A multi-scale deep quad tree based feature extraction method for the recognition of isolated handwritten characters of popular indic scripts

作者：

Highlights：

• A novel multi-column multi-scale convolutional neural network (MMCNN) based architecture has been proposed.

• A deep quad-tree based staggered prediction model has also been added with the model for recognition with SVM.

• A Multiple level tree network is used increases the recognition rate as it votes through the softmax probabilities of all quadrants or decahexadrants than a single CNN.

• The proposed techniques has been evaluated on 10 publicly available datasets of isolated handwritten characters or digits including MNIST.

• Promising results have been achieved by the proposed system for all of the datasets.

摘要

•A novel multi-column multi-scale convolutional neural network (MMCNN) based architecture has been proposed.•A deep quad-tree based staggered prediction model has also been added with the model for recognition with SVM.•A Multiple level tree network is used increases the recognition rate as it votes through the softmax probabilities of all quadrants or decahexadrants than a single CNN.•The proposed techniques has been evaluated on 10 publicly available datasets of isolated handwritten characters or digits including MNIST.•Promising results have been achieved by the proposed system for all of the datasets.

论文关键词：Handwritten character recognition,Indic script,Deep learning,Multi-column architecture,Multi-scale convolutional sampling,Deep quad tree

论文评审过程：Received 25 September 2016, Revised 20 May 2017, Accepted 25 May 2017, Available online 26 May 2017, Version of Record 2 June 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.05.022