Comprehensive Dataset Building and Recognition of Isolated Handwritten Kannada Characters Using Machine Learning Models

Abstract

In this work, an attempt is made to build a dataset for handwritten Kannada characters and also to recognize the isolated Kannada vowels, consonants, modifiers, and ottaksharas. The dataset is collected from 500 writers of varying ages, gender, qualification, and profession. This dataset will be used to recognize the handwritten kagunita's, ottaksharas, and other base characters, where the existing works have addressed very less on the recognition of kagunita's and ottaksharas. There are no datasets for the same. Hence, a dataset for handwritten 85 characters is built using an unsupervised machine learning technique i.e K-means hierarchical clustering with Run Length Code (RLC) features. An accuracy of 80% was achieved with the unsupervised method. The dataset consists of 130,981 samples for 85 classes, these classes are further divided into upper, lower, and middle zones based on the position of the character in the dialect. After the dataset was built SVM model with HOG features was used for recognition and an accuracy of 99.0%, 88.6%, and 92.2% was obtained for the Upper, Middle, and Lower zones respectively to increase the recognition rate, the CNN model is fine-tuned with raw input, and an accuracy of 100%, 96.15%, and 95.38% was obtained for the Upper, Middle, and Lower zones respectively. With the ResNet18 model, an accuracy of 99.88%, 98.92, and 97.55% was obtained for each of the zones respectively. The dataset will be made available online for the researchers to carry out their research on handwritten characters, kagunitas, and word recognition with segmentation.

Using of artificial neural networks and different evolutionary algorithms to predict the viscosity and thermal conductivity of silica-alumina-MWCN/water nanofluid

“…Artificial intelligence (AI) is the intelligence that a machine shows in different situations. Machine learning is a type of AI focused on building computer systems that learn from data, enabling software to improve its performance over time [ [25] , [26] , [27] , [28] ]. Also, ANNs are a class of statistical learning algorithms used in machine learning and cognitive science domains [ [29] , [30] , [31] , [32] , [33] ].…”

Feature Extraction and Classification of Text Data by Combining Two-stage Feature Selection Algorithm and Improved Machine Learning Algorithm

“…The performance of SVM depends largely on the quality of feature selection and extraction. Feature selection is important when dealing with large-scale text data, and effective H. Huang feature extraction is essential to improve classification accuracy and efficiency [6]. Here are some of the relevant studies by scientists and scholars.…”

“…A lower value for intra-class coupling DC indicates that it is more efficient on behalf of the class C . Next, the MRMR algorithm considers the MI of feature words in all categories, fine-tunes the weight of the MI by introducing the class difference degree  , and selects the two largest class difference degree values for processing, as detailed in equation(6).…”