Image region partitioning using pre-labeled regions
View Patent ↗A two pass Zone Of Influence (ZOI) creation method creates a Zone Of Influence (ZOI) image. The two pass ZOI creation method performs a first pass scan to create a first pass intermediate distance image and a shortest distance component label image. It then performs a second pass scan using the first pass intermediate distance image and the shortest distance component label image to create a background distance transform image and a updated shortest distance component label image. An adaptive image region partition method allows distance lengths of the two pass adaptive ZOI creation method depend on their associated component labels.
1. An adaptive image region partition method using a computer or processor to carry out the steps of:
a) Input a component labeled image and its associated characteristics for each component;
b) Perform an adaptive two pass ZOI creation method using the component labeled image and component characteristics to create an adaptive ZOI image using a length function I wherein a component specific weighting factor w is applied to the length function to generated a component weighted length:
l [( i,j ), Z ( i,j )]= l ( i,j )* w ( Z ( i,j ))
wherein w is a general function of component characteristics that is related to one of component size, component confidence, or types of components and Z(i,j) is component labeled image value at image position (i,j).
2. The adaptive image region partition method of claim 1 wherein the adaptive two pass ZOI creation step comprises the steps of:
a) Perform a first pass scan using the component labeled image and component characteristics to create a first pass intermediate adaptive distance image and an adaptive shortest distance component label image wherein the adaptive distance image having distance metric based on the component weighted length;
b) Perform a second pass scan using the first pass intermediate adaptive distance image and the adaptive shortest distance component label image to create an adaptive distance transform image and an updated adaptive shortest distance component label image wherein the adaptive distance transform image having distance metric based on the component weighted length.
3. An adaptive cell segmentation method using a computer or processor to carry out the steps of:
a) Input a nuclei mask image, its component labeled image and component characteristics;
b) Input a cell mask image;
c) Perform adaptive nuclei region partition using the nuclei mask component labeled image and component characteristics to create adaptive nuclei mask ZOI using a length function 1 wherein a component specific weighting factor w is applied to the length function to generate a component weighted length:
l [( i,j ), Z ( i,j )]= l ( i,j )* w ( Z ( i,j ))
wherein w is a general function of component characteristics that is related to one of component size, component confidence, or types of components and Z(i,j) is component labeled image value at image position (i,j);
d) Perform adaptive cell region separation using the cell masks and the adaptive nuclei mask ZOI to generate adaptive cell separated regions wherein the adaptive cell mask having the same component label in the nuclei mask ZOIs is considered as one cell region.