(IJCST-V4I3P40) :chaitali Dhaware, Mrs. K. H. Wanjale
(IJCST-V4I3P40) :chaitali Dhaware, Mrs. K. H. Wanjale
(IJCST-V4I3P40) :chaitali Dhaware, Mrs. K. H. Wanjale
RESEARCH ARTICLE
OPEN ACCESS
ABSTRACT
Classification is the vital and challenging task in co mputer science. Classification is based on the description, texture or
similarity of items or things. Image classification considers two approaches - supervised classification and unsupervised
classification. Pixels are the unit represented in an image. Image classification groups the pixels in different classes. The imag e
classification includes- image acquisition, image pre-processing, image segmentation. So me image classification methods areSupport Vector Machine (SVM), Artificial Neural Network (ANN) and Decision Tree (DT).
Keywords: - Image Processing, Support Vector Machine (SVM), Artificial Neural Network (ANN) and Decision Tree (DT).
I.
INTRODUCTION
II.
RELATED WORK
ISSN: 2347-8578
III.
www.ijcstjournal.org
Page 246
International Journal of Computer Science Trends and Technology (IJCS T) Volume 4 Issue 3, May - Jun 2016
c.
the
important
IV.
IMAGE CLASSIFICATION
METHODS
Method
Advantages
Disadvantages
1.Support
Vector
Machine
Deliver unique
solution.
Very efficient
than other
methods.
Avoid overfitting
Robust to
noisy training
dataset
Very efficient
for large
dataset
Require little
efforts from
users
Easy to
interpret and
explain
2.
Artificial
Neural
Network
3.
Decision
Tree
VI.
High
algorith m
complexity
Run slowly
High
computational
cost
Lazy learner
Splits are
very sensitive
to training
data set
High
classification
error rate
CONCLUSIONS
REFERENCES
V.
COMPARISON OF METHODS
ISSN: 2347-8578
[1]
[2]
www.ijcstjournal.org
Page 247
International Journal of Computer Science Trends and Technology (IJCS T) Volume 4 Issue 3, May - Jun 2016
Semiconductor Manufacturing, Vo l. 27, No. 2, May
2014.
[3] Monica Bianchini and Franco Scarselli, On the
Co mplexity
of
Neu ral
Network
Classifiers:A
Co mparison Between Shallow and Deep Architectures,
IEEE Transactions On Neural Networks And Learning
Systems, Vol. 25, No. 8, August 2014.
[4] Alessandro Bergamo and Lo renzo Torresani, Classemes
and Other Classifier-Based Features for Efficient Ob ject
Categorization, IEEE Transactions On Pattern Analysis
And Machine Intelligence, Vol. 36, No. 10, October
2014.
[5] Serafeim Moustakidis, Giorgos Mallinis, Nikos Koutsias,
John B. Theocharis and Vasilios Petrid is, SVM -Based
Fuzzy Decision Trees for Classification of High Spatial
Resolution Remote Sensing Images, IEEE Transactions
On Geoscience And Remote Sensing, Vol. 50, No. 1,
January 2012
[6] Lizhen Lu, Lip ing Di, Senior and Yan mei Ye, A
Decision-Tree Classifier for Ext racting Transparent
Plastic-Mulched Landcover fro m Landsat-5 TM
Images, IEEE Journal Of Selected Topics In Applied
Earth Observations And Remote Sensing, Vo l. 7, No. 11,
November 2014.
[7] Cheng-Hsuan Li, Bor-Chen Kuo, Ch in-Teng Lin and
Chih-Sheng Huang, A SpatialContextual Support
Vector Machine for Remotely Sensed Image
Classification, IEEE Transactions On Geoscience And
Remote Sensing, Vol. 50, No. 3, March 2012.
[8] Chiming Chang,Paul-Armand Verhaegen, and Joost R.
Duflou, A Co mparison of Classifiers for Intelligent
Machine Usage Prediction, IEEE Transaction Machine
Learning, 2014.
[9] Sri-Kaushik Pavani, Federico M. Sukno, David DelgadoGo mez, Constantine Butakoff, Xavier Planes, and
Alejandro F. Frangi, An Experimental Evaluation of
Three Classifiers for Use in Self-Updating Face
Recognition Systems, IEEE Transactions On
Information Forensics And Security, Vo l. 7, No. 3, June
2012.
[10] Donglian Sun, Yunyue Yu , and M itchell D. Go ldberg,
Deriving Water Fraction and Flood Maps Fro m M ODIS
Images Using a Decision Tree Approach, IEEE
Transaction On Applied Earth Observations And Remote
Sensing, Vol. 4, No. 4, December 2011.
[11] Fuliang Wang And Feng Wang, Void Detection in
TSVs With X-Ray Image Mult ithreshold Segmentation
and Artificial Neural Networks, IEEE TRANSACTIONS
ON
C OMPONENTS,
PACKAGIN G
AND
ISSN: 2347-8578
[12]
[13]
[14]
[15]
www.ijcstjournal.org
Page 248