Name
Abstract | ||
|---|---|---|
In this work, we present a novel approach for the extraction of deep features from a Convolutional Neural Network (CNN), designed for the task of Keyword Spotting (KWS). The main novelty of our work concerns the generation of a compact descriptor able to simulate the existence/absence of unigrams or bigrams. This is accomplished using a binary, attribute-based representation of a word string together with an appropriate training procedure. Deep features are extracted from the output of the last convolutional layer and are organized into zones in order to incorporate spatial information of the detected attributes. In addition, a novel optimization scheme is proposed which relies on a very effective initialization of the network generating the compact descriptors. Experiments conducted on the IAM dataset prove the efficiency of the novel compact descriptor since the proposed system's performance in on par with the state-of-the-art. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/ICFHR-2018.2018.00062 | 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR) |
Keywords | Field | DocType |
Keyword Spotting,Query by Example,Convolutional Neural Networks | Spatial analysis,Pattern recognition,Convolutional neural network,Computer science,Keyword spotting,Query by Example,Artificial intelligence,Bigram,Novelty,Initialization,Binary number | Conference |
ISSN | ISBN | Citations |
2167-6445 | 978-1-5386-5876-5 | 0 |
PageRank | References | Authors |
0.34 | 6 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| George Retsinas | 1 | 8 | 3.91 |
| G. Sfikas | 2 | 155 | 14.23 |
| Georgios Louloudis | 3 | 81 | 9.54 |
| Nikolaos Stamatopoulos | 4 | 34 | 2.78 |
| Basilis Gatos | 5 | 773 | 43.34 |