Image analysis
A computer-implemented method for identifying features in an image. The method comprises fitting a plurality of second models to the image, the plurality of second models together modelling a region of interest, wherein each part of the region of interest is modelled by at least two of the plurality of second models; and identifying the features in the image based upon the fit of the plurality of second models.
1. A computer-implemented method for identifying features in an image, the method comprising:
determining an estimate of location of said features in said image;
fitting a plurality of second models to said image, each of said plurality of second models modelling a part of a region of interest of said image, said plurality of second models together modelling said region of interest, wherein said image parts modelled by said second models overlap such that each part of said region of interest is modelled by at least two of said plurality of second models; and
updating said estimate based upon said fit of one of said second models if the fit of said one of said second models satisfies a predetermined criterion,
wherein the plurality of second models represent a decomposition of the features of the image that are modelled by a first model.
2. A method according to claim 1 , wherein said predetermined criterion is a relationship between said estimate of location of said features and said fit of said one of said second models.
3. A method according to claim 1 , further comprising:
fitting said first model to the image;
wherein said estimate of location of said features in the image is based upon said fit of said first model.
4. A method according to claim 1 , wherein fitting one of said plurality of second models to part of said image is based upon said estimate of location of the features.
5. A method according to claim 4 , wherein fitting said one of said plurality of second models to part of said image is initialised based upon said estimate of location of the features.
6. A method according to claim 1 , wherein said predetermined criterion comprises a geometric criterion.
7. A method according to claim 1 , wherein said predetermined criterion is determined for said one of said second models during a training phase, based upon a set of training images.
8. A method according to claim 7 , wherein said predetermined criterion is based upon a plurality of data items, each data item representing a fit of said one of said second models to a respective one of said training images.
9. A method according to claim 1 , wherein each of said plurality of second models has an associated predetermined criterion.
10. A computer program comprising computer readable instructions configured to cause a computer to carry out a method according to claim 1 .
11. A computer readable medium carrying a computer program according to claim 10 .
12. A computer apparatus for identifying features in an image, the apparatus comprising:
a memory storing processor readable instructions; and
a processor arranged to read and execute instructions stored in said memory;
wherein said processor readable instructions comprise instructions arranged to control the computer to carry out a method according to claim 1 .