DISK_create
import { DISK_create } from '@banou/opencv-wasm'Use after await initOpenCV(). See the initialization and named imports guide.
Creates a DISK detector.
DISK_create(modelPath: EmbindString, maxKeypoints: number, scoreThreshold: number, imageSize: Size, backendId: number, targetId: number): DISK | null;6 available overloads
DISK_create(modelPath: EmbindString): DISK | null;DISK_create(modelPath: EmbindString, maxKeypoints: number): DISK | null;DISK_create(modelPath: EmbindString, maxKeypoints: number, scoreThreshold: number): DISK | null;DISK_create(modelPath: EmbindString, maxKeypoints: number, scoreThreshold: number, imageSize: Size): DISK | null;DISK_create(modelPath: EmbindString, maxKeypoints: number, scoreThreshold: number, imageSize: Size, backendId: number): DISK | null;DISK_create(modelPath: EmbindString, maxKeypoints: number, scoreThreshold: number, imageSize: Size, backendId: number, targetId: number): DISK | null;modelPathPath to the DISK ONNX model.
maxKeypointsMaximum number of keypoints to return per image. The strongest responses (by network score) are kept; -1 keeps all detections.
scoreThresholdDiscard keypoints with network score strictly below this value.
imageSizeTarget input size (width, height) fed to the network. Use Size() (the default) to fall back to the network's expected fixed input shape of 1024x1024. When overriding, both dimensions must be positive multiples of 16, since DISK downsamples by a factor of 16.
backendIdDNN backend identifier (see cv::dnn::Backend); 0 = DNN_BACKEND_DEFAULT.
targetIdDNN target identifier (see cv::dnn::Target); 0 = DNN_TARGET_CPU.
The DISK | null result.
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.