A Novel Shape based Descriptor for Plant Identification

Content based image retrieval is one of the most challenging field in which widespread research is been carried out. In this paper, a modified and effective shape based leaf image retrieval system is presented for leaf identification. The method proposed is an extension of centroid distance method. The major drawbacks of the centroid distance approach are identified and resolved in our proposed approach. This approach, called Quad Centroid Distance Variation (QCDV) uses the concept of shape based image retrieval approach. Four values are computed and used as the feature vectors. The proposed approach effectively manages the size of the feature vectors, is computationally simple and affine invariant. Experiments were conducted on Swedish Leaf Image Database (SLID). The results justify the superior performance of the method even though the feature vector representing the image is very small.