Moment-based extraction on handwritten digits
Handwritten digits recognition software have become a highly demand applications to the market. Manufacturing industries as well as post offices are among the users of these applications. In the past few years, several approaches have been used in development of handwritten recognition applications....
| Main Authors: | , , |
|---|---|
| Format: | Monograph |
| Language: | English |
| Published: |
Faculty of Computer Science and Information System
2005
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/4345/2/71903.pdf |
| _version_ | 1825909539727212544 |
|---|---|
| author | Taliba, Jumail Shamsuddin, Siti Mariyam Tan, Shuen Chuan |
| author_facet | Taliba, Jumail Shamsuddin, Siti Mariyam Tan, Shuen Chuan |
| author_sort | Taliba, Jumail |
| collection | ePrints |
| description | Handwritten digits recognition software have become a highly demand applications to the market. Manufacturing industries as well as post offices are among the users of these applications. In the past few years, several approaches have been used in development of handwritten recognition applications. However, the accuracy of recognition varies between one and another. In this study, the approach of moment-based techniques are employed on handwritten characters.. These include geometric moments, Zernike moments and contour sequence moments. Classification and recognition results are analyzed to determine the necessity of operation thinning when dealing with the moment functions. A Simple Block Segmentation with Moore Tracing Algorithm (SBS & MNTA) is used in image segmentation while Safe-point Thinning Algorithm (SPTA) is applied in image thinning process. Results obtained have shown that operation thinning should be excluded as its deteriorates the recognition accuracy. Contour sequence moments exhibited the highest recognition rate compared to Geometric moments and Zernike moments. |
| first_indexed | 2024-03-05T18:03:41Z |
| format | Monograph |
| id | utm.eprints-4345 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T18:03:41Z |
| publishDate | 2005 |
| publisher | Faculty of Computer Science and Information System |
| record_format | dspace |
| spelling | utm.eprints-43452017-08-07T03:11:13Z http://eprints.utm.my/4345/ Moment-based extraction on handwritten digits Taliba, Jumail Shamsuddin, Siti Mariyam Tan, Shuen Chuan ZA4050 Electronic information resources Handwritten digits recognition software have become a highly demand applications to the market. Manufacturing industries as well as post offices are among the users of these applications. In the past few years, several approaches have been used in development of handwritten recognition applications. However, the accuracy of recognition varies between one and another. In this study, the approach of moment-based techniques are employed on handwritten characters.. These include geometric moments, Zernike moments and contour sequence moments. Classification and recognition results are analyzed to determine the necessity of operation thinning when dealing with the moment functions. A Simple Block Segmentation with Moore Tracing Algorithm (SBS & MNTA) is used in image segmentation while Safe-point Thinning Algorithm (SPTA) is applied in image thinning process. Results obtained have shown that operation thinning should be excluded as its deteriorates the recognition accuracy. Contour sequence moments exhibited the highest recognition rate compared to Geometric moments and Zernike moments. Faculty of Computer Science and Information System 2005 Monograph NonPeerReviewed application/pdf en http://eprints.utm.my/4345/2/71903.pdf Taliba, Jumail and Shamsuddin, Siti Mariyam and Tan, Shuen Chuan (2005) Moment-based extraction on handwritten digits. Project Report. Faculty of Computer Science and Information System, Skudai Johor. (Unpublished) |
| spellingShingle | ZA4050 Electronic information resources Taliba, Jumail Shamsuddin, Siti Mariyam Tan, Shuen Chuan Moment-based extraction on handwritten digits |
| title | Moment-based extraction on handwritten digits |
| title_full | Moment-based extraction on handwritten digits |
| title_fullStr | Moment-based extraction on handwritten digits |
| title_full_unstemmed | Moment-based extraction on handwritten digits |
| title_short | Moment-based extraction on handwritten digits |
| title_sort | moment based extraction on handwritten digits |
| topic | ZA4050 Electronic information resources |
| url | http://eprints.utm.my/4345/2/71903.pdf |
| work_keys_str_mv | AT talibajumail momentbasedextractiononhandwrittendigits AT shamsuddinsitimariyam momentbasedextractiononhandwrittendigits AT tanshuenchuan momentbasedextractiononhandwrittendigits |