Feature extraction for neural-fuzzy inference system
Currently, not many attempts are made to use neural-fuzzy inference system for recognizing primitive features of an input image. The objective of this paper is to propose a method of feature extraction so as the features obtained can be trained in a novel neural-fuzzy inference system called POP-CHA...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2003
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/38845/1/Feature_Extraction_for_Neural-Fuzzy_Inference_System.pdf http://irep.iium.edu.my/38845/ http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1223702 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Islam Antarabangsa Malaysia |
| Language: | English |
| Summary: | Currently, not many attempts are made to use neural-fuzzy inference system for recognizing primitive features of an input image. The objective of this paper is to propose a method of feature extraction so as the features obtained can be trained in a novel neural-fuzzy inference system called POP-CHAR. Common features of digit characters are extracted and converted into vectors. The neural-fuzzy inference system can be trained from the primitive feature vectors and produce good results. Once the fuzzy neural network is trained, it can be used to recognize digits. |
|---|