Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Ehry MacRostie"'
Autor:
Rohit Prasad, Shiv Vitaladevuni, Premkumar Natarajan, David Belanger, Huaigu Cao, Krishna Subramanian, Matin Kamali, Ehry MacRostie, Shirin Saleem
Publikováno v:
Guide to OCR for Arabic Scripts ISBN: 9781447140719
We describe BBN’s script-independent methodology for multilingual machine-print OCR and offline handwriting recognition (HWR) based on the use of hidden Markov models (HMM). The feature extraction, training, and recognition components of the system
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::47d187af4ce2e817ba796c9b2321cf9f
https://doi.org/10.1007/978-1-4471-4072-6_20
https://doi.org/10.1007/978-1-4471-4072-6_20
Autor:
Shirin Saleem, Yue Wu, Ehry MacRostie, Pradeep Natarajan, Rohit Prasad, Fred Bernardin, Prem Natarajan
Publikováno v:
ICME
Robust, real-time, multi-class logo detection in high resolution broadcast videos presents several difficult challenges. For most logos we only have a few training samples, which makes training robust classifiers hard. Also, logos could potentially o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9b492f854623c1cd581a4cd8d96ab1f8
https://doi.org/10.1109/icme.2011.6012121
https://doi.org/10.1109/icme.2011.6012121
Autor:
Matin Kamali, Prem Natarajan, Huaigu Cao, Rohit Prasad, Stephen Rawls, Krishna Subramanian, Ehry MacRostie
Publikováno v:
Document Analysis Systems
In this paper, we introduce a new operational platform for end-to-end document image analysis, recognition, and machine translation. The Raytheon BBN Document Analysis Service (BBN DAS) performs the following operations on scanned machine-print docum
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5c9586704c25e840bc812964bf1cb38b
https://doi.org/10.1145/1815330.1815388
https://doi.org/10.1145/1815330.1815388
Publikováno v:
Advances in Pattern Recognition ISBN: 9781848003293
The BBN Byblos OCR system implements a script-independent methodology for OCR using hidden Markov models (HMMs). We have successfully ported the system to Arabic, English, Chinese, Pashto, and Japanese. In this chapter, we report on our recent effort
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cb461008f0f7ff98e1c1e52484e37e4a
https://doi.org/10.1007/978-1-84800-330-9_9
https://doi.org/10.1007/978-1-84800-330-9_9
Publikováno v:
Document Analysis Systems
In this paper we present an end-to-end trainable optical character recognition (OCR) system for recognizing machine-printed text in Thai documents. The end-to-end OCR system is based on a script-independent methodology using hidden Markov models. Our
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d5920e0d67e9996dec18cb82195e599d
https://doi.org/10.1109/das.2008.76
https://doi.org/10.1109/das.2008.76
Publikováno v:
Arabic and Chinese Handwriting Recognition ISBN: 9783540781981
SACH
SACH
This paper introduces a script-independent methodology for multilingual offline handwriting recognition (OHR) based on the use of Hidden Markov Models (HMM). The OHR methodology extends our script-independent approach for OCR of machine-printed text
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::50b997c700212098a30eda1b58abf27b
https://doi.org/10.1007/978-3-540-78199-8_14
https://doi.org/10.1007/978-3-540-78199-8_14
Publikováno v:
ICASSP
Text in video sequences can provide key indexing information. In particular, videotext is rich in named entities (NEs) and detection of such entities is critical for search applications. Traditional approaches for detecting NEs in OCR output look for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::da70029b22cf72681b53bf95b096fd72
https://doi.org/10.1109/icassp.2008.4517841
https://doi.org/10.1109/icassp.2008.4517841
Publikováno v:
ICASSP
Optical character recognition (OCR) of overlaid text in video streams is a challenging problem due to various factors including the presence of dynamic backgrounds, color, and low resolution. In video feeds such as Broadcast News, a particular overla
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bccb66d4113c94f7b85644f6512b8ee8
https://doi.org/10.1109/icassp.2008.4517870
https://doi.org/10.1109/icassp.2008.4517870
Publikováno v:
ICDAR
In this paper we present a robust multi-pass page segmentation algorithm. The first pass uses a modified smearing algorithm and the second pass performs a hybrid of bottom-up and top-down segmentation on the output of the first pass. Unlike tradition
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bb76f94af254383735bb74cae7c81d60
https://doi.org/10.1109/icdar.2007.4378738
https://doi.org/10.1109/icdar.2007.4378738
Publikováno v:
DRR
The BBN Byblos OCR system implements a script-independent methodology for OCR using Hidden Markov Models (HMMs). We have successfully ported the system to Arabic, English, Chinese, Pashto, and Japanese. In this paper, we report on our recent effort i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5af5c6c44d84eaf8ac51038c02beaed5
https://doi.org/10.1117/12.588810
https://doi.org/10.1117/12.588810