bibtex.bib

@inproceedings{ICDAR,
	title={ICDAR 2003 robust reading competitions},
	author={Lucas, Simon M and Panaretos, Alex and Sosa, Luis and Tang, Anthony and Wong, Shirley and Young, Robert},
	booktitle={Document Analysis and Recognition, 2003. Proceedings. Seventh International Conference on},
	pages={682--687},
	year={2003},
	organization={IEEE}
}

@article{polzounov2017wordfence,
	author={Andrei Polzounov and Artsiom Ablavatski and Sergio Escalera and Shijian Lu and Jianfei Cai},
	title={WordFence: Text Detection in Natural Images with Border Awareness},
	journal={CoRR},
	volume={abs/1705.05483},
	year={2017},
	url={http://arxiv.org/abs/1705.05483},
	timestamp={Wed, 07 Jun 2017 14:41:00 +0200},
	biburl={http://dblp.uni-trier.de/rec/bib/journals/corr/PolzounovAELC17},
	bibsource={dblp computer science bibliography, http://dblp.org}
}


@inproceedings{zhang2016multi,
	title={Multi-oriented text detection with fully convolutional networks},
	author={Zhang, Zheng and Zhang, Chengquan and Shen, Wei and Yao, Cong and Liu, Wenyu and Bai, Xiang},
	booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
	pages={4159--4167},
	year={2016}
}


@article{he2017deep,
	title={Deep Direct Regression for Multi-Oriented Scene Text Detection},
	author={He, Wenhao and Zhang, Xu-Yao and Yin, Fei and Liu, Cheng-Lin},
	journal={arXiv preprint arXiv:1703.08289},
	year={2017}
}


@inproceedings{tian2015text,
	title={Text flow: A unified text detection system in natural scene images},
	author={Tian, Shangxuan and Pan, Yifeng and Huang, Chang and Lu, Shijian and Yu, Kai and Lim Tan, Chew},
	booktitle={Proceedings of the IEEE International Conference on Computer Vision},
	pages={4651--4659},
	year={2015}
}


@inproceedings{cho2016canny,
	title={Canny text detector: Fast and robust scene text localization algorithm},
	author={Cho, Hojin and Sung, Myungchul and Jun, Bongjin},
	booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
	pages={3566--3573},
	year={2016}
}

@article{cocotext,
	author={Andreas Veit and Tomas Matera and Lukas Neumann and Jiri Matas and Serge J. Belongie},
	title={COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images},
	journal={CoRR},
	volume={abs/1601.07140},
	year={2016},
	url={http://arxiv.org/abs/1601.07140},
	timestamp={Wed, 07 Jun 2017 14:41:50 +0200},
	biburl={http://dblp.uni-trier.de/rec/bib/journals/corr/VeitMNMB16},
	bibsource={dblp computer science bibliography, http://dblp.org}
}

@inproceedings{synthtext,
	author={Gupta, A. and Vedaldi, A. and Zisserman, A.},
	title={Synthetic Data for Text Localisation in Natural Images},
	booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
	year={2016}
}

@article{pascalvoc,
	author={Everingham, M. and Van~Gool, L. and Williams, C. K. I. and Winn, J. and Zisserman, A.},
	title={The Pascal Visual Object Classes (VOC) Challenge},
	journal={International Journal of Computer Vision},
	volume={88},
	year={2010},
	number={2},
	month={jun},
	pages={303--338} 
} 

@inproceedings{imagenet,
	author={Deng, J. and Dong, W. and Socher, R. and Li, L.-J. and Li, K. and Fei-Fei, L.},
	title={ImageNet: A Large-Scale Hierarchical Image Database},
	booktitle={CVPR09},
	year={2009},
	bibsource={http://www.image-net.org/papers/imagenet_cvpr09.bib}
}

@inproceedings{mscoco,
	author={Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and Dollar, Piotr and Zitnick, Larry},
	title={Microsoft COCO: Common Objects in Context},
	booktitle={ECCV},
	year={2014},
	month={September},
	abstract={We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. This is achieved by gathering images of complex everyday scenes containing common objects in their natural context. Objects are labeled using per-instance segmentations to aid in precise object localization. Our dataset contains photos of 91 objects types that would be easily recognizable by a 4 year old. With a total of 2.5 million labeled instances in 328k images, the creation of our dataset drew upon extensive crowd worker involvement via novel user interfaces for category detection, instance spotting and instance segmentation. We present a detailed statistical analysis of the dataset in comparison to PASCAL, ImageNet, and SUN. Finally, we provide baseline performance analysis for bounding box and segmentation detection results using a Deformable Parts Model.},
	publisher={European Conference on Computer Vision},
	url={https://www.microsoft.com/en-us/research/publication/microsoft-coco-common-objects-in-context/}
}

