2018 |
Ancuti, Cosmin; Ancuti, Codruta O; Timofte, Radu; Alvarez-Gila, Aitor; Galdran, Adrian; Bria, Alessandro; Vazquez-Corral, Javier; Bertalmio, Marcelo; Others, NTIRE 2018 Challenge on Image Dehazing: Methods and Results Artículo en actas Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 891–901, 2018. Enlaces | BibTeX | Etiquetas: dehazing, retinex @inproceedings{ancuti_ntire_2018, title = {NTIRE 2018 Challenge on Image Dehazing: Methods and Results}, author = {Cosmin Ancuti and Codruta O Ancuti and Radu Timofte and Aitor Alvarez-Gila and Adrian Galdran and Alessandro Bria and Javier Vazquez-Corral and Marcelo Bertalmio and Others}, url = {http://openaccess.thecvf.com/content_cvpr_2018_workshops/w13/html/Ancuti_NTIRE_2018_Challenge_CVPR_2018_paper.html}, year = {2018}, date = {2018-06-01}, urldate = {2018-06-07}, booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops}, pages = {891--901}, keywords = {dehazing, retinex}, pubstate = {published}, tppubtype = {inproceedings} } |
Vicente, Asier ; Velasco, Arturo ; Linares, Miguel ; Picon, Artzai ; Arteche, Jose Antonio ; Angel Sainz, Jose New sensor for Electric Arc Furnace arc stability control Conferencia 2018. BibTeX | Etiquetas: ARC STABILITY, ELECTRIC ARC FURNACE, ELECTRICAL EFFICIENCY, HALL EFFECT, MAGNETIC FIELD @conference{Vicente2018, title = {New sensor for Electric Arc Furnace arc stability control}, author = {Asier {Vicente} and Arturo {Velasco} and Miguel {Linares} and Artzai {Picon} and Jose Antonio {Arteche} and Jose {Angel Sainz}}, editor = {7th international congress on science and technology of steelmaking, At Venice - Italy}, year = {2018}, date = {2018-06-01}, keywords = {ARC STABILITY, ELECTRIC ARC FURNACE, ELECTRICAL EFFICIENCY, HALL EFFECT, MAGNETIC FIELD}, pubstate = {published}, tppubtype = {conference} } |
Salado, Juan Pablo; Picón, Artzai; Bereciartua, Arantza; Irusta, Unai Contaje de mitosis en imágenes histológicas mediante redes neuronales convolucionales Artículo de revista 2018. BibTeX | Etiquetas: cnn, mitosis @article{salado2018contaje, title = {Contaje de mitosis en imágenes histológicas mediante redes neuronales convolucionales}, author = {Juan Pablo Salado and Artzai Picón and Arantza Bereciartua and Unai Irusta}, year = {2018}, date = {2018-01-01}, publisher = {Servicio Editorial de la Universidad del Pa'is Vasco/Euskal Herriko Unibertsitatearen Argitalpen Zerbitzua}, keywords = {cnn, mitosis}, pubstate = {published}, tppubtype = {article} } |
Galdran, Adrian; Alvarez-Gila, Aitor; Bria, Alessandro; Vazquez-Corral, Javier; Bertalmío, Marcelo On the Duality Between Retinex and Image Dehazing Artículo en actas Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8212–8221, Salt Lake City, USA, 2018. Enlaces | BibTeX | Etiquetas: dehazing, retinex @inproceedings{galdran_duality_2018, title = {On the Duality Between Retinex and Image Dehazing}, author = {Adrian Galdran and Aitor Alvarez-Gila and Alessandro Bria and Javier Vazquez-Corral and Marcelo Bertalmío}, url = {http://openaccess.thecvf.com/content_cvpr_2018/html/Galdran_On_the_Duality_CVPR_2018_paper.html}, year = {2018}, date = {2018-01-01}, urldate = {2018-06-06}, booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, pages = {8212--8221}, address = {Salt Lake City, USA}, keywords = {dehazing, retinex}, pubstate = {published}, tppubtype = {inproceedings} } |
Picon, Artzai; Alvarez-Gila, Aitor; Seitz, Maximiliam; Ortiz-Barredo, Amaia; Echazarra, Jone; Johannes, Alexander Deep convolutional neural networks for mobile capture device-based crop disease classification in the wild Artículo de revista Computers and Electronics in Agriculture, 2018, ISSN: 0168-1699. Resumen | Enlaces | BibTeX | Etiquetas: cnn, convolutional neural networks, deep learning, disease identification, early pest, image processing, phytopathology, plant disease, precision agriculture @article{picon_deep_2018, title = {Deep convolutional neural networks for mobile capture device-based crop disease classification in the wild}, author = {Artzai Picon and Aitor Alvarez-Gila and Maximiliam Seitz and Amaia Ortiz-Barredo and Jone Echazarra and Alexander Johannes}, url = {http://www.sciencedirect.com/science/article/pii/S0168169917312619 https://computervision.tecnalia.com/wp-content/uploads/2018/10/preprint_computer_and_electronics_10.1016@j.compag.2018.04.002-1.pdf}, doi = {10.1016/j.compag.2018.04.002}, issn = {0168-1699}, year = {2018}, date = {2018-01-01}, urldate = {2018-06-26}, journal = {Computers and Electronics in Agriculture}, abstract = {Fungal infection represents up to 50% of yield losses, making it necessary to apply effective and cost efficient fungicide treatments, whose efficacy depends on infestation type, situation and time. In these cases, a correct and early identification of the specific infection is mandatory to minimize yield losses and increase the efficacy and efficiency of the treatments. Over the last years, a number of image analysis-based methodologies have been proposed for automatic image disease identification. Among these methods, the use of Deep Convolutional Neural Networks (CNNs) has proven tremendously successful for different visual classification tasks. In this work we extend previous work by Johannes et al. (2017) with an adapted Deep Residual Neural Network-based algorithm to deal with the detection of multiple plant diseases in real acquisition conditions where different adaptions for early disease detection have been proposed. This work analyses the performance of early identification of three relevant European endemic wheat diseases: Septoria (Septoria triciti), Tan Spot (Drechslera triciti-repentis) and Rust (Puccinia striiformis & Puccinia recondita). The analysis was done using different mobile devices, and more than 8178 images were captured in two pilot sites in Spain and Germany during 2014,2015 and 2016. Obtained results reveal an overall improvement of the balanced accuracy from 0.78 (Johannes et al., 2017) up to 0.87 under exhaustive testing, and balanced accuracies greater than 0.96 on a pilot test performed in Germany.}, keywords = {cnn, convolutional neural networks, deep learning, disease identification, early pest, image processing, phytopathology, plant disease, precision agriculture}, pubstate = {published}, tppubtype = {article} } Fungal infection represents up to 50% of yield losses, making it necessary to apply effective and cost efficient fungicide treatments, whose efficacy depends on infestation type, situation and time. In these cases, a correct and early identification of the specific infection is mandatory to minimize yield losses and increase the efficacy and efficiency of the treatments. Over the last years, a number of image analysis-based methodologies have been proposed for automatic image disease identification. Among these methods, the use of Deep Convolutional Neural Networks (CNNs) has proven tremendously successful for different visual classification tasks. In this work we extend previous work by Johannes et al. (2017) with an adapted Deep Residual Neural Network-based algorithm to deal with the detection of multiple plant diseases in real acquisition conditions where different adaptions for early disease detection have been proposed. This work analyses the performance of early identification of three relevant European endemic wheat diseases: Septoria (Septoria triciti), Tan Spot (Drechslera triciti-repentis) and Rust (Puccinia striiformis & Puccinia recondita). The analysis was done using different mobile devices, and more than 8178 images were captured in two pilot sites in Spain and Germany during 2014,2015 and 2016. Obtained results reveal an overall improvement of the balanced accuracy from 0.78 (Johannes et al., 2017) up to 0.87 under exhaustive testing, and balanced accuracies greater than 0.96 on a pilot test performed in Germany. |
2017 |
