<![CDATA[Nowadays food is no longer just a basic necessity, but food has been used as an entertainment. As can be seen on social media, there a lots of photos of foods that attract our attention, thus force us to cook and made the food. To make food, a food recipe is needed. In general, food recipes can be found in magazines, television, newspaper, and websites. The recipe is searched by the name of the dish. The limitation of knowledge obout food's name, makes it difficult to find the recipes. By seeing this problem, we can use Content Based Image Retrieval (CBIR) to make the image as the query. Searching by using an image we need digital image processing to obtain the features of the image. The used features are red, green, and blue (RGB) color channel as the color feature, simple morphological shape descriptors as the shape feature, and k-NN as the classification method. The result of this research give the best n value n=5 where mean average precision (MAP) is 94,1892% on the combination of color and shape feature. The use of color and shape feature commonly obtain the best result on the combination of the both feature at n=10, n=15, n=20, dan n=25. The conclusion is when the higher value of n give the worst result of MAP and the use the combination of color and shape features can provide the best results compared using of one feature.]]>
Copyrights © 2019
