Olsen, Alex, Han, Sunghyu, Calvert, Brendan, Ridd, Peter, and Kenny, Owen (2015) In situ leaf classification using histograms of oriented gradients. In: Proceedings of the lnternational Conference on Digital lmage Computing: techniques and applications. pp. 441-448. From: DICTA 2015: lnternational Conference on Digital lmage Computing: techniques and applications, 23-25 Nov 2015, Adelaide, SA, Australia.

	PDF (Submitted Version) - Submitted Version Restricted to Repository staff only
	PDF (Published Version) - Published Version Restricted to Repository staff only

Abstract

Histograms of Oriented Gradients (HOGs) have proven to be a robust feature set for many visual object recognition applications. In this paper we investigate a simple but powerful approach to make use of the HOG feature set for in situ leaf classification. The contributions of this work are threefold. Firstly, we present a novel method for segmenting leaves from a textured background. Secondly, we investigate a scale and rotation invariant enhancement of the HOG feature set for texture based leaf classification - whose results compare well with a multi-feature probabilistic neural network classifier on a benchmark data set. And finally, we introduce an in situ data set containing 337 images of Lantana camara - a weed of national significance in the Australian landscape - and neighbouring flora, upon which our proposed classifier achieves high accuracy (86.07) in reasonable time and is thus viable for real-time detection and control of Lantana camara.

Item ID:	43004
Item Type:	Conference Item (Research - E1)
ISBN:	978-1-4673-6795-0
Keywords:	biology computing; botany; feature extraction; image classification; image segmentation; image texture; HOG feature; lantana camara; histograms-of-oriented gradients; in situ leaf classification; leave segmentation; rotation invariant enhancement; scale invariant enhancement; texture based leaf classification; textured background; visual object recognition; feature extraction; histograms; image color analysis; image segmentation; neural networks; real-time systems; shape
Related URLs:	https://researchonline.jcu.edu.au/65379/
Additional Information:	A version of this publication was included as Chapter 2 of the following PhD thesis: Olsen, Alex (2020) Improving the accuracy of weed species detection for robotic weed control in complex real-time environments. PhD thesis, James Cook University, which is available Open Access in ResearchOnline@JCU. Please see the Related URLs for access.
Date Deposited:	01 Mar 2016 03:42
FoR Codes:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080106 Image Processing @ 40% 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080104 Computer Vision @ 40% 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080108 Neural, Evolutionary and Fuzzy Computation @ 20%
SEO Codes:	96 ENVIRONMENT > 9604 Control of Pests, Diseases and Exotic Species > 960413 Control of Plant Pests, Diseases and Exotic Species in Farmland, Arable Cropland and Permanent Cropland @ 100%
Downloads:	Total: 10
	More Statistics