Vicente, Asier; Picon, Artzai; Rodríguez-Vaamonde, Sergio; Arteche, Jose Antonio; Armentia, Jorge; Macaya, Inaki Ladle furnace slag characterization through hyperspectral reflectance regression model for secondary metallurgy process optimization Artículo de revista IEEE Transactions on Industrial Informatics, 2017. Enlaces | BibTeX | Etiquetas: hyperspectral @article{rojo2017ladle, title = {Ladle furnace slag characterization through hyperspectral reflectance regression model for secondary metallurgy process optimization}, author = {Asier Vicente and Artzai Picon and Sergio Rodríguez-Vaamonde and Jose Antonio Arteche and Jorge Armentia and Inaki Macaya}, url = {https://www.researchgate.net/publication/320395826_Fast_method_for_slag_characterization_during_ladle_furnace_steelmaking_process_based_on_spectral_reflectance}, year = {2017}, date = {2017-01-01}, journal = {IEEE Transactions on Industrial Informatics}, publisher = {IEEE}, keywords = {hyperspectral}, pubstate = {published}, tppubtype = {article} } |
Vicente, Asier; Macaya, Iñaki; Picon, Artzai; Arteche, Jose Antonio Fast method for slag characterization during ladle furnace steelmaking process based on spectral reflectance Artículo de revista 2017. Enlaces | BibTeX | Etiquetas: industry @article{vicente2017fast, title = {Fast method for slag characterization during ladle furnace steelmaking process based on spectral reflectance}, author = {Asier Vicente and Iñaki Macaya and Artzai Picon and Jose Antonio Arteche}, url = {https://www.researchgate.net/publication/320395826_Fast_method_for_slag_characterization_during_ladle_furnace_steelmaking_process_based_on_spectral_reflectance}, year = {2017}, date = {2017-01-01}, keywords = {industry}, pubstate = {published}, tppubtype = {article} } |
Johannes, Alexander; Picon, Artzai; Alvarez-Gila, Aitor; Echazarra, Jone; Rodríguez-Vaamonde, Sergio; Navajas, Ana Díez; Ortiz-Barredo, Amaia Automatic plant disease diagnosis using mobile capture devices, applied on a wheat use case Artículo de revista Computers and Electronics in Agriculture, 138 , pp. 200–209, 2017. Enlaces | BibTeX | Etiquetas: plant disease @article{johannes2017automatic, title = {Automatic plant disease diagnosis using mobile capture devices, applied on a wheat use case}, author = {Alexander Johannes and Artzai Picon and Aitor Alvarez-Gila and Jone Echazarra and Sergio Rodríguez-Vaamonde and Ana Díez Navajas and Amaia Ortiz-Barredo}, url = {https://www.sciencedirect.com/science/article/pii/S016816991631050X https://computervision.tecnalia.com/wp-content/uploads/2018/10/10.1016j.compag.2017.04.013_preprint.pdf }, year = {2017}, date = {2017-01-01}, journal = {Computers and Electronics in Agriculture}, volume = {138}, pages = {200--209}, publisher = {Elsevier}, keywords = {plant disease}, pubstate = {published}, tppubtype = {article} } |
Galdran, Adrian; Alvarez-Gila, Aitor; Meyer, Maria Ines; Saratxaga, Cristina L; Araújo, Teresa; Garrote, Estibaliz; Aresta, Guilherme; Costa, Pedro; Mendonça, Ana Maria; Campilho, Aurélio Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis Artículo de revista arXiv preprint arXiv:1703.03702, 2017. Enlaces | BibTeX | Etiquetas: health @article{galdran2017data, title = {Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis}, author = {Adrian Galdran and Aitor Alvarez-Gila and Maria Ines Meyer and Cristina L Saratxaga and Teresa Araújo and Estibaliz Garrote and Guilherme Aresta and Pedro Costa and Ana Maria Mendonça and Aurélio Campilho}, url = {https://arxiv.org/abs/1703.03702}, year = {2017}, date = {2017-01-01}, journal = {arXiv preprint arXiv:1703.03702}, keywords = {health}, pubstate = {published}, tppubtype = {article} } |
Picon, Artzai; Alvarez-Gila, Aitor; Duro, Gorka; Cruz-Lopez, Antonio; Linares, Miguel; Lago, Alberto; Garrote, Estibaliz; Gutierrez Olabarria, Jose Angel High speed quality inspection of hot long metal products surface based on Deep Convolutional Neural Networks Artículo en actas Open session - International Summer School on Deep Learning 2017, Bilbao, Spain, 2017. Enlaces | BibTeX | Etiquetas: deep learning, industry @inproceedings{picon_high_2017, title = {High speed quality inspection of hot long metal products surface based on Deep Convolutional Neural Networks}, author = {Artzai Picon and Aitor Alvarez-Gila and Gorka Duro and Antonio Cruz-Lopez and Miguel Linares and Alberto Lago and Estibaliz Garrote and Gutierrez Olabarria, Jose Angel}, url = {https://computervision.tecnalia.com/wp-content/uploads/2017/06/Surfin_DeepLearn_Bilbao2017.pdf}, year = {2017}, date = {2017-01-01}, booktitle = {Open session - International Summer School on Deep Learning 2017}, address = {Bilbao, Spain}, keywords = {deep learning, industry}, pubstate = {published}, tppubtype = {inproceedings} } |
