Constarium
← Search

Data · dataset · 2025

Graph-based Optical Character Recognition for Syair Perang Johor

Listed in RIN Data Repository

Description

Graph and Freeman chaincode traversal log from optical character recognition on historic manuscript (Syair Perang Johor) Generated using series of Python scripts: - github.com/jendralhxr/cursive-scribe/blob/main/view2page.py (conversion from a single scan into respective pages) - github.com/jendralhxr/cursive-scribe/blob/main/page2line.py (from a single pages to multiple lines based on horizontal projection histogram) - github.com/jendralhxr/cursive-scribe/blob/main/feature2rasm.py (SLIC feature extraction for graph construction) - github.com/jendralhxr/cursive-scribe/blob/main/rasm2hurf.py (graph traversal into detected Arab/Jawi rasm in Unicode)

Links

Where it is published

Catalogue records · 1

Topics

Inferred from text
Optical character recognition 75%
Provenance · 1 source records, 6 field assertions
SourceKeyLast seenRaw
RIN Data Repositoryhdl:20.500.12690/RIN/1JFQSA7 d agoJSON v1
FieldAssertionExtractorEvidence
concepts[field].local:field:earth-environmentalmapping · rin brin go idconnector:rin_brin_go_id@1.0.0
concepts[field].local:field:humanitiesmapping · rin brin go idconnector:rin_brin_go_id@1.0.0
concepts[method].local:method:ocrenrichment · rin brin go idkeyword-concept-rules@1.0.0title+description (75%)
descriptionsource · rin brin go idconnector:rin_brin_go_id@1.0.0/metadata/dc/description
publication_datesource · rin brin go idconnector:rin_brin_go_id@1.0.0
titlesource · rin brin go idconnector:rin_brin_go_id@1.0.0/metadata/dc/title