A Convolutional Neural Network for Arabic Document Analysis
| Autor: | János Csirik, Hassina Bouressace |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Connected component
Artificial neural network business.industry Computer science 020207 software engineering Pattern recognition 02 engineering and technology Convolutional neural network Thresholding ComputingMethodologies_DOCUMENTANDTEXTPROCESSING 0202 electrical engineering electronic engineering information engineering Table (database) 020201 artificial intelligence & image processing Artificial intelligence business Projection (set theory) Smoothing Block (data storage) |
| Zdroj: | ISSPIT |
| DOI: | 10.1109/isspit47144.2019.9001779 |
| Popis: | In this study we apply a CNN (convolutional neural network) to segment a document image into its page components. Our approach consists of two main steps. Firstly, there is a new method of extracting layouts based on sharpness/smoothing filters, adaptive thresholding techniques, morphological operations, along with a CC (connected-component) technique and ARLSA (Adaptive run-length smoothing algorithm) for the patch extraction phase. Secondly, the extracted patches will be put into six classes (text, table, figure, title, legend, author) using a CNN, and four other classes (straight-line, text-line, block, article) using PP (projection profiles) analysis and geometric features. The method was tested on smartphone-captured newspaper images selected from the PATD [1] (Printed Arabic Text Database). The results indicate that the proposed method is suitable for detecting multiple labels in Arabic newspaper pages. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|