Title :
Plant image retrieval using color and texture features
Author :
Kebapci, Hanife ; Yanikoglu, Berrin ; Unal, Gozde
Author_Institution :
Fac. of Eng. & Natural Sci., Sabanci Univ., Istanbul, Turkey
Abstract :
An application of content-based image retrieval is proposed for identifying plants, along with a preliminary implementation. The system takes a plant image as input and finds the matching plant from a plant image database and is intended to provide users a simple method to locate information about their house plants. Max-flow min-cut technique is used as the image segmentation method to extract the general structure of the plant. Various color and texture features extracted from the segmented plant region are used in matching images to the database. Results show that for 60% of the queries, the correct plant image is retrieved among the top-10 results, using a small database of 188 images.
Keywords :
biology computing; botany; content-based retrieval; feature extraction; image colour analysis; image matching; image retrieval; image segmentation; image texture; minimax techniques; visual databases; content-based image retrieval; feature extraction; image color; image database; image segmentation; image texture; max-flow min-cut technique; plant image database; plant image retrieval; Bicycles; Content based retrieval; Data mining; Histograms; Image databases; Image retrieval; Image segmentation; Information retrieval; Shape measurement; Spatial databases;
Conference_Titel :
Computer and Information Sciences, 2009. ISCIS 2009. 24th International Symposium on
Conference_Location :
Guzelyurt
Print_ISBN :
978-1-4244-5021-3
Electronic_ISBN :
978-1-4244-5023-7
DOI :
10.1109/ISCIS.2009.5291857