Galdran, Adrian; Vazquez-Corral, Javier; Pardo, David; Bertalmío, Marcelo Fusion-based variational image dehazing Artículo de revista IEEE Signal Processing Letters, 24 (2), pp. 151–155, 2017. Enlaces | BibTeX | Etiquetas: image processing @article{galdran2017fusion, title = {Fusion-based variational image dehazing}, author = {Adrian Galdran and Javier Vazquez-Corral and David Pardo and Marcelo Bertalmío}, url = {https://ieeexplore.ieee.org/document/7792620/}, year = {2017}, date = {2017-01-01}, journal = {IEEE Signal Processing Letters}, volume = {24}, number = {2}, pages = {151--155}, publisher = {IEEE}, keywords = {image processing}, pubstate = {published}, tppubtype = {article} } |
Galdran, Adrian; Isasi, Alberto; Al-Rawi, Mohammed; Rodriguez, Jonathan; Bastos, Joaquim; Elmgren, Fredrik; Pinto, Marc An efficient non-uniformity correction technique for side-scan sonar imagery Artículo en actas OCEANS 2017-Aberdeen, pp. 1–6, IEEE 2017. Enlaces | BibTeX | Etiquetas: image processing @inproceedings{galdran2017efficient, title = {An efficient non-uniformity correction technique for side-scan sonar imagery}, author = {Adrian Galdran and Alberto Isasi and Mohammed Al-Rawi and Jonathan Rodriguez and Joaquim Bastos and Fredrik Elmgren and Marc Pinto}, url = {https://ieeexplore.ieee.org/document/8084577/}, doi = {doi: 10.1109/OCEANSE.2017.8084577}, year = {2017}, date = {2017-01-01}, booktitle = {OCEANS 2017-Aberdeen}, pages = {1--6}, organization = {IEEE}, keywords = {image processing}, pubstate = {published}, tppubtype = {inproceedings} } |
Al-Rawi, Mohammed; Galdran, Adrian; Isasi, Alberto; Elmgren, Fredrik; Carbonara, Gaetano; Falotico, Egidio; Real-Arce, Daniel A; Rodriguez, Jonathan; Bastos, Joaquim; Pinto, Marc Cubic spline regression based enhancement of side-scan sonar imagery Artículo en actas OCEANS 2017-Aberdeen, pp. 1–7, IEEE 2017. @inproceedings{al2017cubic, title = {Cubic spline regression based enhancement of side-scan sonar imagery}, author = {Mohammed Al-Rawi and Adrian Galdran and Alberto Isasi and Fredrik Elmgren and Gaetano Carbonara and Egidio Falotico and Daniel A Real-Arce and Jonathan Rodriguez and Joaquim Bastos and Marc Pinto}, url = {https://ieeexplore.ieee.org/iel7/8067435/8084562/08084567.pdf}, doi = {doi: 10.1109/OCEANSE.2017.8084567}, year = {2017}, date = {2017-01-01}, booktitle = {OCEANS 2017-Aberdeen}, pages = {1--7}, organization = {IEEE}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Isasi-Andrieu, Alberto; Garrote-Contreras, Estibaliz; Iriondo-Bengoa, Pedro; Aldama-Gant, David; Galdran, Adrian Deflectometry setup definition for automatic chrome surface inspection Artículo en actas Emerging Technologies and Factory Automation (ETFA), 2017 22nd IEEE International Conference on, pp. 1–4, IEEE 2017. Enlaces | BibTeX | Etiquetas: deflectometry @inproceedings{isasi2017deflectometry, title = {Deflectometry setup definition for automatic chrome surface inspection}, author = {Alberto Isasi-Andrieu and Estibaliz Garrote-Contreras and Pedro Iriondo-Bengoa and David Aldama-Gant and Adrian Galdran}, url = {https://ieeexplore.ieee.org/document/8247756/}, doi = {doi: 10.1109/ETFA.2017.8247756}, year = {2017}, date = {2017-01-01}, booktitle = {Emerging Technologies and Factory Automation (ETFA), 2017 22nd IEEE International Conference on}, pages = {1--4}, organization = {IEEE}, keywords = {deflectometry}, pubstate = {published}, tppubtype = {inproceedings} } |
