Recognition of contour invariants with neurofuzzy classifier
In this study, we explore contour invariants for handwritten digits recognitions with neuro-fuzzy classifier. We use fuzzy triangular function in backpropagation network to initialize the weights. The results reveal that fuzzy triangular membership function manages to decrease the network convergenc...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Medwell Online
2006
|
| Subjects: | |
| Online Access: | http://eprints.utem.edu.my/id/eprint/22/ http://eprints.utem.edu.my/id/eprint/22/1/Recognition_of_contour_invariants_with_NeuroFuzzy_classifier.pdf |
| _version_ | 1848886872016683008 |
|---|---|
| author | Shamsuddin, Siti Mariyam Draman @ Muda, Azah Kamilah Tan, Shuen Chuan |
| author_facet | Shamsuddin, Siti Mariyam Draman @ Muda, Azah Kamilah Tan, Shuen Chuan |
| author_sort | Shamsuddin, Siti Mariyam |
| building | UTeM Institutional Repository |
| collection | Online Access |
| description | In this study, we explore contour invariants for handwritten digits recognitions with neuro-fuzzy classifier. We use fuzzy triangular function in backpropagation network to initialize the weights. The results reveal that fuzzy triangular membership function manages to decrease the network convergence rate with proper parameter setting. In this study, unthinned images are appropriate for training and classification purpose as it preserves the images significant features. From our experiments, the results show that contour invariants exhibits highest rate of classification compares to geometric and zernike invariants. |
| first_indexed | 2025-11-15T19:45:23Z |
| format | Article |
| id | utem-22 |
| institution | Universiti Teknikal Malaysia Melaka |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T19:45:23Z |
| publishDate | 2006 |
| publisher | Medwell Online |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | utem-222023-05-25T12:18:59Z http://eprints.utem.edu.my/id/eprint/22/ Recognition of contour invariants with neurofuzzy classifier Shamsuddin, Siti Mariyam Draman @ Muda, Azah Kamilah Tan, Shuen Chuan Q Science (General) In this study, we explore contour invariants for handwritten digits recognitions with neuro-fuzzy classifier. We use fuzzy triangular function in backpropagation network to initialize the weights. The results reveal that fuzzy triangular membership function manages to decrease the network convergence rate with proper parameter setting. In this study, unthinned images are appropriate for training and classification purpose as it preserves the images significant features. From our experiments, the results show that contour invariants exhibits highest rate of classification compares to geometric and zernike invariants. Medwell Online 2006 Article PeerReviewed text en http://eprints.utem.edu.my/id/eprint/22/1/Recognition_of_contour_invariants_with_NeuroFuzzy_classifier.pdf Shamsuddin, Siti Mariyam and Draman @ Muda, Azah Kamilah and Tan, Shuen Chuan (2006) Recognition of contour invariants with neurofuzzy classifier. Asian Journal of Information Technology, 5 (9). pp. 924-932. |
| spellingShingle | Q Science (General) Shamsuddin, Siti Mariyam Draman @ Muda, Azah Kamilah Tan, Shuen Chuan Recognition of contour invariants with neurofuzzy classifier |
| title | Recognition of contour invariants with neurofuzzy classifier |
| title_full | Recognition of contour invariants with neurofuzzy classifier |
| title_fullStr | Recognition of contour invariants with neurofuzzy classifier |
| title_full_unstemmed | Recognition of contour invariants with neurofuzzy classifier |
| title_short | Recognition of contour invariants with neurofuzzy classifier |
| title_sort | recognition of contour invariants with neurofuzzy classifier |
| topic | Q Science (General) |
| url | http://eprints.utem.edu.my/id/eprint/22/ http://eprints.utem.edu.my/id/eprint/22/1/Recognition_of_contour_invariants_with_NeuroFuzzy_classifier.pdf |