Puzzle optimization algorithm with capsule networks based Telugu character recognition model

Recently, <span>Telugu character recognition (TCR) becomes a hot research topic because of drastic increase in technological advancements such as multimedia, and smartphones. Though numerous works have been concentrated on offline TCR models, it is still needed to develop automated intelligent online models. This paper presents novel puzzle optimization algorithm with capsule networks-based Telugu (POACN-TCR) model. The presented POACN-TCR model intends effectively identify recognize distinct characters online. To accomplish this, the primarily undergoes pre-processing different ways normalization, smoothing, interpolation. In addition, designs an effective network (CapsNet) generate feature vectors hyperparameter takes place using (POA). Finally, C4.5 decision tree classifier utilized for effectual characters. utilization POA CapsNet helps achieving improved performance. For ensuring enhanced outcomes model, wide-ranging experimental analysis performed pointed out betterment recent approaches.</span>