Alvarez-Gila, Aitor; van de Weijer, Joost; Garrote, Estíbaliz Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB Artículo en actas 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 480–490, 2017, (The arxiv.org version contains updated results.). Resumen | Enlaces | BibTeX | Etiquetas: cnn, color, GAN, hyperspectral, neural networks @inproceedings{alvarez-gila_adversarial_2017, title = {Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB}, author = {Aitor Alvarez-Gila and Joost van de Weijer and Estíbaliz Garrote}, url = {https://arxiv.org/abs/1709.00265}, doi = {10.1109/ICCVW.2017.64}, year = {2017}, date = {2017-01-01}, booktitle = {2017 IEEE International Conference on Computer Vision Workshops (ICCVW)}, pages = {480--490}, abstract = {Hyperspectral signal reconstruction aims at recovering the original spectral input that produced a certain trichromatic (RGB) response from a capturing device or observer. Given the heavily underconstrained, non-linear nature of the problem, traditional techniques leverage different statistical properties of the spectral signal in order to build informative priors from real world object reflectances for constructing such RGB to spectral signal mapping. However, most of them treat each sample independently, and thus do not benefit from the contextual information that the spatial dimensions can provide. We pose hyperspectral natural image reconstruction as an image to image mapping learning problem, and apply a conditional generative adversarial framework to help capture spatial semantics. This is the first time Convolutional Neural Networks -and, particularly, Generative Adversarial Networks- are used to solve this task. Quantitative evaluation shows a Root Mean Squared Error (RMSE) drop of 44.7% and a Relative RMSE drop of 47.0% on the ICVL natural hyperspectral image dataset.}, note = {The arxiv.org version contains updated results.}, keywords = {cnn, color, GAN, hyperspectral, neural networks}, pubstate = {published}, tppubtype = {inproceedings} } Hyperspectral signal reconstruction aims at recovering the original spectral input that produced a certain trichromatic (RGB) response from a capturing device or observer. Given the heavily underconstrained, non-linear nature of the problem, traditional techniques leverage different statistical properties of the spectral signal in order to build informative priors from real world object reflectances for constructing such RGB to spectral signal mapping. However, most of them treat each sample independently, and thus do not benefit from the contextual information that the spatial dimensions can provide. We pose hyperspectral natural image reconstruction as an image to image mapping learning problem, and apply a conditional generative adversarial framework to help capture spatial semantics. This is the first time Convolutional Neural Networks -and, particularly, Generative Adversarial Networks- are used to solve this task. Quantitative evaluation shows a Root Mean Squared Error (RMSE) drop of 44.7% and a Relative RMSE drop of 47.0% on the ICVL natural hyperspectral image dataset. |
Picon, Artzai; Irusta, Unai; Alvarez-Gila, Aitor; Aramendi, Elisabete; Garrote, Estibaliz; Ayala, Unai; Alonso, Felipe; Figuera, Carlos Detección de fibrilación ventricular mediante técnicas de aprendizaje profundo Artículo en actas CASEIB 2017 - XXXV Congreso Anual de la Sociedad Espanola de Ingeniería Biomedica, Bilbao, Spain, 2017. Resumen | Enlaces | BibTeX | Etiquetas: cnn, convolutional neural networks, ecg, fibrillation, LSTM, neural networks, recurrent neural networks, RNN @inproceedings{picon_deteccion_2017, title = {Detección de fibrilación ventricular mediante técnicas de aprendizaje profundo}, author = {Artzai Picon and Unai Irusta and Aitor Alvarez-Gila and Elisabete Aramendi and Estibaliz Garrote and Unai Ayala and Felipe Alonso and Carlos Figuera}, url = {https://computervision.tecnalia.com/wp-content/uploads/2018/01/caseib_2017_picon.pdf}, year = {2017}, date = {2017-01-01}, booktitle = {CASEIB 2017 - XXXV Congreso Anual de la Sociedad Espanola de Ingeniería Biomedica}, address = {Bilbao, Spain}, abstract = {La detección de arritmias ventriculares, en particular la fibrilación ventricular (FV), es parte fundamental de los algoritmos de clasificación de arritmias de los desfibriladores. Dichos algoritmos deciden si administrar la descarga de desfibrilación, para lo que clasifican los ritmos en desfibrilables (Sh) o no desfibrilables (NSh). Este trabajo propone un nuevo abordaje para la clasificación Sh/NSh de ritmos basado en un