Implementation of 4-Directional Depth First Search and Projection Profile for Javanese Manuscript Image Segmentation

Abstrak

One of the key steps in digitizing Javanese manuscripts is image segmentation, which separates elements such as lines and characters. This study evaluates the Projection Profile and Four-Directional Depth-First Search (4-Directional DFS) methods for segmenting handwritten Javanese script. The Projection Profile method is used for line segmentation, while 4-Directional DFS identifies interconnected pixels for character segmentation. A total of 20 scanned images were randomly selected from Serat Pratanda and Serat Primbon Reracikan Jampi Jawi. After grayscale conversion and binarization, each image underwent two treatments: with and without advanced preprocessing, before segmentation. Results showed that line segmentation achieved 100% accuracy in both treatments. Character segmentation reached 91.02% accuracy with advanced preprocessing and 84.28% without it. Segmentation errors were mainly caused by over-segmentation and under-segmentation. These results demonstrate that the Projection Profile and 4-Directional DFS methods are effective in segmenting handwritten Javanese manuscripts. They show promise for supporting future developments in automatic Javanese script transliteration.

Identifier

• DOI: https://doi.org/10.31289/jite.v9i1.15433
• OpenAlex: https://openalex.org/W7167058286