Handwritten images (HWIs) play a major role in human society for the purpose of communication. So, it is very much essential for the categorization of HWIs into several types in a better way. In this work, a machine intelligent (MI) based approach is proposed for the classification of HWIs into several categories such as Odia handwritten images (OHWIs), Bengali handwritten images (BHWIs), Hindi handwritten images (HHWIs) and Cedar handwritten images (CHWIs). The proposed approach is focused on the stacking (hybridization) of Logistic Regression (LRG) and Neural Network (NNT) methods to carry out such classification. The proposed method is compared with other machine learning (ML) based methods such as AdaBoost (ADB), Random Forest (RFS), Decision Tree (DTR), K-Nearest Neighbor (KNNH), Support Vector Machine (SVMN), LRG and NNT for performance analysis. The proposed method and other ML based methods have been implemented using Python based Orange 3.26.0. In this work, 310 HWIs having 100 numbers of BHWIs, HHWIs and CHWIs type each are taken from the Kaggle source, and 10 numbers of OHWIs are taken for processing. The performance of all the methods is assessed using the performance parameters such as classification accuracy (CA), F1, Precision (PR) and Recall (RC). From the results, it is found that the proposed method is capable of providing better classification results in terms of CA, F1, PR and RC as compared to other ML based methods such as ADB, RF, DTR, KNNH, SVMN, LRG and NNT.

Odia Handwritten Images, Machine Intelligence, Classification Accuracy, F1, Precision,Recall