@article{McCulloch1943,
	author={McCulloch, Warren S. and Pitts, Walter},
	title={A logical calculus of the ideas immanent in nervous activity},
	journal={The bulletin of mathematical biophysics},
	year={1943},
	month={Dec},
	day={01},
	volume={5},
	number={4},
	pages={115--133},
	abstract={Because of the ``all-or-none'' character of nervous activity, neural events and the relations among them can be treated by means of propositional logic. It is found that the behavior of every net can be described in these terms, with the addition of more complicated logical means for nets containing circles; and that for any logical expression satisfying certain conditions, one can find a net behaving in the fashion it describes. It is shown that many particular choices among possible neurophysiological assumptions are equivalent, in the sense that for every net behaving under one assumption, there exists another net which behaves under the other and gives the same results, although perhaps not in the same time. Various applications of the calculus are discussed.},
	issn={1522-9602},
	doi={10.1007/BF02478259},
	url={http://dx.doi.org/10.1007/BF02478259}
}

@book{hebb,
	title={The Organization of Behavior: A Neuropsychological Theory},
	author={Hebb, D.O.},
	isbn={9781135631901},
	url={https://books.google.it/books?id=ddB4AgAAQBAJ},
	year={2005},
	publisher={Taylor \& Francis}
}

@article{rosenblatt1958perceptron,
	title={The perceptron: A probabilistic model for information storage and organization in the brain.},
	author={Rosenblatt, Frank},
	journal={Psychological review},
	volume={65},
	number={6},
	pages={386},
	year={1958},
	publisher={American Psychological Association}
}

@book{minsky1972,
	title={Perceptrons: An Introduction to Computational Geometry},
	author={Minsky, M.L. and Papert, S.},
	isbn={9780262130431},
	url={https://books.google.it/books?id=Ow1OAQAAIAAJ},
	year={1972},
	publisher={Mit Press}
}

@article{LeNet, 
	author={Y. Lecun and L. Bottou and Y. Bengio and P. Haffner}, 
	journal={Proceedings of the IEEE}, 
	title={Gradient-based learning applied to document recognition}, 
	year={1998}, 
	volume={86}, 
	number={11}, 
	pages={2278-2324}, 
	doi={10.1109/5.726791}, 
	ISSN={0018-9219}, 
	month={Nov}
}

@article{Cybenko1989,
	title={Approximation by superpositions of a sigmoidal function},
	author={Cybenko, George},
	journal={Mathematics of Control, Signals, and Systems (MCSS)},
	volume={2},
	number={4},
	pages={303--314},
	year={1989},
	publisher={Springer}
}

@inproceedings{ICDAR2013,
	title={ICDAR 2013 Robust Reading Competition},
	author={Dimosthenis Karatzas and Faisal Shafait and Seiichi Uchida and Masakazu Iwamura and Llu{\'i}s G{\'o}mez i Bigorda and Sergi Robles Mestre and Joan Mas Romeu and David Fern{\'a}ndez Mota and Jon Almaz{\'a}n and Llu{\'i}s-Pere de las Heras},
	booktitle={ICDAR},
	year={2013}
}

@inproceedings{ICDAR2015,
	title={ICDAR 2015 competition on Robust Reading},
	author={Dimosthenis Karatzas and Llu{\'i}s G{\'o}mez i Bigorda and Anguelos Nicolaou and Suman K. Ghosh and Andrew D. Bagdanov and Masakazu Iwamura and Jiri Matas and Lukas Neumann and Vijay Ramaseshan Chandrasekhar and Shijian Lu and Faisal Shafait and Seiichi Uchida and Ernest Valveny},
	booktitle={ICDAR},
	year={2015}
}

@article{Adagrad,
	title={Adaptive subgradient methods for online learning and stochastic optimization},
	author={Duchi, John and Hazan, Elad and Singer, Yoram},
	journal={Journal of Machine Learning Research},
	volume={12},
	number={Jul},
	pages={2121--2159},
	year={2011}
}

@article{Momentum,
	title={Learning representations by back-propagating errors},
	author={Rumelhart, David E and Hinton, Geoffrey E and Williams, Ronald J and others},
	journal={Cognitive modeling},
	volume={5},
	number={3},
	pages={1},
	year={1988}
}

