Open AccessFleckmentation: rapid segmentation using repeated 2‐means
Author(s) -
Rasche Christoph
Publication year - 2019
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2018.6060
Subject(s) - computer science , task (project management) , segmentation , frame (networking) , artificial intelligence , process (computing) , image segmentation , image (mathematics) , decomposition , pattern recognition (psychology) , computer vision , image processing , scale space segmentation , ecology , management , economics , biology , operating system , telecommunications
A procedure for segmentation is introduced that uses the K ‐means algorithm to decompose an image by recursively applying the K ‐means with k = 2 . This 2‐means decomposition procedure finds any region that corresponds to a scene part, but it is also prone to oversegmentation. The procedure has already been used in two tasks previously: a scene classification task and a foreground–background segregation task (skin lesion detection). Here, the authors explain its operation in more detail and analyse its lower performance. It is sufficient to apply the procedure with only three to four recursions, making the process of almost minimal complexity O ( n 5 ) in case of four recursions. It is thus suitable for large‐image analysis and frame processing.