Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Shuvozit Ghose"'
Autor:
Ayan Kumar Bhunia, Aneeshan Sain, Amandeep Kumar, Shuvozit Ghose, Pinaki Nath Chowdhury, Yi-Zhe Song
Although text recognition has significantly evolved over the years, state-of-the-art (SOTA) models still struggle in the wild scenarios due to complex backgrounds, varying fonts, uncontrolled illuminations, distortions and other artefacts. This is be
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::85c73d917a1fbd66e960d2ab156acf96
http://arxiv.org/abs/2107.12090
http://arxiv.org/abs/2107.12090
Autor:
Yi-Zhe Song, Aneeshan Sain, Amandeep Kumar, Ayan Kumar Bhunia, Shuvozit Ghose, Pinaki Nath Chowdhury
Publikováno v:
CVPR
Handwritten Text Recognition (HTR) remains a challenging problem to date, largely due to the varying writing styles that exist amongst us. Prior works however generally operate with the assumption that there is a limited number of styles, most of whi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0daf617c5bdee486c6510c698333ae2f
https://doi.org/10.1109/cvpr46437.2021.01557
https://doi.org/10.1109/cvpr46437.2021.01557
Publikováno v:
ICPR
Degraded document image binarization is one of the most challenging tasks in the domain of document image analysis. In this paper, we present a novel approach towards document image binarization by introducing three-player min-max adversarial game. W
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3ef439bd770caf26c03d6fc1c1e1f9dd
http://arxiv.org/abs/2007.07075
http://arxiv.org/abs/2007.07075
Publikováno v:
ICPR
Ground Terrain Recognition is a difficult task as the context information varies significantly over the regions of a ground terrain image. In this paper, we propose a novel approach towards ground-terrain recognition via modeling the Extent-of-Textur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6709dfd046759a6f8bbbe25471ac46af
http://arxiv.org/abs/2004.08141
http://arxiv.org/abs/2004.08141
Publikováno v:
ICASSP
Thumbnails are widely used all over the world as a preview for digital images. In this work we propose a deep neural framework to generate thumbnails of any size and aspect ratio, even for unseen values during training, with high accuracy and precisi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ae8dd1369f8972ef3dc5437310a2d3d8
https://doi.org/10.1109/icassp.2019.8683761
https://doi.org/10.1109/icassp.2019.8683761
Autor:
Umapada Pal, Ankan Kumar Bhunia, Abhirup Das, Shuvozit Ghose, Ayan Kumar Bhunia, Partha Pratim Roy
Logo detection in real-world scene images is an important problem with applications in advertisement and marketing. Existing general-purpose object detection methods require large training data with annotations for every logo class. These methods do
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3d032b4d1d77ca5a5ac2d9f75abb9280
http://arxiv.org/abs/1811.01395
http://arxiv.org/abs/1811.01395
In this paper, a new texture descriptor named "Fractional Local Neighborhood Intensity Pattern" (FLNIP) has been proposed for content based image retrieval (CBIR). It is an extension of the Local Neighborhood Intensity Pattern (LNIP)[1]. FLNIP calcul
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e1a93a1c6e0a9af19e5d9b919df2ad4b
http://arxiv.org/abs/1801.00187
http://arxiv.org/abs/1801.00187