Line Segmentation Free Probabilistic Keyword Spotting and Indexing
| Autor: | Enrique Vidal, Killian Barrere, Alejandro Héctor Toselli |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry Search engine indexing Probabilistic logic 020206 networking & telecommunications Pattern recognition 02 engineering and technology Slicing Image (mathematics) Keyword spotting 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Artificial intelligence Line (text file) business Word (computer architecture) |
| Zdroj: | Pattern Recognition and Image Analysis ISBN: 9783030313203 IbPRIA (2) |
| DOI: | 10.1007/978-3-030-31321-0_18 |
| Popis: | Probabilistic Keyword Spotting and Indexing (PKWSI) allows effective search through untranscribed large collections of images. However, when text-line detection fails to detect foreground text, the PKWSI techniques also fail dramatically. In this paper, we develop a new line segmentation-free approach using a uniform line-sized image slicing instead of previous text-line detection. As a result, new issues arise due to overlapping slices, leading to several spot hypotheses for the same word. We develop solutions to take advantage of multiple spots and to consolidate them into single hypotheses. We test our approach on a difficult historical handwritten dataset and it yields promising results. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|