Functions
static Array< Rectangle2D >	oevislib_net.DeepLearning.OCR.Paddle.FindText (Image inImage, Optional< Rectangle2D > inRoi=null, Optional< UCS2D > inRoiAlignment=null, ModelPerformance inModelPerformance=ModelPerformance.Best, float inThreshold=0.3f, float inBoxThreshold=0.6f, float inUnclipRatio=1.5f)
	Find the region of the image containing text.
static Array< string >	oevislib_net.DeepLearning.OCR.Paddle.ReadText (Image inImage, Array< Rectangle2D > inTextRegions, Optional< TextOrientation > inOrientation=null, Language inLanguage=Language.English)
	Read and segment text from an image using Paddle pre-trained OCR model.

Detailed Description

Function Documentation

Array< Rectangle2D > oevislib_net.DeepLearning.OCR.Paddle.FindText	(	Image	inImage,
		Optional< Rectangle2D >	inRoi = null,
		Optional< UCS2D >	inRoiAlignment = null,
		ModelPerformance	inModelPerformance = ModelPerformance::Best,
		float	inThreshold = 0::3f,
		float	inBoxThreshold = 0::6f,
		float	inUnclipRatio = 1::5f )

inlinestatic

Find the region of the image containing text.

Parameters

inImage	The input Image containing the text to be highlighted.
inRoi	Region of interest where the text is located.
inRoiAlignment	UCS2D alignment to apply to the given ROI.
inModelPerformance	Whether to use the Best or the Fast model available.
inThreshold	Threshold applied to the model's score map to binarize and extract candidate text regions.
inBoxThreshold	Minimum average score required for a detected box/region to be considered valid.
inUnclipRatio	Ratio used to expand ("unclip") the detected text region. A higher value increases the size of the output bounding box, useful for covering the full text area.

Returns: An Array<Rectangle2D> representing the found bounding boxes delimiting text regions.

Array< string > oevislib_net.DeepLearning.OCR.Paddle.ReadText	(	Image	inImage,
		Array< Rectangle2D >	inTextRegions,
		Optional< TextOrientation >	inOrientation = null,
		Language	inLanguage = Language::English )

inlinestatic

Read and segment text from an image using Paddle pre-trained OCR model.

Parameters

inImage	The input Image containing the text to be recognized.
inTextRegions	Array of Rectangle2D specifying regions to read.
inOrientation	Whether the text is horizontal or vertical oriented.
inLanguage	Language in which the text is written.