Koi varieties identification based zero parameter simple linear iterative clustering and support vector machine

There’s currently 120 types of koi fish that has been bred around the
world. The types of koi fish depend on the colour patterns and shapes they have.
There’s alot of patterns that has similarity between one type with another. For
example, sanke and showa koi fish will look similar from a non-expert’s point of
view, because both type has same colour pattern, which is red, black and white. In
actuality, sanke koi is dominantly red and white with slight black accent, while
showa’s dominant colour is red and black, with white accent. In this research, Zero
Parameter Simple Linear Iterative Clustering (SLICO) method and Simple Linear
Iterative Clustering (SLIC) will be tested and used to process the image
segmentation process to eliminate the background of the image. Colour Local
Binary Pattern method is used to get the textures on images through the RGB, HSV,
and grayscale colour space. Support Vector Machine is used to identify types of koi
fish. To test the SVM, two kind of kernel is used, which is linear kernel and Radial
Basis Function (RBF) kernel. The results of this study are the program able to
recognize types of koi from images. The test results show an accuracy of 36% in
grayscale colour space, 50% in RGB colour space, and 48% in HSV colour space.