Convolutional Neural Networks for Off-Line Writer Identification Based on Simple Graphemes
The writer’s identification/verification problem has traditionally been solved by analyzing complex biometric sources (text pages, paragraphs, words, signatures, etc.). This implies the need for pre-processing techniques, feature computation and construction of also complex classifiers. A group of s...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/22/7999 |
| _version_ | 1827702424097259520 |
|---|---|
| author | Marco Mora José Naranjo-Torres Verónica Aubin |
| author_facet | Marco Mora José Naranjo-Torres Verónica Aubin |
| author_sort | Marco Mora |
| collection | DOAJ |
| description | The writer’s identification/verification problem has traditionally been solved by analyzing complex biometric sources (text pages, paragraphs, words, signatures, etc.). This implies the need for pre-processing techniques, feature computation and construction of also complex classifiers. A group of simple graphemes (“ S ”, “ ∩ ”, “ C ”, “ ∼ ” and “ U ”) has been recently introduced in order to reduce the structural complexity of biometric sources. This paper proposes to analyze the images of simple graphemes by means of Convolutional Neural Networks. In particular, the AlexNet, VGG-16, VGG-19 and ResNet-18 models are considered in the learning transfer mode. The proposed approach has the advantage of directly processing the original images, without using an intermediate representation, and without computing specific descriptors. This allows to dramatically reduce the complexity of the simple grapheme processing chain and having a high hit-rate of writer identification performance. |
| first_indexed | 2024-03-10T14:56:09Z |
| format | Article |
| id | doaj.art-b9f2454f63e44dca97dbb8c67ff3d84a |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T14:56:09Z |
| publishDate | 2020-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b9f2454f63e44dca97dbb8c67ff3d84a2023-11-20T20:36:19ZengMDPI AGApplied Sciences2076-34172020-11-011022799910.3390/app10227999Convolutional Neural Networks for Off-Line Writer Identification Based on Simple GraphemesMarco Mora0José Naranjo-Torres1Verónica Aubin2Laboratory of Technological Research in Pattern Recognition, Faculty of Engineering Science, Universidad Católica del Maule, Talca 3480112, Maule, ChileLaboratory of Technological Research in Pattern Recognition, Faculty of Engineering Science, Universidad Católica del Maule, Talca 3480112, Maule, ChileDepartment of Engineering and Technological Research, Universidad Nacional de La Matanza, San Justo B1754JEC, Provincia de Buenos Aires, ArgentinaThe writer’s identification/verification problem has traditionally been solved by analyzing complex biometric sources (text pages, paragraphs, words, signatures, etc.). This implies the need for pre-processing techniques, feature computation and construction of also complex classifiers. A group of simple graphemes (“ S ”, “ ∩ ”, “ C ”, “ ∼ ” and “ U ”) has been recently introduced in order to reduce the structural complexity of biometric sources. This paper proposes to analyze the images of simple graphemes by means of Convolutional Neural Networks. In particular, the AlexNet, VGG-16, VGG-19 and ResNet-18 models are considered in the learning transfer mode. The proposed approach has the advantage of directly processing the original images, without using an intermediate representation, and without computing specific descriptors. This allows to dramatically reduce the complexity of the simple grapheme processing chain and having a high hit-rate of writer identification performance.https://www.mdpi.com/2076-3417/10/22/7999writer identificationoff-line analysissimple graphemesconvolutional neural networks |
| spellingShingle | Marco Mora José Naranjo-Torres Verónica Aubin Convolutional Neural Networks for Off-Line Writer Identification Based on Simple Graphemes Applied Sciences writer identification off-line analysis simple graphemes convolutional neural networks |
| title | Convolutional Neural Networks for Off-Line Writer Identification Based on Simple Graphemes |
| title_full | Convolutional Neural Networks for Off-Line Writer Identification Based on Simple Graphemes |
| title_fullStr | Convolutional Neural Networks for Off-Line Writer Identification Based on Simple Graphemes |
| title_full_unstemmed | Convolutional Neural Networks for Off-Line Writer Identification Based on Simple Graphemes |
| title_short | Convolutional Neural Networks for Off-Line Writer Identification Based on Simple Graphemes |
| title_sort | convolutional neural networks for off line writer identification based on simple graphemes |
| topic | writer identification off-line analysis simple graphemes convolutional neural networks |
| url | https://www.mdpi.com/2076-3417/10/22/7999 |
| work_keys_str_mv | AT marcomora convolutionalneuralnetworksforofflinewriteridentificationbasedonsimplegraphemes AT josenaranjotorres convolutionalneuralnetworksforofflinewriteridentificationbasedonsimplegraphemes AT veronicaaubin convolutionalneuralnetworksforofflinewriteridentificationbasedonsimplegraphemes |