Method of image segmentation
View Patent ↗A method of processing of photo and video images is disclosed which searches for a minimum of cost functions carried out at an N-number of image detail levels, from coarser to finer, and at each image detail level the image is divided into regions; each region is assigned a single segmentation value by a η-number of successive iterations. The value of the cost function for the seams at the region boundaries is calculated with different types of image segmentation, and for every region a segmentation value is chosen which minimizes the sum of the cost functions of the seams and data. The technical result is the segmentation of an image with little use of the memory resources of a mobile device while maintaining both resistance to image noise and operating speed.
1. The image segmentation method comprising of search for an optimum of the cost functions, wherein:
the search is carried out at an N-number of image detail levels, from coarser to finer;
at each image detail level the image is divided (segmented) into regions;
each region is assigned a single segmentation value by means of an n-number of successive iterations;
at each iteration the value of the cost function for the seams at the region boundaries is calculated for different versions of image segmentation;
for every region a segmentation value is chosen which optimizes the combination of the cost functions of the seams and data.
2. A method according to claim 1 , wherein the search for an optimum at each iteration is executed through processing of the image regions which do not have common boundaries, and the choice of regions for processing is changed for each iteration.
3. The method according to claim 1 , wherein the input of the cost function of seams into the combination of the cost functions of the data and seams is reduced in subset of the iterations.
4. The method according to claim 1 , wherein optimum of the cost functions is searched as minimum of cost functions.
5. The method according to claim 1 , wherein combination of cost functions of the seams and data is arithmetic summation.