Traitement en cours

Veuillez attendre...

Paramétrages

Paramétrages

Aller à Demande

1. WO1997041533 - PROCEDE D'APPRENTISSAGE DESTINE A UN SYSTEME D'ANALYSE D'IMAGES SERVANT A ANALYSER UN OBJET, ET UTILISATIONS DE CE PROCEDE

Note: Texte fondé sur des processus automatiques de reconnaissance optique de caractères. Seule la version PDF a une valeur juridique

[ EN ]

P a t e n t C l a i m s :

1. A learning method for an image analysis system for use in the analysis of an object, wherein the object is compared with a reference object, and comprising the steps of:

a. capturing a video image of the reference object which is represented by a plurality of pixel positions, each pixel having its own identification,

b. dividing parts of the video image into a plurality of subareas which represent a plurality of classes

c h a r a c t e r i z e d by

c. setting up a user-defined table of classes where a plurality of identifications is assigned to each class in the table, each class in the table being formed by the user by his selection of a plurality of pixels in the reference image,

d. setting up a special zero class in the table which contains pixel identifications which have not been assigned to any class by the user, and

e. setting up a special conflict class which contains the pixel identifications which have been assigned to more than one class by the user.

2. A method according to claim 1, c h a r a c t e r i z e d in that all pixels belonging to the zero class or the conflict class are assigned to the class having a pixel identification which is closest to the identification of the pixel concerned.

3. A method according to claim 2, c h a r a c t e r i z e d m that the assignment takes place in several stages, each stage comprising processing pixel identifications which adjoin pixel identifications which have al-ready been assigned to a class.

4. A method according to claims 1-3, c h a r a c t e r i z e d m that the user-operated table of classes is formed by drawing a line, a polygon or the like on the video image, e.g. with a "mouse".

5. A method according to claims 1-4, c h a r a c t e r i z e d m that several reference images are used in the learning .

6. A method according to claims 1-6, c h a r a c t e r i z e d m that a user-selected class may be suppressed.

7. A method according to claims 1-6, c h a r a c t e r -l z e d m that the identifications of the individual pixels may be expressed in an N-dimensional space.

8. A method according to claims 1-7, c h a r a c t e r i z e d m that the identifications of the individual pixels are expressed in RGB coordinates or in HSI coordinates .

9. A method according to claims 1-8, c h a r a c t e r i z e d in that an object is analyzed by assigning to each pixel position in the image which represents the object with a given identification, the class symbol which contains precisely the identification valid after learning .

10. Use of the method according to any one of claims 1-9 for the analysis of cells/tissue.

11. Use of the method according to any one of claims 1-9 for the analysis of cuts of meat.

12. Use of the method according to any one of claims 1-9 for metallurgical analyses.

13. Use of the method according to any one of claims 1-9 for the grading of e.g. fruit, vegetables, berries or the like.

14. Use of the method according to any one of claims 1-9 for the analysis of cement.

15. Use of the method according to any one of claims 1-9 for the analysis of fabrics.