^{1}

^{*}

^{1}

A method has been proposed to classify handwritten Arabic numerals in its compressed form using partitioning approach, Leader algorithm and Neural network. Handwritten numerals are represented in a matrix form. Compressing the matrix representation by merging adjacent pair of rows using logical OR operation reduces its size in half. Considering each row as a partitioned portion, clusters are formed for same partition of same digit separately. Leaders of clusters of partitions are used to recognize the patterns by Divide and Conquer approach using proposed ensemble neural network. Experimental results show that the proposed method recognize the patterns accurately.

Handwritten digit recognition has received remarkable attention in the field of character recognition. To meet industry demands, handwritten digit recognition systems must have good accuracy, acceptable classification times, and robustness to variations in handwriting style. Currently several approaches are able to reach com- petitive performance in terms of accuracy, including the ones based on multilayer neural networks [

Clustering is a well known task in data mining and pattern recognition that organize a set of objects into groups in such a way that similar objects belong to the same cluster and dissimilar objects belong to different clusters [

Classification is an important problem in the emerging field of data mining. Although classification has been studied extensively in the past, most of the classification algorithms are designed only for memory resident data, thus limiting their suitability for data mining large data sets. Handwritten digit recognition has received re- markable attention in the field of character recognition. To meet industry demands, handwritten digit recogni- tion systems must have good accuracy, acceptable classification times, and robustness to variations in hand- writing style. Monu Agrawal et al., [

Park and Lee [

In this paper, handwritten Arabic numerals are recognized by partition, compression, cluster and ensemble neural network methods. The novelty of this method is recognizing cluster representatives by the proposed ensemble network. The rest of the paper is organized as follows. The ensemble neural network model is intro- duced in Section 2. In Section 3, a training method is given for neural network. An alternative method to recognize handwritten Arabic numerals is proposed in Section 4. In Section 5, the training procedure of the proposed method is given. Experimental result of the proposed work is in Section 6.

The proposed network has group of Single hidden layer feedforward neural networks connected with a layer called classifier layer. The single hidden layer network has input, hidden and output layer as shown in

and output layers are sigmoidal. Number of neural networks of this type considered in the ensemble network is equivalent to number of partitions of the matrix. Number of neurons in each output layer is 10, which represent the digits 0, 1, 2, 3, 4, 5, 6, 7, 8, 9. All these single hidden layer neural networks are formed as an ensemble network by adding one more layer called classifier layer. Output layer of allthe feedforward neural networks are connected with classifier layer which has 10 neurons

Decide the topology of the single hidden layer feedforward network for training the partitioned patterns for classification. For q partitions of the compressed matrix select q number of networks. Input the patterns through the corresponding neural network one by one. Find the output of the hidden and output layer neurons using (2) and (3). Find the error of the network using (4). Update the network weights using (5), (6) and (7). Again input the patterns through the corresponding network of the partitioned pattern. Repeat the above process until network gives predefined accuracy.

where m represents number of neurons in the layer

where

Handwritten digits are represented in matrix form. Every pair of row of a digit is considered without overlapping. Matrix is compressed to its half size by applying logical OR operation on bits that occur in the same columns of selected pair of rows. Each row of a compressed matrix is considered as a new pattern. A pattern of each digit is partitioned into many individual patterns based on rows of a compressed matrix.

Bits of each row are member of the group. Bits in each row of a digit are clustered based on distance measure. By considering all patterns of a particular digit clusters are formed for each partition of those digits separately. Similarly for every digit clusters are formed. Clustering technique with leader concept is used to group meaning- ful patterns so as to improve classification accuracy with minimum input-output operations. In this method [

All leaders are considered for training the feedforward neural network. Standard backpropagation algorithm is used for training. Separate neural network is considered for training the cluster leaders of each partition. After training each neural network individually, the outputs are sent to the classifier layer of the proposed ensemble network. Based on the maximum value received by the neuron of the classifier layer, one of the neuron

Step 1. Convert 192 bits of numerals into 16 ´ 12 size matrix and treat 193^{rd} bit as target value for the 16 rows of a digit.

Step 2. Repeat step 1 for all training patterns of the problem.

Step 3. Apply logical OR operation on bits of each column of adjacent in two rows without row overlapping. Now the size 16 ´ 12 becomes 8 ´ 12.

Step 4. Treat every resultant pattern as with 8 partitions.

Step 5. Form clusters for every partition of each digit separately.

Step 6. Train each neural network individually using standard in backpropagation algorithm by considering every leader as a pattern.

Step 7. Represent the pattern to be classified in 16 ´ 12 size matrix.

Step 8. Compress adjacent two rows using logical OR operation.

Step 9. Input first row into first neural network of ensemble network in and second row into second neural network of ensemble network and in similarly input other rows of the compressed matrix.

Step 10. Find the neuron in the classifier layer which is in “ON” state.

Step 11. Conclude the pattern belonging to the class as position of the neuron in which is in “ON” state.

The proposed method is applied on OCR Handwritten digit data [

Neural network | Epoch |
---|---|

1 | 12,259 |

2 | 13 |

3 | 9529 |

4 | 5825 |

5 | 7246 |

6 | 8037 |

7 | 8690 |

8 | 12,215 |

Neural network | Time (m) |
---|---|

1 | 2.1 |

2 | 0.2 |

3 | 1.7 |

4 | 1.2 |

5 | 1.5 |

6 | 1.6 |

7 | 1.9 |

8 | 2.1 |

Digit | Classification |
---|---|

0 | 333 |

1 | 333 |

2 | 326 |

3 | 320 |

4 | 327 |

5 | 326 |

6 | 324 |

7 | 321 |

8 | 328 |

9 | 326 |

Method | Accuracy (%) |
---|---|

Compressed data in terms of runs [ | 92.47 |

Partition based prototyping [ | 96.28 |

Leaders-subleaders [ | 97.34 |

Proposed Work | 98.6 |

Novelty of this work is recognition of digit through ensemble neural network. Each digit is converted into matrix form and then compressed using logical OR operation. Each row of a compressed matrix is partitioned into individual patterns. Clusters are formed for each partition of the digits using Leader algorithm. Cluster leaders are only considered for training. Ensemble neural network is with 8 neural networks as the compressed matrix has 8 rows. Training neural network consumes time but negligible time is needed for testing. This is the advantage of neural network but if we consider KNN classifier it consumes large time for classification. But another drawback of backpropagation is local minima. Reasonable time is needed to fix learning parameter value for convergence and avoiding local minima. As each partitioned pattern is trained with individual network the training is faster.

KathirvalavakumarThangairulappan,PalaniappanRathinasamy, (2016) Ensemble Neural Network in Classifying Handwritten Arabic Numerals. Journal of Intelligent Learning Systems and Applications,08,1-8. doi: 10.4236/jilsa.2016.81001