This paper presents a real-time document image retrieval method for a large-scale database with Locally Likely Arrangement Hashing (LLAH). In general, when a database is scaled up, a large amount of memory is required and retrieval accuracy drops due to insufficient discrimination power of features. To solve these problems, we propose three improvements: memory reduction by sampling feature points, improvement of discrimination power by increasing the number of feature dimensions and stabilizing features by reducing redundancy. From the experimental results, we have confirmed that the proposed method realizes 50% memory reduction, and achieves 99.4% accuracy and 38ms processing time for a database of 10 million pages.
Files
…
Export this publication
Tab-separated. Paste into the sheet starting at column A. Required fields that cannot be inferred are left blank.
Format definition
Edits apply immediately and stay in effect until you pick a style again or reset. First line is the default; add lines like "book: …" to override per type.
How to write the definition
Insert a field with braces like {authors}. A part enclosed in [ ... ] is omitted entirely when any field inside it is empty. Available fields:
One macro per line as \name{field}{field}…. A field name in braces is replaced by its (LaTeX-escaped) value; other text is kept. Rename macros or add lines freely — they appear in the macro selector. A line like master_thesis: thesis fixes the macro for a type (automatic choice: journals use paperdoi with a DOI, paperno with a number, else paper; conferences conf with pages, else confpaper; books book). {pages} comes as 119--124; {journal} falls back to the book title. Fields: