Classification Of Hand-Writing Identification Based On ANFIS

Leong, Shu Ching (2011) Classification Of Hand-Writing Identification Based On ANFIS. Project Report. UTeM, Melaka. (Submitted)

	PDF (24 Pages) Classification_Of_Hand-Writing_Identification_Based_On_ANFIS_24_Pages.pdf - Submitted Version Download (1MB)
	PDF (Full Text) Classification_Of_Hand-Writing_Identification_Based_On_ANFIS_Full_Text.pdf - Submitted Version Restricted to Registered users only Download (14MB)

Abstract

Hand-writing identification is an active topic m the image processmg and pattern recognition, though a lot affords have put in, it still remain a challenge issue. This project was focused on classification of hand-writing identification. Adaptive-Network-Based Fuzzy Inference System (ANFIS) is the choosing classification technique to identify the hand-writing. ANFIS is a Sugeno type Neuro-fuzzy model, where it is the combination of neural network and fuzzy logic. In this project, an experiment was carried out where several testing are done to produce the accurate classification performance. The testing involved the choosing of Neurofuzzy system, three classifiers have been selected: ANFIS-GRID, ANFIS-SUB, and ANFIS FCM. Besides, data type also tested in the experiment to check whether the discretized data or original data show the better result. Last, the cross-validation technique also being used in experiment to set the training data set and testing data set. The performance of ANFIS was evaluated in terms of training performance and classification accuracy. The discretization data and ANFIS-FCM show the better result compared to the others.

Actions (login required)

View Item