect results

Upstream declaration ↗

These signatures describe this package. Upstream documentation can mention optional backends that are absent from this build. Check runtime compatibility before choosing a backend or file format.