TY - GEN
T1 - Handwritten character recognition based on a multiple Fermat's spiral
AU - Boudjella, Aissa
AU - Samir, Brahim Belhouari
AU - Khalil, Omar Kassem
PY - 2013
Y1 - 2013
N2 - This paper describes a new feature extraction method which can be used very effectively in combination with Cluster K-Nearest Neighbor (CKNN) and KNN Classifier for image recognition. We propose handwritten English character recognition using Fermat's spiral approach to convert an image space into a parameter space. The system is implemented and simulated in MATLAB, and its performance is tested on real alphabet handwriting image. Fifteen (15) alphabet classes were created to carry out the experiment. Each class contains 9 alphabets {a, b, c, d, e, f, g, h, i}. The total of 15x9=135 alphabet images are captured under fixed camera position and controlled energy light intensity. The experimental results give a better recognition rate, 76.19% for KNN and 95.16% for C-KNN with reducing the overall data size of the transformed image. The relationship between the accuracy and k is investigated. It seems that when k goes from 1 to 9, the accuracy decreases linearly. The result of this investigation is a high performance character recognition system with significantly improved recognition rates and real-time.
AB - This paper describes a new feature extraction method which can be used very effectively in combination with Cluster K-Nearest Neighbor (CKNN) and KNN Classifier for image recognition. We propose handwritten English character recognition using Fermat's spiral approach to convert an image space into a parameter space. The system is implemented and simulated in MATLAB, and its performance is tested on real alphabet handwriting image. Fifteen (15) alphabet classes were created to carry out the experiment. Each class contains 9 alphabets {a, b, c, d, e, f, g, h, i}. The total of 15x9=135 alphabet images are captured under fixed camera position and controlled energy light intensity. The experimental results give a better recognition rate, 76.19% for KNN and 95.16% for C-KNN with reducing the overall data size of the transformed image. The relationship between the accuracy and k is investigated. It seems that when k goes from 1 to 9, the accuracy decreases linearly. The result of this investigation is a high performance character recognition system with significantly improved recognition rates and real-time.
KW - A multiple Fermat's spiral
KW - Feature extraction
KW - Handwritten alphabets
KW - KNN and C-KNN classifier
UR - https://www.scopus.com/pages/publications/84884930734
U2 - 10.4028/www.scientific.net/AMR.774-776.1629
DO - 10.4028/www.scientific.net/AMR.774-776.1629
M3 - Conference contribution
AN - SCOPUS:84884930734
SN - 9783037858004
T3 - Advanced Materials Research
SP - 1629
EP - 1635
BT - Advanced Technologies in Manufacturing, Engineering and Materials
T2 - 2013 International Forum on Mechanical and Material Engineering, IFMME 2013
Y2 - 13 June 2013 through 14 June 2013
ER -