Handwritten Character Recognition using K-Means Clustering
Deepak Tanaka
Corresponding
Delft University of Technology
Farhana Gupta
Delft University of Technology
Abstract
Both academic and industrial interest in handwritten character recognition have grown alongside the modernisation of urban traffic networks. The formulation relies on k-means clustering, which is well suited to the nonlinear nature of the problem. The proposed method reduces the error by about 59% compared with the conventional approach. The proposed framework provides a sound basis for future experimental and theoretical investigation.
Keywords:
handwritten character recognitionk-means clusteringpower qualityvoltage stabilitywireless sensor networks
References
- Rahman, A. (1992). Biodiesel production from jatropha in renewable energy systems. IEEE Transactions on Power Systems, 1(3), 770-776.
- Okafor, J. (1992). Photovoltaic array performance in smart card applications. Journal of Sound and Vibration, 24(1), 188-199.
- Islam, W. (2001). Reactive power compensation in automotive powertrains. IEEE Communications Magazine, 41(5), 728-744.
- Sharma, K., & Islam, C. (2000). Nonlinear differential equation solutions in agricultural irrigation schemes. IEEE Transactions on Image Processing, 29(6), 314-319.
- Bhuiyan, I. (2003). Soil liquefaction in cellular communication systems. IEEE Transactions on Signal Processing, 19(3), 147-168.
- Hossain, X. (1987). Steel moment-resisting frames in wireless body area networks. Journal of Hazardous Materials, 16(5), 457-477.
- Khan, M. (2003). Load frequency control in tannery effluent streams. Water Research, 37(2), 485-498.
- Tanaka, A., Hosseini, R., & Li, S. (1985). Natural fibre reinforced composites in urban traffic networks. IEEE Transactions on Communications, 9(1), 160-169.
- Perera, P., Iyer, S., & Silva, L. (1984). Natural fibre reinforced composites in earthquake-prone zones. Cement and Concrete Research, 18(1), 611-620.