Oak leaf classification: an analysis of features and classifiers

Heysem Kaya; Ilhan Keklik; Tolga Ensari; Fatih Alkan; Yagmur Biricik

doi:10.1109/EBBT.2019.8742053

Oak leaf classification: an analysis of features and classifiers

Heysem Kaya
, Ilhan Keklik
, Tolga Ensari
, Fatih Alkan
, Yagmur Biricik

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Automatic classification of trees from leaves is a popular computer vision/machine learning task and has important applications in monitoring of forest wealth. While the final aim is preparing an application, which is capable of visual signal processing and classification, in this paper we present a new oak leaf dataset and preliminary results for classification of 8 types of oak trees. The novelties include comparative analysis of a small set of hand-crafted geometric features and popularly used high-dimensional appearance features, such as Local Binary Patterns (LBP) and Histograms of Oriented Gradients (HOG). We further compare commonly used Support Vector Machines (SVM) classifier with a recently popular, fast and robust learner called Extreme Learning Machines (ELM). Results indicate that a small set of geometric features reach an accuracy of 75%, while high dimensional appearance features can boost the performance up to92%.

Original language	English
Title of host publication	Scientific Meeting on Electrical-Electronics and Biomedical Engineering and Computer Science, EBBT 2019
Publisher	IEEE
ISBN (Electronic)	9781728110134
DOIs	https://doi.org/10.1109/EBBT.2019.8742053
Publication status	Published - 1 Apr 2019
Externally published	Yes
Event	2019 Scientific Meeting on Electrical-Electronics and Biomedical Engineering and Computer Science, EBBT 2019 - Istanbul, Turkey Duration: 24 Apr 2019 → 26 Apr 2019

Conference

Conference	2019 Scientific Meeting on Electrical-Electronics and Biomedical Engineering and Computer Science, EBBT 2019
Country/Territory	Turkey
City	Istanbul
Period	24/04/19 → 26/04/19

Keywords

Classificaiton
Extreme Learning Machines (ELM)
HOG
LBP

Access to Document

10.1109/EBBT.2019.8742053

Cite this

@inproceedings{5c6aa3ecaaaf4b82a427fc96575e4a60,

title = "Oak leaf classification: an analysis of features and classifiers",

abstract = "Automatic classification of trees from leaves is a popular computer vision/machine learning task and has important applications in monitoring of forest wealth. While the final aim is preparing an application, which is capable of visual signal processing and classification, in this paper we present a new oak leaf dataset and preliminary results for classification of 8 types of oak trees. The novelties include comparative analysis of a small set of hand-crafted geometric features and popularly used high-dimensional appearance features, such as Local Binary Patterns (LBP) and Histograms of Oriented Gradients (HOG). We further compare commonly used Support Vector Machines (SVM) classifier with a recently popular, fast and robust learner called Extreme Learning Machines (ELM). Results indicate that a small set of geometric features reach an accuracy of 75\%, while high dimensional appearance features can boost the performance up to92\%.",

keywords = "Classificaiton, Extreme Learning Machines (ELM), HOG, LBP",

author = "Heysem Kaya and Ilhan Keklik and Tolga Ensari and Fatih Alkan and Yagmur Biricik",

year = "2019",

month = apr,

day = "1",

doi = "10.1109/EBBT.2019.8742053",

language = "English",

booktitle = "Scientific Meeting on Electrical-Electronics and Biomedical Engineering and Computer Science, EBBT 2019",

publisher = "IEEE",

address = "United States",

note = "2019 Scientific Meeting on Electrical-Electronics and Biomedical Engineering and Computer Science, EBBT 2019 ; Conference date: 24-04-2019 Through 26-04-2019",

}

Kaya, H, Keklik, I, Ensari, T, Alkan, F & Biricik, Y 2019, Oak leaf classification: an analysis of features and classifiers. in Scientific Meeting on Electrical-Electronics and Biomedical Engineering and Computer Science, EBBT 2019., 8742053, IEEE, 2019 Scientific Meeting on Electrical-Electronics and Biomedical Engineering and Computer Science, EBBT 2019, Istanbul, Turkey, 24/04/19. https://doi.org/10.1109/EBBT.2019.8742053

TY - GEN

T1 - Oak leaf classification

T2 - 2019 Scientific Meeting on Electrical-Electronics and Biomedical Engineering and Computer Science, EBBT 2019

AU - Kaya, Heysem

AU - Keklik, Ilhan

AU - Ensari, Tolga

AU - Alkan, Fatih

AU - Biricik, Yagmur

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Automatic classification of trees from leaves is a popular computer vision/machine learning task and has important applications in monitoring of forest wealth. While the final aim is preparing an application, which is capable of visual signal processing and classification, in this paper we present a new oak leaf dataset and preliminary results for classification of 8 types of oak trees. The novelties include comparative analysis of a small set of hand-crafted geometric features and popularly used high-dimensional appearance features, such as Local Binary Patterns (LBP) and Histograms of Oriented Gradients (HOG). We further compare commonly used Support Vector Machines (SVM) classifier with a recently popular, fast and robust learner called Extreme Learning Machines (ELM). Results indicate that a small set of geometric features reach an accuracy of 75%, while high dimensional appearance features can boost the performance up to92%.

AB - Automatic classification of trees from leaves is a popular computer vision/machine learning task and has important applications in monitoring of forest wealth. While the final aim is preparing an application, which is capable of visual signal processing and classification, in this paper we present a new oak leaf dataset and preliminary results for classification of 8 types of oak trees. The novelties include comparative analysis of a small set of hand-crafted geometric features and popularly used high-dimensional appearance features, such as Local Binary Patterns (LBP) and Histograms of Oriented Gradients (HOG). We further compare commonly used Support Vector Machines (SVM) classifier with a recently popular, fast and robust learner called Extreme Learning Machines (ELM). Results indicate that a small set of geometric features reach an accuracy of 75%, while high dimensional appearance features can boost the performance up to92%.

KW - Classificaiton

KW - Extreme Learning Machines (ELM)

KW - HOG

KW - LBP

UR - https://www.scopus.com/pages/publications/85068570413

U2 - 10.1109/EBBT.2019.8742053

DO - 10.1109/EBBT.2019.8742053

M3 - Conference contribution

BT - Scientific Meeting on Electrical-Electronics and Biomedical Engineering and Computer Science, EBBT 2019

PB - IEEE

Y2 - 24 April 2019 through 26 April 2019

ER -

Oak leaf classification: an analysis of features and classifiers

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this