Feature extraction for neural-fuzzy inference system

• Main Authors: Quek, Chai, See Ng, Goek, Abdul Rahman, Abdul Wahab
• Format: Conference or Workshop Item
• Language: English
• Published: 2003
• Subjects: T Technology (General)
• 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

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.