Class DecodeEAST
Object
org.anchoranalysis.bean.AnchorBean<org.anchoranalysis.image.inference.bean.segment.instance.DecodeInstanceSegmentation<T>>
org.anchoranalysis.image.inference.bean.segment.instance.DecodeInstanceSegmentation<ai.onnxruntime.OnnxTensor>
org.anchoranalysis.plugin.onnx.bean.object.segment.decode.instance.text.DecodeEAST
public class DecodeEAST
extends org.anchoranalysis.image.inference.bean.segment.instance.DecodeInstanceSegmentation<ai.onnxruntime.OnnxTensor>
Extracts text from a RGB image by using the EAST deep neural network model and the ONNX
Runtime.
Each object-mask represented rotated-bounding box and is associated with a confidence score.
Particular thanks to Adrian Rosebrock whose tutorial was useful in applying this model
- Author:
- Owen Feehan
-
Constructor Summary
Constructors Constructor Description DecodeEAST() -
Method Summary
Modifier and Type Method Description List<org.anchoranalysis.image.inference.segment.LabelledWithConfidence<org.anchoranalysis.image.inference.segment.MultiScaleObject>>decode(List<ai.onnxruntime.OnnxTensor> inferenceOutput, org.anchoranalysis.image.inference.ImageInferenceContext context)List<String>expectedOutputs()doublegetMinConfidence()Proposed bounding boxes below this confidence interval are removed from consideration.voidsetMinConfidence(double minConfidence)Proposed bounding boxes below this confidence interval are removed from consideration.
-
Constructor Details
-
DecodeEAST
public DecodeEAST()
-
-
Method Details
-
decode
public List<org.anchoranalysis.image.inference.segment.LabelledWithConfidence<org.anchoranalysis.image.inference.segment.MultiScaleObject>> decode(List<ai.onnxruntime.OnnxTensor> inferenceOutput, org.anchoranalysis.image.inference.ImageInferenceContext context) throws org.anchoranalysis.core.exception.OperationFailedException- Specified by:
decodein classorg.anchoranalysis.image.inference.bean.segment.instance.DecodeInstanceSegmentation<ai.onnxruntime.OnnxTensor>- Throws:
org.anchoranalysis.core.exception.OperationFailedException
-
expectedOutputs
- Specified by:
expectedOutputsin classorg.anchoranalysis.image.inference.bean.segment.instance.DecodeInstanceSegmentation<ai.onnxruntime.OnnxTensor>
-
getMinConfidence
public double getMinConfidence()Proposed bounding boxes below this confidence interval are removed from consideration. -
setMinConfidence
public void setMinConfidence(double minConfidence)Proposed bounding boxes below this confidence interval are removed from consideration.
-