<![CDATA[The existing food recipe search application only uses text queries. Text queries often does not represent everything the user wants and cannot be done if user only knows food images. Solution offered to overcome this problem is make food recipe search using food image. Image search is done by measuring similarity between query image features and corpus image features. Features image are obtained by extracting Simple Morphological Shape Descriptors and Color Moment features. After feature extraction, similarity measurements are carried out using Euclidean Distance. Then system display search results which are as many as n images that have the greatest degree of similarity. The results of this study indicate the highest MAP value at k-rank 10 is 95.713% and the lowest MAP value is at k-rank 100 is 76.108%. Color Moment feature is better than Simple Morphological Shape Descriptors because MAP Color Moment value is higher at 93.32% than the Simple Morphological Shape Descriptors is 89.8%. Merging of the two features proved to be able to increase MAP value. It can be concluded that at k-rank 10 system returns good results according to user requirements and the use of the two merged features can overcome disadvantages of using each feature.]]>
Copyrights © 2019
