Method and system for fuzzy clustering of images

An apparatus for clustering a set of N images into P final clusters, where N and P are integers, comprising:

• means for calculating at least one similarity measure Si,j between members of each pair of images, wherein Si,j represents the similarity measure between an ith image and an jth image with i and j being image indices and Si,j=Sj,i;
• means for calculating a total connectivity value for each of the images remaining to be clustered, a total connectivity value for each image being defined as a sum of a function f of the similarity measures associated with that image;
• means for identifying, from among said images remaining to be clustered, a maximum total connectivity value tmax corresponding to an image Imax, image Imax belonging to a current cluster C which initially includes all images remaining to be clustered;
• means for removing, from the current cluster C, at least one image based on at least one of its similarity measure with image Imax and its total connectivity value within the current cluster C;
• means for adding, to the current cluster C, images having a similarity measure that is greater than a threshold T3 with any image currently in cluster C;
• means for calculating, for each image within the current cluster C, a total connectivity value based on those images within cluster C;
• means for removing, from the current cluster C, those images having a total connectivity value less than a threshold T4, wherein said total connectivity value calculating step and said image removing step are repeated until no further images are removed to thereby establish the current cluster C as one of the final clusters;
• and
• means for removing all images in the current cluster C from further consideration, wherein one or more of said calculating steps, said identifying step, said removing steps, and said adding step are repeating until all N images are assigned to a final cluster.

A computer-readable medium having stored thereon a plurality of instructions, the plurality of instructions including instructions which, when executed by a processor, cause the processor to perform the steps of a method for clustering a set of N images into P final clusters, where N and P are integers comprising of:

• (a) calculating at least one similarity measure Si,j between members of each pair of images, wherein Si,j represents the similarity measure between an ith image and an jth image with i and j being image indices and Si,j=Sj,i;
• (b) calculating a total connectivity value for each of the images remaining to be clustered, a total connectivity value for each image being defined as a sum of a function f of the similarity measures associated with that image;
• (c) identifying, from among said images remaining to be clustered, a maximum total connectivity value Tmax corresponding to an image Imax, image Imax belonging to a current cluster C which initially includes all images remaining to be clustered;
• (d) removing, from the current cluster C, at least one image based on at least one of its similarity measure with image Imax and its total connectivity value within current cluster C;
• (e) adding, to the current cluster C, images having a similarity measure that is greater than a threshold T3 with any image currently in cluster C;
• (f) calculating, for each image within the current cluster C, a total connectivity value based on those images within C;
• (g) removing, from the current cluster C, those images having a total connectivity value less than a threshold T4;
• (h) repeating said steps (f) and (g) until no further images are removed to thereby establish the current cluster C as one of the final clusters;
• (i) removing all images in the current cluster C from further consideration;
• and
• (j) repeating steps (b)-(i) until all N images are assigned to a final cluster.