Plant image retrieval using color, shape and texture features

Kebapcı, Hanife and Yanıkoğlu, Berrin and Ünal, Gözde (2011) Plant image retrieval using color, shape and texture features. Computer Journal (SI), 54 (9). pp. 1475-1490. ISSN 0010-4620

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader

Official URL: http://dx.doi.org/10.1093/comjnl/bxq037


We present a content-based image retrieval system for plant image retrieval, intended especially for the house plant identification problem. A plant image consists of a collection of overlapping leaves and possibly flowers, which makes the problem challenging.We studied the suitability of various well-known color, shape and texture features for this problem, as well as introducing some new texture matching techniques and shape features. Feature extraction is applied after segmenting the plant region from the background using the max-flow min-cut technique. Results on a database of 380 plant images belonging to 78 different types of plants show promise of the proposed new techniques and the overall system: in 55% of the queries, the correct plant image is retrieved among the top-15 results. Furthermore, the accuracy goes up to 73% when a 132-image subset of well-segmented plant images are considered.

Item Type:Article
Uncontrolled Keywords:image retrieval; plants; Gabor wavelets; SIFT
Subjects:Q Science > QA Mathematics > QA075 Electronic computers. Computer science
ID Code:14086
Deposited By:Berrin Yanıkoğlu
Deposited On:30 Jun 2010 11:27
Last Modified:25 Jul 2019 10:36

Repository Staff Only: item control page