sistema de aprendizaje profundo. Para el trabajo se emplearon tres bases de datos públicas de la plataforma Physionet (CUDB, VFDB y AHADB), y se extrajeron segmentos de 4 y 8 segundos. Se anotaron los segmentos como Sh y NSh en base a las anotaciones de las bases de datos, que fueron auditadas por expertos. Los datos se dividieron por paciente en 80% para desarrollar los algoritmos y 20% para evaluación. El sistema de aprendizaje profundo emplea dos etapas convolucionales seguidas de, una red long-short-term-memory y una etapa final de clasificación basada en red neuronal. A modo de referencia se optimizó un clasificador SVM basado en las características de detección de arritmias ventriculares más eficientes publicadas en la literatura. Se calculó la sensibilidad (Se), ritmos desfibrilables, especificidad (Sp), ritmos no desfibrilables, y la precisión (Acc). El método de aprendizaje profundo proporcionó Se, Sp y Acc de 98.5%, 99.4% y 99.2% para segmentos de 4 segundos y 99.7%, 98.9%, 99.1% para segmentos de 8 segundos. El algoritmo permite detectar FV de forma fiable con segmentos de 4 segundos, corrigiendo un 30% de los errores del método basado en SVM.}, keywords = {cnn, convolutional neural networks, ecg, fibrillation, LSTM, neural networks, recurrent neural networks, RNN}, pubstate = {published}, tppubtype = {inproceedings} } La detección de arritmias ventriculares, en particular la fibrilación ventricular (FV), es parte fundamental de los algoritmos de clasificación de arritmias de los desfibriladores. Dichos algoritmos deciden si administrar la descarga de desfibrilación, para lo que clasifican los ritmos en desfibrilables (Sh) o no desfibrilables (NSh). Este trabajo propone un nuevo abordaje para la clasificación Sh/NSh de ritmos basado en un sistema de aprendizaje profundo. Para el trabajo se emplearon tres bases de datos públicas de la plataforma Physionet (CUDB, VFDB y AHADB), y se extrajeron segmentos de 4 y 8 segundos. Se anotaron los segmentos como Sh y NSh en base a las anotaciones de las bases de datos, que fueron auditadas por expertos. Los datos se dividieron por paciente en 80% para desarrollar los algoritmos y 20% para evaluación. El sistema de aprendizaje profundo emplea dos etapas convolucionales seguidas de, una red long-short-term-memory y una etapa final de clasificación basada en red neuronal. A modo de referencia se optimizó un clasificador SVM basado en las características de detección de arritmias ventriculares más eficientes publicadas en la literatura. Se calculó la sensibilidad (Se), ritmos desfibrilables, especificidad (Sp), ritmos no desfibrilables, y la precisión (Acc). El método de aprendizaje profundo proporcionó Se, Sp y Acc de 98.5%, 99.4% y 99.2% para segmentos de 4 segundos y 99.7%, 98.9%, 99.1% para segmentos de 8 segundos. El algoritmo permite detectar FV de forma fiable con segmentos de 4 segundos, corrigiendo un 30% de los errores del método basado en SVM. |
A.Cobo, ; A.Picón, ; M.Martinez, ; C.L.Saratxaga, ; Z.Amondarain, ; J.M.Lopez-Higuera, Automatic classification of metal allows from their LIBS spectra and its robustness against spectrometer decalibration Artículo de revista 2017. Enlaces | BibTeX | Etiquetas: machine learning @article{cobo2017automatic, title = {Automatic classification of metal allows from their LIBS spectra and its robustness against spectrometer decalibration}, author = {A.Cobo and A.Picón and M.Martinez and C.L.Saratxaga and Z.Amondarain and J.M.Lopez-Higuera}, url = {https://computervision.tecnalia.com/wp-content/uploads/2017/02/poster_emslibs2017.pdf}, year = {2017}, date = {2017-01-01}, keywords = {machine learning}, pubstate = {published}, tppubtype = {article} } |
2016 |
Cruz-Lopez, Antonio; Lago, Alberto; González, Roberto; Alvarez-Gila, Aitor High-speed inspection system finds defects in steel Artículo de revista 2016. Enlaces | BibTeX | Etiquetas: industry, machine vision @article{cruz2016high, title = {High-speed inspection system finds defects in steel}, author = {Antonio Cruz-Lopez and Alberto Lago and Roberto González and Aitor Alvarez-Gila}, url = {https://computervision.tecnalia.com/wp-content/uploads/2016/12/visionsystemsdesign201612-dl.pdf}, year = {2016}, date = {2016-12-01}, keywords = {industry, machine vision}, pubstate = {published}, tppubtype = {article} } |
