Contribution to Segmentation of Digital Images Based on Clustering Jraj Horvath DepartmentofCybeetics andArtiialIntelligence FacutyofElecricalEngineeringandInfoatics TechnicalniversityofKsice Lea9, 04200Koice,Slovakia Juraj.Hovath@tuke.sk Ladislav Madrasz DeparentofCybeeticsand ticiaIntelligene FacultyoEleccalEngineeringandInfonatcs Tecncalniversityo Kice Letn 9, 04200 Kosice,Slovaka Ladislav.Madarasz@tuke.sk A- In this work are described methods of segmentation of digital images based on clustering. As clustering method was chosen fuzzy c-means clustering method, but these methods of segmentation are not restricted only to fuzzy c means. In these methods of segmentation can be used any clustering method, which respects some rules. Colour perception by humans is also important part of this contribution. s a logical consequence of colour perception is L*u*v* colour ,which is also deined and described. It is described L*u*v* transformation and application of this transformation in image segmentation. First of all is mathematical definition of partial segmentation required for introduced segmentations' methods. I.INTRODCTION Imagesegmentationwas,is andwillbamaor research toc or man image roessing researhers. he reasons areobviousandapplicationscountendless. Mostcomputer vsion and imageanasis proemsreuire a sementaion stage in order o detect oects or divide the image into regions, whch can be considered homogeneous according toa given criterion, sucha colour, motion, texture, etc [2, 3 . Sometime is necessary to adust computer vision to human vison. Especially is it necessa, when we are sementing images. which were semented by people and we y to repace people with computers o when we want o he people n semenation of iages. Typical appicaion s meicine, e.g. sementation oI images ordenatological images 2,3. II.PARTIALSEGENAIONDEFINITION For claim of methods is necessay to express more mathematically exactly artial sementation.which is not exactlymathematicallydenedin2.3, 10. Let I mars digtal image of rectangular shape. Let image 1 has wid w and height h. Let a E I, = {1,2, ... , w}, j= 1,2, . . . , h} marks pixel of image I(in general pixel can be a vectorof vaues). Let R;  I 0-7803-8588-8/4/$20.00 24EEE. Iveta Zolotova Deparent of CybeticsanAicial Intlligence Facultyof Elecical Engineering andInfoatics TechnicalniversityofKosice Lea 9, 04200Koice,Slovakia Iveta.Zolotova@tuke.sk marks segment, let segment's numer is M. Let H marks homogenous criterion, let homoenous criterion is biny (itcanreachonytwovalues)4, 10 { I> argumetaccomplishriterion H=  argumennot accomplishcriterion (I) Digita images segmentation is process f dividing imageI tonotoverappingsemens R;. Eachement R; accompish homogenous crierion H and at the same time or each neighong sements R  applis, that by homogenous criteron uniting nghbong seent Rj and sement R; wilecreaed not homogenous sement. Semnt R, i part o imae I, which was created in process o seentaion. Dgitl image segmentation is process, which rest accomplish next oitions 2, 3, 4, 10 89 ;=1 V n,m E {I, 2, . . . , M}, n'm : R Ó R = 0 V n E {I. 2, ... , M}: H( R n) = 1  n.m E {I, 2 .. ... M}, n,m,R and R, whicareebours:H(Rn U R ) = 0 III. ANS COLORPERCEPTION (2 ) (3) (4 ) (5) n human ee are hree ierent sensors for colour perception. These receptors are called cones. Eveyone om these receptors hae dierent visal pient, which respods on photos. One pigment has mimm sensiliy on waeleng of 455 nometres (blue pment), seononwavelen o535 nanomees (een pigment) and third has maximum on wavelength of 570 nomeres(redpient). Curvescorrespondedo sensibilityofeachpimentwere gotexperimentalandweregotom[8.