针对现有手写数字识别方法对噪声和图像结构敏感,易导致识别准确度下降,且计算过程复杂的问题,引入客观聚类算法并结合模板匹配机制,通过对待识别数字模板集的一次聚类以降低噪声和数据分布对聚类结果的影响,提高了识别结果的准确性;并利用新聚类中心约简原始模板数据集,实现计算效率的提高。通过对随机手写数字在结构变形和添加噪声等情况下仿真,并与传统手写数字识别方法比较,验证了所提方法的简单易行和有效性
The handwriting digital recognition methods generally are sensitive to the noise and the structure of image, which easily leads to the decrement of recognition accuracy and the increment of computation complexity. In this paper, the objective cluster analysis algorithm is introduced and combined with the template matching mechanism. In order to reduce the effects of the noise and the data distribution, and to improve the recognition accuracy, the one-pass clustering for the template set of the numeral to be identified is proposed. Furthermore, the new clustering centers are used to simplify the primary template dataset, by which the computation efficiency can be enhanced. The simulation about the random handwriting recognition in presence of structural deformation and noise demonstrates the simplicity, practicability and effectiveness of the proposed approach by comparing with the traditional methods
[1]Choudhury H, Mahadeva Prasanna S R. Handwriting recognition using sinusoidal model parameters[J]. Pattern Recognition Letters, 2019,121:87-96.
[2]潘园园,张力,段玲玲等.离散Hopfield神经网络的手写数字识别研究[J]. 复杂系统与复杂性科学,2018,15(1):75-79.
Pan Yuanyuan, Zhang Li, Duan lingling, et al. Study of handwritten digital recognition in discrete hopfield neural networks[J]. Complex Systems and Complexity Science, 2018, 15(1):75-79.
[3]闵锋,叶显一,张彦铎. 基于改进主成分分析网络的手写数字识别方法[J]. 华中科技大学学报(自然科学版),2018,46(12):101-105.
Min Feng, Ye Xianyi, Zhang Yanduo. Method of handwritten digit recognition based on improved PCANet[J]. Journal of Huazhong University of Science & Technology (Natural Science Edition), 2018,46(12):101-105.
[4]陈诗文,王宪保,李梦园等. 矢量量化地标点的显式监督等距映射算法[J].模式识别与人工智能,2015,28(9):788-794.
Chen Shiwen, Wang Xianbao, Li Mengyuan, et al. Vector quantization landmark points for supervised isometric mapping with explicit mapping[J]. Pattern Recognition and Artificial Intelligence, 2015,28(9):788-794.
[5]杨淑莹,张桦. 模式识别与智能计算—MATLAB技术实现[M]. 北京:电子工业出版社,2015.
[6]Sternby J, Morwing J, Andersson J, et al. On-line Arabic handwriting recognition with templates [J]. Pattern Recognition, 2009, 42(12):3278-3286.
[7]吴德超. 基于Hadoop的分布式聚类算法研究与应用[D]. 山东:山东理工大学计算机科学与技术学院,2018.
Wu dechao. Research on distributed clustering algorithm based on Hadoop[D]. Shandong: School of Computer Science and Technology, Shandong University of Technology, 2018.
[8]薛洋,金连文.一种基于加速度传感器的虚拟手写数字特征提取及识别方法[J]. 模式识别与人工智能,2011,24(4):492-500.
Xue Yang, Jin Lianwen. A feature extraction and recognition approach for accelerometer based virtual handwriting digit [J]. Pattern Recognition and Artificial Intelligence, 2011,24(4):492-500.
[9]贺昌政.自组织数据挖掘与经济预测[M]. 北京:科学出版社,2005.
[10] Mollineda R A, Enrique V. A Relative Approach to Hierarchical Clustering, Pattern Recognition and Applications, Frontiers in Artificial Intelligence and Applications[M]. Amsterdam: IOS Press, 2000,56: 19-28.
