RECOGNIZING TAMIL CHARACTERS IN PALM LEAF MANUSCRIPTS (DEEP LEARNING)

Tamil is an ancient language that has a vast collection of literature written on palm leaves and other materials. Palm leaf manuscripts have been used as versatile medium to record information medicine, literature, theatre, subjects. Despite the need for digitization transcription, recognizing cursive characters in remains challenging task. This study introduces novel Convolutional Neural Network (CNN) technique train characteristics characters, enabling CNN significantly classify during training phase. Preprocessing input image done using morphological operations remove noise. Connected component analysis processing identify label individual connected regions, or components, binary image. Analysis then segment with feature including text line spacing, spacing without obstacle, obstacle. Finally, extracted are into final classification. Experiments conducted collected validate performance proposed existing deep learning techniques terms accuracy, precision, recall, etc.