Adopting hybrid descriptors to recognise leaf images for automatic plant specie identification

Al-kharaz, Ali A. and Tao, Xiaohui and Zhang, Ji and Lafta, Raid (2016) Adopting hybrid descriptors to recognise leaf images for automatic plant specie identification. In: 12th International Conference on Advanced Data Mining and Applications (ADMA 2016), 12-15 Dec 2016, Gold Coast, QLD, Australia.

[img]
Preview
Text (Accepted Version)
ADMA16.pdf

Download (610Kb) | Preview

Abstract

In recent years, leaf image recognition and classification has become one of the most important subjects in computer vision. Many approaches have been proposed to recognise and classify leaf images relying on features extraction and selection algorithms. In this paper, a concept of distinctive hybrid descriptor is proposed consisting of both global and local features. HSV Colour histogram (HSV-CH) is extracted from leaf images as the global features, whereas Local Binary Pattern after two level wavelet decomposition (WavLBP) is extracted to represent the local characteristics of leaf images. A hybrid method, namely “Hybrid Descriptor” (HD), is then proposed considering both the global and local features. The proposed method has been empirically evaluated using four data sets of leaf images with 256 × 256 pixels. Experimental results indicate that the performance of proposed method is promising – the HD outperformed typical leaf image recognising approaches as baseline models in experiments. The presented work makes clear, significant contribution to knowledge advancement in leaf recognition and image classification.


Statistics for USQ ePrint 30375
Statistics for this ePrint Item
Item Type: Conference or Workshop Item (Commonwealth Reporting Category E) (Paper)
Refereed: Yes
Item Status: Live Archive
Additional Information: Accepted version deposited in accordance with the copyright policy of the publisher.
Faculty / Department / School: Current - Faculty of Health, Engineering and Sciences - School of Agricultural, Computational and Environmental Sciences
Date Deposited: 16 Feb 2017 07:20
Last Modified: 03 Jan 2018 06:49
Uncontrolled Keywords: leaf image; local feature; global feature; colour histogram; texture; LBP; wavelet
Fields of Research : 08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080109 Pattern Recognition and Data Mining
08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080106 Image Processing
Socio-Economic Objective: E Expanding Knowledge > 97 Expanding Knowledge > 970108 Expanding Knowledge in the Information and Computing Sciences
Identification Number or DOI: 10.1007/978-3-319-49586-6_15
URI: http://eprints.usq.edu.au/id/eprint/30375

Actions (login required)

View Item Archive Repository Staff Only