Bereciartua, Arantza Universidad del País Vasco - UPV/EHU, 2016. Resumen | Enlaces | BibTeX | Etiquetas: active contours, medical image, regularization, segmentation, variational methods @phdthesis{Bereciartua_tesis_2016, title = {Development of image processing algorithms for medical image segmentation. Application on Liver segmentation over mRI multi-sequence images}, author = {Arantza Bereciartua}, url = {https://computervision.tecnalia.com/wp-content/uploads/2016/12/Tesis_Arantza-Bereciartua_Memoria_completa_FINAL.pdf}, year = {2016}, date = {2016-12-01}, school = {Universidad del País Vasco - UPV/EHU}, abstract = {Automatic segmentation (delimitation) of the liver is a complex problem. Partial results have been achieved mainly on images obtained by CT. MRI technique provides more information for diagnostic purposes. However, liver segmentation in MRI images is a challenge due to the presence of characteristic artifacts, such as the partial volumes, the noise, and generally, the low sharpness and the low contrast between organs, so that the boundary between different tissues is often confusing. There are fewer developments on MRI, although these have been steadily increasing in recent years. In this thesis, we present a novel method for multichannel MRI automatic liver segmentation. The proposed method consists of the minimization of a 3D active surface by means of the dual approach to the variational formulation of the underlying problem. This active surface evolves over a probability map that is based on a new compact descriptor comprising spatial and multisequence information of every pixel which is further modeled by means of a liver multivariate statistical model that has been previously generated. This proposed 3D active surface approach naturally integrates volumetric regularization in the statistical model. The advantages of the compact visual descriptor together with the proposed approach result in a fast and accurate 3D segmentation method. The method was tested on 18 healthy liver studies and results were compared to a gold standard made by expert radiologists. Comparisons with other state-of-the-art approaches are provided by means of nine well established quality metrics. The obtained results are in line with the state-of-the-art methodologies, and are even better than them in some cases. A Dice Similarity Coefficient of 98.59 has been achieved.}, keywords = {active contours, medical image, regularization, segmentation, variational methods}, pubstate = {published}, tppubtype = {phdthesis} } Automatic segmentation (delimitation) of the liver is a complex problem. Partial results have been achieved mainly on images obtained by CT. MRI technique provides more information for diagnostic purposes. However, liver segmentation in MRI images is a challenge due to the presence of characteristic artifacts, such as the partial volumes, the noise, and generally, the low sharpness and the low contrast between organs, so that the boundary between different tissues is often confusing. There are fewer developments on MRI, although these have been steadily increasing in recent years. In this thesis, we present a novel method for multichannel MRI automatic liver segmentation. The proposed method consists of the minimization of a 3D active surface by means of the dual approach to the variational formulation of the underlying problem. This active surface evolves over a probability map that is based on a new compact descriptor comprising spatial and multisequence information of every pixel which is further modeled by means of a liver multivariate statistical model that has been previously generated. This proposed 3D active surface approach naturally integrates volumetric regularization in the statistical model. The advantages of the compact visual descriptor together with the proposed approach result in a fast and accurate 3D segmentation method. The method was tested on 18 healthy liver studies and results were compared to a gold standard made by expert radiologists. Comparisons with other state-of-the-art approaches are provided by means of nine well established quality metrics. The obtained results are in line with the state-of-the-art methodologies, and are even better than them in some cases. A Dice Similarity Coefficient of 98.59 has been achieved. |
