Automatic plant identification from photographs

Yanıkoğlu, Berrin and Aptoula, Erchan and Tırkaz, Çağlar (2014) Automatic plant identification from photographs. Machine Vision and Applications, 25 (6). pp. 1369-1383. ISSN 0932-8092 (Print) 1432-1769 (Online)

Full text not available from this repository. (Request a copy)


We present a plant identification system for automatically identifying the plant in a given image. In addition to common difficulties faced in object recognition, such as light, pose and orientation variations, there are further difficulties particular to this problem, such as changing leaf shapes according to plant age and changes in the overall shape due to leaf composition. Our system uses a rich variety of shape, texture and color features, some being specific to the plant domain. The system has achieved the best overall score in the ImageCLEF’12 plant identification campaign in both the automatic and human-assisted categories. We report the results of this system on the publicly available ImageCLEF’12 plant dataset, as well as the effectiveness of individual features. The results show 61 and 81 % accuracies in classifying the 126 different plant species in the top-1 and top-5 choices.
Item Type: Article
Uncontrolled Keywords: Plant identification, Leaf shape, Color image segmentation, Mathematical morphology
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Computer Science & Eng.
Faculty of Engineering and Natural Sciences
Depositing User: Berrin Yanıkoğlu
Date Deposited: 15 Oct 2014 16:10
Last Modified: 02 Aug 2019 10:29

Actions (login required)

View Item
View Item