Mostra el registre d'ítem simple
WordFences: Text localization and recognition
dc.contributor | Escalera, Sergio |
dc.contributor | Lu, Shijian |
dc.contributor.author | Polzounov, Andrei |
dc.date.accessioned | 2017-03-03T11:50:20Z |
dc.date.available | 2017-03-03T11:50:20Z |
dc.date.issued | 2017-01 |
dc.identifier.uri | http://hdl.handle.net/2117/101911 |
dc.description | En col·laboració amb la Universitat de Barcelona (UB) i la Universitat Rovira i Virgili (URV) |
dc.description.abstract | In recent years, text recognition has achieved remarkable success in recognizing scanned document text. However, word recognition in natural images is still an open problem, which generally requires time consuming post-processing steps. We present a novel architecture for individual word detection in scene images based on semantic segmentation. Our contributions are twofold: the concept of WordFence, which detects border areas surrounding each individual word and a unique pixelwise weighted softmax loss function which penalizes background and emphasizes small text regions. WordFence ensures that each word is detected individually, and the new loss function provides a strong training signal to both text and word border localization. The proposed technique avoids intensive post-processing by combining semantic word segmentation with a voting scheme for merging segmentations of multiple scales, producing an end-to-end word detection system. We achieve superior localization recall on common benchmark datasets - 92% recall on ICDAR11 and ICDAR13 and 63% recall on SVT. Furthermore, end-to-end word recognition achieves state-of-the-art 86% F-Score on ICDAR13. |
dc.language.iso | eng |
dc.publisher | Universitat Politècnica de Catalunya |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial |
dc.subject.lcsh | Machine learning |
dc.subject.lcsh | Neural networks (Computer science) |
dc.subject.other | artificial intelligence |
dc.subject.other | object detection |
dc.subject.other | text detection |
dc.subject.other | text recognition |
dc.title | WordFences: Text localization and recognition |
dc.type | Master thesis |
dc.subject.lemac | Aprenentatge automàtic |
dc.subject.lemac | Xarxes neuronals (Informàtica) |
dc.identifier.slug | 122778 |
dc.rights.access | Open Access |
dc.date.updated | 2017-02-11T05:00:07Z |
dc.audience.educationlevel | Màster |
dc.audience.mediator | Facultat d'Informàtica de Barcelona |
dc.audience.degree | MÀSTER UNIVERSITARI EN INTEL·LIGÈNCIA ARTIFICIAL (Pla 2012) |
dc.contributor.covenantee | Institute for Infocomm Research |