Bereciartua, Arantza; Picon, Artzai; Galdran, Adrian; Iriondo, Pedro 3D active surfaces for liver segmentation in multisequence MRI images Artículo de revista Computer methods and programs in biomedicine, 132 , pp. 149–160, 2016. Enlaces | BibTeX | Etiquetas: health @article{bereciartua20163d, title = {3D active surfaces for liver segmentation in multisequence MRI images}, author = {Arantza Bereciartua and Artzai Picon and Adrian Galdran and Pedro Iriondo}, url = {https://www.sciencedirect.com/science/article/pii/S0169260715303114}, year = {2016}, date = {2016-01-01}, journal = {Computer methods and programs in biomedicine}, volume = {132}, pages = {149--160}, publisher = {Elsevier}, keywords = {health}, pubstate = {published}, tppubtype = {article} } |
2018 |
NTIRE 2018 Challenge on Image Dehazing: Methods and Results Artículo en actas Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 891–901, 2018. |
New sensor for Electric Arc Furnace arc stability control Conferencia 2018. |
Contaje de mitosis en imágenes histológicas mediante redes neuronales convolucionales Artículo de revista 2018. |
On the Duality Between Retinex and Image Dehazing Artículo en actas Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8212–8221, Salt Lake City, USA, 2018. |
Deep convolutional neural networks for mobile capture device-based crop disease classification in the wild Artículo de revista Computers and Electronics in Agriculture, 2018, ISSN: 0168-1699. |
2017 |
Ladle furnace slag characterization through hyperspectral reflectance regression model for secondary metallurgy process optimization Artículo de revista IEEE Transactions on Industrial Informatics, 2017. |
Fast method for slag characterization during ladle furnace steelmaking process based on spectral reflectance Artículo de revista 2017. |
Automatic plant disease diagnosis using mobile capture devices, applied on a wheat use case Artículo de revista Computers and Electronics in Agriculture, 138 , pp. 200–209, 2017. |
Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis Artículo de revista arXiv preprint arXiv:1703.03702, 2017. |
High speed quality inspection of hot long metal products surface based on Deep Convolutional Neural Networks Artículo en actas Open session - International Summer School on Deep Learning 2017, Bilbao, Spain, 2017. |
Fusion-based variational image dehazing Artículo de revista IEEE Signal Processing Letters, 24 (2), pp. 151–155, 2017. |
An efficient non-uniformity correction technique for side-scan sonar imagery Artículo en actas OCEANS 2017-Aberdeen, pp. 1–6, IEEE 2017. |
Cubic spline regression based enhancement of side-scan sonar imagery Artículo en actas OCEANS 2017-Aberdeen, pp. 1–7, IEEE 2017. |
Deflectometry setup definition for automatic chrome surface inspection Artículo en actas Emerging Technologies and Factory Automation (ETFA), 2017 22nd IEEE International Conference on, pp. 1–4, IEEE 2017. |
Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB Artículo en actas 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 480–490, 2017, (The arxiv.org version contains updated results.). |
Detección de fibrilación ventricular mediante técnicas de aprendizaje profundo Artículo en actas CASEIB 2017 - XXXV Congreso Anual de la Sociedad Espanola de Ingeniería Biomedica, Bilbao, Spain, 2017. |
Automatic classification of metal allows from their LIBS spectra and its robustness against spectrometer decalibration Artículo de revista 2017. |
2016 |
High-speed inspection system finds defects in steel Artículo de revista 2016. |
Universidad del País Vasco - UPV/EHU, 2016. |
3D active surfaces for liver segmentation in multisequence MRI images Artículo de revista Computer methods and programs in biomedicine, 132 , pp. 149–160, 2016. |