@article{RMSProp,
	title={Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude},
	author={Tieleman, Tijmen and Hinton, Geoffrey},
	journal={COURSERA: Neural networks for machine learning},
	volume={4},
	number={2},
	pages={26--31},
	year={2012}
}

@article{Adam,
	title={Adam: A method for stochastic optimization},
	author={Kingma, Diederik and Ba, Jimmy},
	journal={arXiv preprint arXiv:1412.6980},
	year={2014}
}

@article{dropout,
	title={Dropout: a simple way to prevent neural networks from overfitting.},
	author={Srivastava, Nitish and Hinton, Geoffrey E and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan},
	journal={Journal of machine learning research},
	volume={15},
	number={1},
	pages={1929--1958},
	year={2014}
}

@inproceedings{batchnorm,
	title={Batch normalization: Accelerating deep network training by reducing internal covariate shift},
	author={Ioffe, Sergey and Szegedy, Christian},
	booktitle={International Conference on Machine Learning},
	pages={448--456},
	year={2015}
}

@inproceedings{he2015delving,
	title={Delving deep into rectifiers: Surpassing human-level performance on imagenet classification},
	author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
	booktitle={Proceedings of the IEEE international conference on computer vision},
	pages={1026--1034},
	year={2015}
}

@article{zhang1990parallel,
	title={Parallel distributed processing model with local space-invariant interconnections and its optical architecture},
	author={Zhang, Wei and Itoh, Kazuyoshi and Tanida, Jun and Ichioka, Yoshiki},
	journal={Applied optics},
	volume={29},
	number={32},
	pages={4790--4797},
	year={1990},
	publisher={Optical Society of America}
}

@inproceedings{gpuml,
	title={Using GPUs for machine learning algorithms},
	author={Steinkraus, Dave and Buck, I and Simard, PY},
	booktitle={Document Analysis and Recognition, 2005. Proceedings. Eighth International Conference on},
	pages={1115--1120},
	year={2005},
	organization={IEEE}
}

@inproceedings{gpu2011,
	title={Flexible, high performance convolutional neural networks for image classification},
	author={Ciresan, Dan C and Meier, Ueli and Masci, Jonathan and Maria Gambardella, Luca and Schmidhuber, J{\"u}rgen},
	booktitle={IJCAI Proceedings-International Joint Conference on Artificial Intelligence},
	volume={22},
	number={1},
	pages={1237},
	year={2011},
	organization={Barcelona, Spain}
}

@incollection{alexnet,
	title = {ImageNet Classification with Deep Convolutional Neural Networks},
	author = {Alex Krizhevsky and Sutskever, Ilya and Hinton, Geoffrey E},
	booktitle = {Advances in Neural Information Processing Systems 25},
	editor = {F. Pereira and C. J. C. Burges and L. Bottou and K. Q. Weinberger},
	pages = {1097--1105},
	year = {2012},
	publisher = {Curran Associates, Inc.},
	url = {http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf}
}

@inproceedings{googlenet,
	title={Going deeper with convolutions},
	author={Szegedy, Christian and Liu, Wei and Jia, Yangqing and Sermanet, Pierre and Reed, Scott and Anguelov, Dragomir and Erhan, Dumitru and Vanhoucke, Vincent and Rabinovich, Andrew},
	booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
	pages={1--9},
	year={2015}
}

@article{ILSVRC15,
	Author = {Olga Russakovsky and Jia Deng and Hao Su and Jonathan Krause and Sanjeev Satheesh and Sean Ma and Zhiheng Huang and Andrej Karpathy and Aditya Khosla and Michael Bernstein and Alexander C. Berg and Li Fei-Fei},
	Title = {{ImageNet Large Scale Visual Recognition Challenge}},
	Year = {2015},
	journal = {International Journal of Computer Vision (IJCV)},
	doi = {10.1007/s11263-015-0816-y},
	volume={115},
	number={3},
	pages={211-252}
}

@article{VGG,
	author = {Simonyan, K. and Zisserman, A.},
	title = {Very Deep Convolutional Networks for Large-Scale Image Recognition},
	journal = {CoRR},
	volume = {abs/1409.1556},
	year = {2014}
}

@inproceedings{resnet,
	title={Deep residual learning for image recognition},
	author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
	booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
	pages={770--778},
	year={2016}
}

