Representative Image Selection for Data Efficient Word Spotting
| Autor: | Florian Westphal, Niklas Lavesson, Håkan Grahn |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Pixel
Computer science Active learning (machine learning) business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION graph representation 020206 networking & telecommunications Pattern recognition 02 engineering and technology Spotting sample selection Synthetic data PHOCNet Datorseende och robotik (autonoma system) Histogram active learning 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Pyramid (image processing) word spotting business Representation (mathematics) Word (computer architecture) Computer Vision and Robotics (Autonomous Systems) |
| Zdroj: | Document Analysis Systems ISBN: 9783030570576 DAS |
| Popis: | This paper compares three different word image representations as base for label free sample selection for word spotting in historical handwritten documents. These representations are a temporal pyramid representation based on pixel counts, a graph based representation, and a pyramidal histogram of characters (PHOC) representation predicted by a PHOCNet trained on synthetic data. We show that the PHOC representation can help to reduce the amount of required training samples by up to 69% depending on the dataset, if it is learned iteratively in an active learning like fashion. While this works for larger datasets containing about 1 700 images, for smaller datasets with 100 images, we find that the temporal pyramid and the graph representation perform better. open access |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|