PHOCNet: A Deep Convolutional Neural Network for Word Spotting in Handwritten Documents

PHOCNet: A Deep Convolutional Neural Network for Word Spotting in Handwritten Documents. Sudholt, S. & Fink, G. A. December, 2017. arXiv:1604.00187 [cs]

Paper doi abstract bibtex

In recent years, deep convolutional neural networks have achieved state of the art performance in various computer vision task such as classification, detection or segmentation. Due to their outstanding performance, CNNs are more and more used in the field of document image analysis as well. In this work, we present a CNN architecture that is trained with the recently proposed PHOC representation. We show empirically that our CNN architecture is able to outperform state of the art results for various word spotting benchmarks while exhibiting short training and test times.

@misc{sudholt2017,
	title = {{PHOCNet}: {A} {Deep} {Convolutional} {Neural} {Network} for {Word} {Spotting} in {Handwritten} {Documents}},
	shorttitle = {{PHOCNet}},
	url = {http://arxiv.org/abs/1604.00187},
	doi = {10.48550/arXiv.1604.00187},
	abstract = {In recent years, deep convolutional neural networks have achieved state of the art performance in various computer vision task such as classification, detection or segmentation. Due to their outstanding performance, CNNs are more and more used in the field of document image analysis as well. In this work, we present a CNN architecture that is trained with the recently proposed PHOC representation. We show empirically that our CNN architecture is able to outperform state of the art results for various word spotting benchmarks while exhibiting short training and test times.},
	urldate = {2023-11-17},
	publisher = {arXiv},
	author = {Sudholt, Sebastian and Fink, Gernot A.},
	month = dec,
	year = {2017},
	note = {arXiv:1604.00187 [cs]},
	keywords = {Computer Science - Computer Vision and Pattern Recognition},
}

Downloads: 0

{"_id":"ibDrg8gudcWMY7Q7Q","bibbaseid":"sudholt-fink-phocnetadeepconvolutionalneuralnetworkforwordspottinginhandwrittendocuments-2017","author_short":["Sudholt, S.","Fink, G. A."],"bibdata":{"bibtype":"misc","type":"misc","title":"PHOCNet: A Deep Convolutional Neural Network for Word Spotting in Handwritten Documents","shorttitle":"PHOCNet","url":"http://arxiv.org/abs/1604.00187","doi":"10.48550/arXiv.1604.00187","abstract":"In recent years, deep convolutional neural networks have achieved state of the art performance in various computer vision task such as classification, detection or segmentation. Due to their outstanding performance, CNNs are more and more used in the field of document image analysis as well. In this work, we present a CNN architecture that is trained with the recently proposed PHOC representation. We show empirically that our CNN architecture is able to outperform state of the art results for various word spotting benchmarks while exhibiting short training and test times.","urldate":"2023-11-17","publisher":"arXiv","author":[{"propositions":[],"lastnames":["Sudholt"],"firstnames":["Sebastian"],"suffixes":[]},{"propositions":[],"lastnames":["Fink"],"firstnames":["Gernot","A."],"suffixes":[]}],"month":"December","year":"2017","note":"arXiv:1604.00187 [cs]","keywords":"Computer Science - Computer Vision and Pattern Recognition","bibtex":"@misc{sudholt2017,\n\ttitle = {{PHOCNet}: {A} {Deep} {Convolutional} {Neural} {Network} for {Word} {Spotting} in {Handwritten} {Documents}},\n\tshorttitle = {{PHOCNet}},\n\turl = {http://arxiv.org/abs/1604.00187},\n\tdoi = {10.48550/arXiv.1604.00187},\n\tabstract = {In recent years, deep convolutional neural networks have achieved state of the art performance in various computer vision task such as classification, detection or segmentation. Due to their outstanding performance, CNNs are more and more used in the field of document image analysis as well. In this work, we present a CNN architecture that is trained with the recently proposed PHOC representation. We show empirically that our CNN architecture is able to outperform state of the art results for various word spotting benchmarks while exhibiting short training and test times.},\n\turldate = {2023-11-17},\n\tpublisher = {arXiv},\n\tauthor = {Sudholt, Sebastian and Fink, Gernot A.},\n\tmonth = dec,\n\tyear = {2017},\n\tnote = {arXiv:1604.00187 [cs]},\n\tkeywords = {Computer Science - Computer Vision and Pattern Recognition},\n}\n\n","author_short":["Sudholt, S.","Fink, G. A."],"key":"sudholt2017","id":"sudholt2017","bibbaseid":"sudholt-fink-phocnetadeepconvolutionalneuralnetworkforwordspottinginhandwrittendocuments-2017","role":"author","urls":{"Paper":"http://arxiv.org/abs/1604.00187"},"keyword":["Computer Science - Computer Vision and Pattern Recognition"],"metadata":{"authorlinks":{}}},"bibtype":"misc","biburl":"https://api.zotero.org/groups/2386895/collections/7PPRTB2H/items?format=bibtex&limit=100","dataSources":["u8q5uny4m5jJL9RcX"],"keywords":["computer science - computer vision and pattern recognition"],"search_terms":["phocnet","deep","convolutional","neural","network","word","spotting","handwritten","documents","sudholt","fink"],"title":"PHOCNet: A Deep Convolutional Neural Network for Word Spotting in Handwritten Documents","year":2017}