Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Canjie Luo"'
Publikováno v:
International Journal of Computer Vision. 130:2623-2645
Handwritten Chinese text recognition (HCTR) has been an active research topic for decades. However, most previous studies solely focus on the recognition of cropped text line images, ignoring the error caused by text line detection in real-world appl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f013b92b56752421f8785e23ef2e4b59
https://doi.org/10.1007/s11263-022-01654-0
https://doi.org/10.1007/s11263-022-01654-0
Autor:
Hao Chen, Shuaitao Zhang, Canjie Luo, Xinyu Wang, Yuliang Liu, Lianwen Jin, Tong He, Chunhua Shen
Publikováno v:
International Journal of Computer Vision. 129:1972-1992
Multi-orientation scene text detection has recently gained significant research attention. Previous methods directly predict words or text lines, typically by using quadrilateral shapes. However, many of these methods neglect the significance of cons
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::97d269f4d903d71ff728838032393ec6
https://doi.org/10.1007/s11263-021-01459-7
https://doi.org/10.1007/s11263-021-01459-7
Publikováno v:
International Journal of Computer Vision. 129:960-976
Scene text recognition is an important task in computer vision. Despite tremendous progress achieved in the past few years, issues such as varying font styles, arbitrary shapes and complex backgrounds etc. have made the problem very challenging. In t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7b280961869f1821d50bb113edb97a2d
https://doi.org/10.1007/s11263-020-01411-1
https://doi.org/10.1007/s11263-020-01411-1
Publikováno v:
Pattern Recognition Letters. 136:205-211
Scene text recognition has become a research hotspot owing to its abundant semantic information and various applications. Recent methods of scene text recognition usually focus on handling shape distortion, attention drift, or background noise, ignor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::45d379997f3b11e276ff0b1fc6971c23
https://doi.org/10.1016/j.patrec.2020.06.009
https://doi.org/10.1016/j.patrec.2020.06.009
Publikováno v:
Neurocomputing. 376:202-213
For most previous attention-based scene text recognition methods, images are transformed into high-level feature vectors that form a feature map with height equal to one. Such vectors may contain unnecessary noise that limits recognition performance.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::241d900cf8aa531d329a938408b5a25f
https://doi.org/10.1016/j.neucom.2019.10.010
https://doi.org/10.1016/j.neucom.2019.10.010
Publikováno v:
IEEE Transactions on Image Processing. 29:8760-8775
Scene text removal has attracted increasing research interests owing to its valuable applications in privacy protection, camera-based virtual reality translation, and image editing. However, existing approaches, which fall short on real applications,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f6273be5348cf19a16ccc02c94fbd72e
https://doi.org/10.1109/tip.2020.3018859
https://doi.org/10.1109/tip.2020.3018859
Publikováno v:
Frontiers in Handwriting Recognition ISBN: 9783031216473
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6f11b1faffaec7b887aee7bad2095a6a
https://doi.org/10.1007/978-3-031-21648-0_24
https://doi.org/10.1007/978-3-031-21648-0_24
Camera-captured document images usually suffer from perspective and geometric deformations. It is of great value to rectify them when considering poor visual aesthetics and the deteriorated performance of OCR systems. Recent learning-based methods in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::837cbbc95f3c6cb04fb28f9583e5c2eb
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198144
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a788259c925b7d54be22d709df889d2d
https://doi.org/10.1007/978-3-031-19815-1_24
https://doi.org/10.1007/978-3-031-19815-1_24
Large amounts of labeled data are urgently required for the training of robust text recognizers. However, collecting handwriting data of diverse styles, along with an immense lexicon, is considerably expensive. Although data synthesis is a promising
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fa03a6e128b36b2b80088bfde5a977ab