A Novel Two-Stage Spectrum-Based Approach for Dimensionality Reduction: A Case Study on the Recognition of Handwritten Numerals
Dimensionality reduction (feature selection) is an important step in pattern recognition systems. Although there are different conventional approaches for feature selection, such as Principal Component Analysis, Random Projection, and Linear Discriminant Analysis, selecting optimal, effective, and r...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2014-01-01
|
| Series: | Journal of Applied Mathematics |
| Online Access: | http://dx.doi.org/10.1155/2014/654787 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832564158676074496 |
|---|---|
| author | Mohammad Amin Shayegan Saeed Aghabozorgi Ram Gopal Raj |
| author_facet | Mohammad Amin Shayegan Saeed Aghabozorgi Ram Gopal Raj |
| author_sort | Mohammad Amin Shayegan |
| collection | DOAJ |
| description | Dimensionality reduction (feature selection) is an important step in pattern recognition systems. Although there are different conventional approaches for feature selection, such as Principal Component Analysis, Random Projection, and Linear Discriminant Analysis, selecting optimal, effective, and robust features is usually a difficult task. In this paper, a new two-stage approach for dimensionality reduction is proposed. This method is based on one-dimensional and two-dimensional spectrum diagrams of standard deviation and minimum to maximum distributions for initial feature vector elements. The proposed algorithm is validated in an OCR application, by using two big standard benchmark handwritten OCR datasets, MNIST and Hoda. In the beginning, a 133-element feature vector was selected from the most used features, proposed in the literature. Finally, the size of initial feature vector was reduced from 100% to 59.40% (79 elements) for the MNIST dataset, and to 43.61% (58 elements) for the Hoda dataset, in order. Meanwhile, the accuracies of OCR systems are enhanced 2.95% for the MNIST dataset, and 4.71% for the Hoda dataset. The achieved results show an improvement in the precision of the system in comparison to the rival approaches, Principal Component Analysis and Random Projection. The proposed technique can also be useful for generating decision rules in a pattern recognition system using rule-based classifiers. |
| format | Article |
| id | doaj-art-eccd658298104b0ba1728f90c77da437 |
| institution | Kabale University |
| issn | 1110-757X 1687-0042 |
| language | English |
| publishDate | 2014-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Applied Mathematics |
| spelling | doaj-art-eccd658298104b0ba1728f90c77da4372025-02-03T01:11:45ZengWileyJournal of Applied Mathematics1110-757X1687-00422014-01-01201410.1155/2014/654787654787A Novel Two-Stage Spectrum-Based Approach for Dimensionality Reduction: A Case Study on the Recognition of Handwritten NumeralsMohammad Amin Shayegan0Saeed Aghabozorgi1Ram Gopal Raj2Image Processing and Pattern Recognition Research Lab, R&D Center, Department of Artificial Intelligence, Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kuala Lumpur, MalaysiaDepartment of Information System, Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kuala Lumpur, MalaysiaDepartment of Artificial Intelligence, Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kuala Lumpur, MalaysiaDimensionality reduction (feature selection) is an important step in pattern recognition systems. Although there are different conventional approaches for feature selection, such as Principal Component Analysis, Random Projection, and Linear Discriminant Analysis, selecting optimal, effective, and robust features is usually a difficult task. In this paper, a new two-stage approach for dimensionality reduction is proposed. This method is based on one-dimensional and two-dimensional spectrum diagrams of standard deviation and minimum to maximum distributions for initial feature vector elements. The proposed algorithm is validated in an OCR application, by using two big standard benchmark handwritten OCR datasets, MNIST and Hoda. In the beginning, a 133-element feature vector was selected from the most used features, proposed in the literature. Finally, the size of initial feature vector was reduced from 100% to 59.40% (79 elements) for the MNIST dataset, and to 43.61% (58 elements) for the Hoda dataset, in order. Meanwhile, the accuracies of OCR systems are enhanced 2.95% for the MNIST dataset, and 4.71% for the Hoda dataset. The achieved results show an improvement in the precision of the system in comparison to the rival approaches, Principal Component Analysis and Random Projection. The proposed technique can also be useful for generating decision rules in a pattern recognition system using rule-based classifiers.http://dx.doi.org/10.1155/2014/654787 |
| spellingShingle | Mohammad Amin Shayegan Saeed Aghabozorgi Ram Gopal Raj A Novel Two-Stage Spectrum-Based Approach for Dimensionality Reduction: A Case Study on the Recognition of Handwritten Numerals Journal of Applied Mathematics |
| title | A Novel Two-Stage Spectrum-Based Approach for Dimensionality Reduction: A Case Study on the Recognition of Handwritten Numerals |
| title_full | A Novel Two-Stage Spectrum-Based Approach for Dimensionality Reduction: A Case Study on the Recognition of Handwritten Numerals |
| title_fullStr | A Novel Two-Stage Spectrum-Based Approach for Dimensionality Reduction: A Case Study on the Recognition of Handwritten Numerals |
| title_full_unstemmed | A Novel Two-Stage Spectrum-Based Approach for Dimensionality Reduction: A Case Study on the Recognition of Handwritten Numerals |
| title_short | A Novel Two-Stage Spectrum-Based Approach for Dimensionality Reduction: A Case Study on the Recognition of Handwritten Numerals |
| title_sort | novel two stage spectrum based approach for dimensionality reduction a case study on the recognition of handwritten numerals |
| url | http://dx.doi.org/10.1155/2014/654787 |
| work_keys_str_mv | AT mohammadaminshayegan anoveltwostagespectrumbasedapproachfordimensionalityreductionacasestudyontherecognitionofhandwrittennumerals AT saeedaghabozorgi anoveltwostagespectrumbasedapproachfordimensionalityreductionacasestudyontherecognitionofhandwrittennumerals AT ramgopalraj anoveltwostagespectrumbasedapproachfordimensionalityreductionacasestudyontherecognitionofhandwrittennumerals AT mohammadaminshayegan noveltwostagespectrumbasedapproachfordimensionalityreductionacasestudyontherecognitionofhandwrittennumerals AT saeedaghabozorgi noveltwostagespectrumbasedapproachfordimensionalityreductionacasestudyontherecognitionofhandwrittennumerals AT ramgopalraj noveltwostagespectrumbasedapproachfordimensionalityreductionacasestudyontherecognitionofhandwrittennumerals |