Restoration of Ancient Kannada Handwritten Palm Leaf Manuscripts using Image Enhancement Techniques Parashuram Bannigidad 1[0000-0001-6191-6117] and S. P. Sajjan 2[0000-0001-7891-2446] 1,2 Dept. of Computer Science, Rani Channamma University, Belagavi- 571159, India parashurambannigidad@gmail.com, sajjanvsl@gmail.com Abstract. In the recent days, the research area of handwritten character recogni- tion has got much attention towards ancient inscriptions, since they contain lots of unfolding knowledge in the field of science, literature, astronomy, medicine, etc. The materials used to write these inscriptions are paper, palm leaf, stone rocks, and temple walls, etc., These materials are now degrading in nature due to climatic conditions, ink bleeding, lack of attention, and unscientific storage. Pre- sent paper, the digitization & restoration of Kannada handwritten palm leaf with iterative global threshold based segmentation is developed. The performance es- timation is measured by calculating MSE and PSNR values and The image qual- ity is compared to manual obtained results by Epigraphists. The average values of PSNR and MSE are 6.198 and 0.234, respectively. The higher the PSNR and lower the MSE determines the quality of the image. The outcomes are also com- pared to other standard methods, namely; Souvola, Niblack, and Adaptive thresh- olding (Gaussion+Binary Inverse). The comparison studies confirm that the pro- posed algorithm is more effective than the other methods. The proposed algo- rithm is also implemented on the benchmark standard palm leaf dataset, i.e., the AMADI_LONTARSET. Keywords: Palm leaf manuscripts, Image enhancement, Thresholding, IGT, Degraded document, PSNR, MSE, Document image Binarization. 1 Introduction In the recent days, the research area of handwritten character recognition has got much attention towards ancient inscriptions, since they contain lots of unfolding knowledge in the field of science, literature, astronomy, medicine, etc., the materials used to write these inscriptions are paper, palm leaf, stone rocks, and temple walls, etc., These materials are now degrading in nature due to climatic condition, ink bleeding, lack of attention and unscientific storage. In digital image processing, the binarization of document image is often the first stage. Ancient documents are ruined, where exten- sive noise in the background or lots of changes exists. Hence, it is very difficult to categorize foreground and background pixels. Fig 1 shows a sample manuscript of his- torical degraded Kannada handwritten manuscripts written on palm leaf.