ISSN 22773061 985 | Page July 15, 2013 Comparing the impact of Clustering with Content Based Image Retrieval Approaches for Plant Identification Komal Asrani 1 , Renu Jain 2 1 B.B.D.N.I.T.M., Lucknow. komalasrani@rediffmail.com 2 U,I,E,T., Kanpur jainrenu@gmail.com Abstract Contour Based retrieval of images is an active and challenging field of research. Among various parameters available for contour based image retrieval, shape is considered an important aspect because it is closest to the human perception. Most of the shape based image retrieval methods require large processing time for generating accurate results due to huge database. To reduce the search time, we have divided the database into clusters on the basis of eccentricity of leaf using K-Means approach. After making the clusters, different contour based approaches are applied for leaf/plant identification and results are compared. The leaf image is processed to generate feature vectors which are stored in database. We have used Swedish leaf image database (SLID) consisting of 15 species with 75 leaves per class and total of 1125 leaf images. In this paper, we compare results of contour based retrieval approaches with and without clustering. From these results, it is found that by incorporating clustering, performance of contour based retrieval approaches remains same but retrieval time is reduced. Index Terms Contour Based Image Retrieval, Shape descriptors, Plant Identification, Clustering, Content Based Image Retrieval, Leaf recognition, Image Retrieval. ACADEMIC DISCIPLINE AND SUB-DISCIPLINES Computer Science (Image Processing) SUBJECT CLASSIFICATION Image Processing and Retrieval TYPE (METHOD/APPROACH) Experimental Council for Innovative Research Peer Review Research Publishing System Journal: INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY Vol 9, No 1 editor@cirworld.com www.cirworld.com, member.cirworld.com