In this paper, we propose a new classification method that addresses classification in multiple categories of textual documents. We call it Matrix Regression (MR) due to its resem...
Iulian Sandu Popa, Karine Zeitouni, Georges Gardar...
It is known that convolutional neural networks (CNNs) are efficient for optical character recognition (OCR) and many other visual classification tasks. This paper applies error-co...
New devices gaining access to the Internet need to obtain multimedia content adapted to their limited capacities. Scalable formats allow to retrieve different versions of a single...
—A fast method of handwritten word recognition suitable for real time applications is presented in this paper. Preprocessing, segmentation and feature extraction are implemented ...
Halftone image watermarking techniques that allow automated extraction of the embedded watermark data are useful in a variety of document security and workflow applications. The p...