Experiments of Distance Measurements in a Foliage Plant Retrieval System
This work addresses the specific challenge of improving retrieval accuracy for foliage plant identification, but it is incremental as it applies standard distance measures to a new dataset.
The paper tackled the problem of selecting a distance measure for a foliage plant image retrieval system, testing seven measures on 60 plant types and finding that city block and Euclidean distances performed best.
One of important components in an image retrieval system is selecting a distance measure to compute rank between two objects. In this paper, several distance measures were researched to implement a foliage plant retrieval system. Sixty kinds of foliage plants with various leaf color and shape were used to test the performance of 7 different kinds of distance measures: city block distance, Euclidean distance, Canberra distance, Bray-Curtis distance, x2 statistics, Jensen Shannon divergence and Kullback Leibler divergence. The results show that city block and Euclidean distance measures gave the best performance among the others.