<![CDATA[Image retrieval systems with a fast search process are still challenging for researchers. Fast search methods are one of the most important parts of image retrieval. One of the techniques used is reducing feature dimensions using the Locality Sensitivity Hashing (LSH) method. Apart from that, feature types and image extraction methods are selected. Image feature extraction uses the Convolutional Neural Network (CNN) method in this research. Measuring similarity using the Hamming Distance (HD) and Euclidean Distance (ED) methods. The datasets used are TenunIkatNet and Batik300. The LSH method forms a hash table as a bucket to group similar images based on probability and in the form of binary code. The research results show that the LSH+HD+ED method provides faster search results than ED. The image retrieval time for the LSH+HD+ED and ED methods is 0.252 seconds and 4.5 seconds, respectively, for the TenunIkatNet dataset. Meanwhile, the Batik300 dataset is 0.03 seconds and 0.9 seconds. Using the LSH method is very effective for large datasets. Retrieval accuracy using the LSH+HD+ED method was 99.705% and 84% for the TenunIkatNet and Batik300 datasets, respectively. Meanwhile, the ED method produces 94.17% and 82% retrieval accuracy, respectively.]]>
Copyrights © 2024