@article{yolo,
	title={YOLO9000: Better, Faster, Stronger},
	author={Redmon, Joseph and Farhadi, Ali},
	journal={arXiv preprint arXiv:1612.08242},
	year={2016}
}

@inproceedings{fastrcnn,
	author = {Ross Girshick},
	title = {Fast R-CNN},
	booktitle = {International Conference on Computer Vision ({ICCV})},
	year = {2015}
}

@inproceedings{fasterrcnn,
	author = {Shaoqing Ren and Kaiming He and Ross Girshick and Jian Sun},
	title = {Faster {R-CNN}: Towards Real-Time Object Detection with Region Proposal Networks},
	booktitle = {Advances in Neural Information Processing Systems ({NIPS})},
	year = {2015}
}

@inproceedings{fcn,
	title={Fully convolutional networks for semantic segmentation},
	author={Long, Jonathan and Shelhamer, Evan and Darrell, Trevor},
	booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
	pages={3431--3440},
	year={2015}
}

@inproceedings{pixellevel,
	title={Pixel-level encoding and depth layering for instance-level semantic labeling},
	author={Uhrig, Jonas and Cordts, Marius and Franke, Uwe and Brox, Thomas},
	booktitle={German Conference on Pattern Recognition},
	pages={14--25},
	year={2016},
	organization={Springer}
}

@misc{scipy,
	author={Eric Jones and Travis Oliphant and Pearu Peterson and others},
	title={{SciPy}: Open source scientific tools for {Python}},
	year={2001--},
	url="http://www.scipy.org/",
	note={[Online]}
}

@article{numpy,
	title={The NumPy array: a structure for efficient numerical computation},
	author={Walt, St{\'e}fan van der and Colbert, S Chris and Varoquaux, Gael},
	journal={Computing in Science \& Engineering},
	volume={13},
	number={2},
	pages={22--30},
	year={2011},
	publisher={IEEE}
}

@article{opencv,
	author={Bradski, G.},
	citeulike-article-id={2236121},
	journal={Dr. Dobb's Journal of Software Tools},
	keywords={bibtex-import},
	posted-at={2008-01-15 19:21:54},
	priority={4},
	title={{The OpenCV Library}},
	year={2000}
}

@article{shapely,
	title={Shapely},
	author={Gillies, Sean and Bierbaum, Aron and Lautaportti, Kai and Tonnhofer, O},
	journal={GIS-Python Lab},
	year={2013}
}

@article{python,
	title={Interactively testing remote servers using the Python programming language},
	author={van Rossum, Guido and de Boer, Jelke},
	journal={CWi Quarterly},
	volume={4},
	number={4},
	pages={283--303},
	year={1991}
}

@article{tensorflow,
	title={Tensorflow: Large-scale machine learning on heterogeneous distributed systems},
	author={Abadi, Mart{\'\i}n and Agarwal, Ashish and Barham, Paul and Brevdo, Eugene and Chen, Zhifeng and Citro, Craig and Corrado, Greg S and Davis, Andy and Dean, Jeffrey and Devin, Matthieu and others},
	journal={arXiv preprint arXiv:1603.04467},
	year={2016}
}

@misc{pretrained,
	title={{MatConvNet} pretrained models on the {ImageNet ILSVRC} classification task},
	howpublished={\url{http://www.vlfeat.org/matconvnet/pretrained/#imagenet-ilsvrc-classification}}
}

@misc{ICDAR2015results,
	title={{Incidental Scene Text}: Task 1 - {Text Localization}},
	howpublished={\url{http://rrc.cvc.uab.es/?ch=4&com=evaluation&task=1}}
}

@article{ajou,
	title={Scene text detection via connected component clustering and nontext filtering},
	author={Koo, Hyung Il and Kim, Duck Hoon},
	journal={IEEE transactions on image processing},
	volume={22},
	number={6},
	pages={2296--2305},
	year={2013},
	publisher={IEEE}
}

@misc{ICDAR2013results,
	title={{Focused Scene Text}: Task 1 - {Text Localization (IoU)}},
	howpublished={\url{http://rrc.cvc.uab.es/?ch=2&com=evaluation&task=1}}
}

@article{vggmaxnet,
	title={Synthetic data and artificial neural networks for natural scene text recognition},
	author={Jaderberg, Max and Simonyan, Karen and Vedaldi, Andrea and Zisserman, Andrew},
	journal={arXiv preprint arXiv:1406.2227},
	year={2014}
}