DocumentCode :
183238
Title :
A Novel Feature Selection and Extraction Technique for Classification
Author :
Goel, Kratarth ; Vohra, Raunaq ; Bakshi, Ankita
Author_Institution :
Dept. of Comput. Sci., BITS Pilani Goa, Pilani, India
fYear :
2014
fDate :
1-4 Sept. 2014
Firstpage :
104
Lastpage :
109
Abstract :
Pattern recognition is a vast field which has seen significant advances over the years. As the datasets under consideration grow larger and more comprehensive, using efficient techniques to process them becomes increasingly important. We present a versatile technique for the purpose of feature selection and extraction - Class Dependent Features (CDFs). CDFs identify the features innate to a class and extract them accordingly. The features thus extracted are relevant to the entire class and not just to the individual data item. This paper focuses on using CDFs to improve the accuracy of classification and at the same time control computational expense by tackling the curse of dimensionality. In order to demonstrate the generality of this technique, it is applied to two problem statements which have very little in common with each other - handwritten digit recognition and text categorization. It is found that for both problem statements, the accuracy is comparable to state-of-the-art results and the speed of the operation is considerably greater. Results are presented for Reuters-21578 and Web-KB datasets relating to text categorization and the MNIST and USPS datasets for handwritten digit recognition.
Keywords :
feature extraction; feature selection; handwritten character recognition; image classification; text analysis; CDFs; MNIST datasets; Reuters-21578 datasets; USPS datasets; Web-KB datasets; class dependent features; classification; curse of dimensionality; feature extraction; feature selection; handwritten digit recognition; pattern recognition; text categorization; Accuracy; Feature extraction; Handwriting recognition; Support vector machines; Text categorization; Text recognition; Vectors; Hand-written Digit Recognition; MNIST; Pattern Recognition; Reuters-21578; SVM; Text Categorization; USPS; WebKB;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Frontiers in Handwriting Recognition (ICFHR), 2014 14th International Conference on
Conference_Location :
Heraklion
ISSN :
2167-6445
Print_ISBN :
978-1-4799-4335-7
Type :
conf
DOI :
10.1109/ICFHR.2014.25
Filename :
6981004
Link To Document :
بازگشت