Oracle Character Recognition by Nearest Neighbor Classification with Deep Metric Learning

Oracle character is one kind of the earliest hieroglyphics, which can be dated back to Shang Dynasty in China. Oracle character recognition is important for modern archaeology, ancient text understanding, and historical chronology, etc. To overcome the limitation and class imbalance of training data in oracle character recognition, we propose a classification method based on deep metric learning. We use a convolutional neural network (CNN) to map the character images to an Euclidean space where the distance between different samples can measure their similarities such that classification can be performed by the Nearest Neighbor (NN) rule. Because new categories are still being discovered in reality, our model enables the rejection of unseen categories and the configuration of new categories. To accelerate NN classification, we also propose a prototype pruning method with little loss of accuracy. The proposed method exceeds the state of the art on the public dataset Oracle-20K and outperforms CNN with softmax layer on a new dataset Oracle-AYNU.

[1]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[2]  José Francisco Martínez Trinidad,et al.  A review of instance selection methods , 2010, Artificial Intelligence Review.

[3]  Ricardo da Silva Torres,et al.  Nearest neighbors distance ratio open-set classifier , 2016, Machine Learning.

[4]  L. Qingsheng.  Recognition of inscriptions on bones or tortoise shells based on graph isomorphism , 2011 .

[5]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[6]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[7]  Fei Yin,et al.  Handwritten Chinese character recognition with spatial transformer and deep residual networks , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[8]  Tao Xiang,et al.  Sketch-a-Net: A Deep Neural Network that Beats Humans , 2017, International Journal of Computer Vision.

[9]  Hongyang Chao,et al.  Building Hierarchical Representations for Oracle Character and Sketch Recognition , 2016, IEEE Transactions on Image Processing.

[10]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[11]  Yi Liu,et al.  An Efficient Algorithm for Local Distance Metric Learning , 2006, AAAI.

[12]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  G. Gates.  The Reduced Nearest Neighbor Rule , 1998 .

[14]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[16]  Peng-Yung Woo,et al.  The coding principle and method for automatic recognition of Jia Gu Wen characters , 2000, Int. J. Hum. Comput. Stud..

[17]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[18]  Rong Jin,et al.  Bayesian Active Distance Metric Learning , 2007, UAI.

[19]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[20]  Ioannis A. Kakadiaris,et al.  An Overview and Empirical Comparison of Distance Metric Learning Methods , 2017, IEEE Transactions on Cybernetics.

[21]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[22]  Wenju Liu,et al.  Robust offline handwritten character recognition through exploring writer-independent features under the guidance of printed data , 2018, Pattern Recognit. Lett..

[23]  Yoshua Bengio,et al.  Online and offline handwritten Chinese character recognition: A comprehensive study and new benchmark , 2016, Pattern Recognit..