Open AccessALGORITMA NON-PHOTOREALISTIC RENDERING UNTUK KARTUN MENGGUNAKAN K-MEANS DAN CANNY
Author(s) -
Budiman Baso,
Irit Maulana Sapta,
Saniyatul Mawaddah
Publication year - 2021
Publication title -
journal of information and technology
Language(s) - English
Resource type - Journals
ISSN - 2775-2720
DOI - 10.32938/jitu.v1i1.888
Subject(s) - computer science , computer vision , artificial intelligence , computer graphics (images) , rendering (computer graphics) , cluster analysis , visualization , k means clustering
Cartoons are one type of illustration usually in a non-realistic or semi-realistic style. To make a cartoon drawing manually requires good drawing ability. So, not everyone can make cartoons. This research proposes a non-photorealistic rendering algorithm to create cartoon drawings automatically. The algorithm consists of four phases. First, create an image abstraction using bilateral filtering. Second, using kmeans clustering for abstract image quantization. Third, get the contour lines of the drawing using the canny algorithm. Fourth, contour lines and quantized images are combined. The results show that this algorithm can produce good visualization of cartoon images.