(Für diese Definition ist die deutsche Übersetzung noch nicht abgeschlossen)
Automatic annotation or labelling of scenes.
Semantic segmentation of scenes, e.g. by means of labelling each pixel of an image with a corresponding class of what is being represented. This process can be seen as image classification at pixel level.
Syntactic segmentation of scenes, e.g. by means of using the structural representation of an image. Examples of structural representations include grammars or graphs. This process can be used instead of statistical pattern recognition when there is a clear structure in the pattern.
Examples
Semantic segmentation of hair wherein a tiered structure constraint has been used for determining the labels of the pixels.
Labelling of image objects according to known object classes
Image preprocessing for image or video recognition or understanding involving the determination of region of interest [ROI] or a volume of interest [VOI] | G06V 10/25 |
Segmentation of patterns in the image field; Cutting or merging image elements to establish the pattern region, e.g. region growing, watershed or clustering-based techniques; Detection of occlusion | G06V 10/26 |
Recognition using syntactic or structural representations of the image or video pattern, e.g. symbolic string recognition; Graph matching | G06V 10/86 |
Techniques for post-processing in character recognition using context analysis, e.g. lexical, syntactic or semantic context | G06V 30/262 |
Information retrieval; Database structures therefor; File system structures therefor | G06F 16/00 |
Image analysis by segmentation or edge detection in general | G06T 7/10 |
Automatic annotation or labelling of scenes.
Semantic segmentation of scenes, e.g. by means of labelling each pixel of an image with a corresponding class of what is being represented. This process can be seen as image classification at pixel level.
Syntactic segmentation of scenes, e.g. by means of using the structural representation of an image. Examples of structural representations include grammars or graphs. This process can be used instead of statistical pattern recognition when there is a clear structure in the pattern.
Examples
Semantic segmentation of hair wherein a tiered structure constraint has been used for determining the labels of the pixels.
Labelling of image objects according to known object classes
Image preprocessing for image or video recognition or understanding involving the determination of region of interest [ROI] or a volume of interest [VOI] | G06V 10/25 |
Segmentation of patterns in the image field; Cutting or merging image elements to establish the pattern region, e.g. region growing, watershed or clustering-based techniques; Detection of occlusion | G06V 10/26 |
Recognition using syntactic or structural representations of the image or video pattern, e.g. symbolic string recognition; Graph matching | G06V 10/86 |
Techniques for post-processing in character recognition using context analysis, e.g. lexical, syntactic or semantic context | G06V 30/262 |
Information retrieval; Database structures therefor; File system structures therefor | G06F 16/00 |
Image analysis by segmentation or edge detection in general | G06T 7/10 |