Fynbos leaf online plant recognition application

Simon Winberg; Shaun Katz; Amit Kumar Mishra

doi:10.1109/NCVPRIPG.2013.6776220

Fynbos leaf online plant recognition application

Simon Winberg, Shaun Katz, Amit Kumar Mishra

University of Cape Town

Research output: Contribution to conference › Paper › peer-review

4 Citations (Scopus)

Abstract

Computer-aided plant identification combines computer vision and pattern recognition. The Cape Floristic Kingdom is the most varied of plant kingdoms, comprising thousands of species of fynbos plants. While it is easier to classify fynbos when they are flowering, mostly flower for only a few weeks in a year. This paper concerns an image processing application for automatic identification of certain fynbos using leaf photographs. The architecture of this application is overviewed prior to focusing on the leaf recognition operations, and how these were experimentally tested using a series of experiments, culminating in a comprehensive test to measure identification accuracy, effectiveness of the online user interface, and the processing speed. Our conclusions reflect on the overall effectiveness of the application and our plans to take it further.

Original language	English
DOIs	https://doi.org/10.1109/NCVPRIPG.2013.6776220
Publication status	Published - 18 Dec 2013
Externally published	Yes
Event	2013 4th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2013 - Jodhpur, Rajasthan, India Duration: 18 Dec 2013 → 21 Dec 2013

Conference

Conference	2013 4th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2013
Country/Territory	India
City	Jodhpur, Rajasthan
Period	18 Dec 2013 → 21 Dec 2013

Keywords

computer vision
digital morphological features
fynbos
image procesing
leaf database
plant recognition

Access to Document

10.1109/NCVPRIPG.2013.6776220

Permanent link

Persistent link

Cite this

@conference{ca82b0cd3f6743ada39249cc980fc5e4,

title = "Fynbos leaf online plant recognition application",

abstract = "Computer-aided plant identification combines computer vision and pattern recognition. The Cape Floristic Kingdom is the most varied of plant kingdoms, comprising thousands of species of fynbos plants. While it is easier to classify fynbos when they are flowering, mostly flower for only a few weeks in a year. This paper concerns an image processing application for automatic identification of certain fynbos using leaf photographs. The architecture of this application is overviewed prior to focusing on the leaf recognition operations, and how these were experimentally tested using a series of experiments, culminating in a comprehensive test to measure identification accuracy, effectiveness of the online user interface, and the processing speed. Our conclusions reflect on the overall effectiveness of the application and our plans to take it further.",

keywords = "computer vision, digital morphological features, fynbos, image procesing, leaf database, plant recognition",

author = "Simon Winberg and Shaun Katz and Mishra, {Amit Kumar}",

year = "2013",

month = dec,

day = "18",

doi = "10.1109/NCVPRIPG.2013.6776220",

language = "English",

note = "2013 4th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2013 ; Conference date: 18-12-2013 Through 21-12-2013",

}

TY - CONF

T1 - Fynbos leaf online plant recognition application

AU - Winberg, Simon

AU - Katz, Shaun

AU - Mishra, Amit Kumar

PY - 2013/12/18

Y1 - 2013/12/18

N2 - Computer-aided plant identification combines computer vision and pattern recognition. The Cape Floristic Kingdom is the most varied of plant kingdoms, comprising thousands of species of fynbos plants. While it is easier to classify fynbos when they are flowering, mostly flower for only a few weeks in a year. This paper concerns an image processing application for automatic identification of certain fynbos using leaf photographs. The architecture of this application is overviewed prior to focusing on the leaf recognition operations, and how these were experimentally tested using a series of experiments, culminating in a comprehensive test to measure identification accuracy, effectiveness of the online user interface, and the processing speed. Our conclusions reflect on the overall effectiveness of the application and our plans to take it further.

AB - Computer-aided plant identification combines computer vision and pattern recognition. The Cape Floristic Kingdom is the most varied of plant kingdoms, comprising thousands of species of fynbos plants. While it is easier to classify fynbos when they are flowering, mostly flower for only a few weeks in a year. This paper concerns an image processing application for automatic identification of certain fynbos using leaf photographs. The architecture of this application is overviewed prior to focusing on the leaf recognition operations, and how these were experimentally tested using a series of experiments, culminating in a comprehensive test to measure identification accuracy, effectiveness of the online user interface, and the processing speed. Our conclusions reflect on the overall effectiveness of the application and our plans to take it further.

KW - computer vision

KW - digital morphological features

KW - fynbos

KW - image procesing

KW - leaf database

KW - plant recognition

UR - http://www.scopus.com/inward/record.url?scp=84898777259&partnerID=8YFLogxK

U2 - 10.1109/NCVPRIPG.2013.6776220

DO - 10.1109/NCVPRIPG.2013.6776220

M3 - Paper

AN - SCOPUS:84898777259

T2 - 2013 4th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2013

Y2 - 18 December 2013 through 21 December 2013

ER -

Fynbos leaf online plant recognition application

Abstract

Conference

Keywords

Access to Document

Permanent link

Other files and links

Fingerprint

Cite this