The Experts below are selected from a list of 18279 Experts worldwide ranked by ideXlab platform
Danijel Skočaj - One of the best experts on this subject based on the ideXlab platform.
-
a compact convolutional neural network for textured surface anomaly detection
Workshop on Applications of Computer Vision, 2018Co-Authors: Domen Racki, Dejan Tomazevic, Danijel SkočajAbstract:Convolutional neural methods have proven to outperform other approaches in various computer vision tasks. In this paper we apply the Deep Learning Technique to the domain of automated visual surface inspection. We design a unified CNN-based framework for segmentation and detection of surface anomalies. We investigate whether a compact CNN architecture, which exhibit fewer parameters that need to be learned, can be used, while retaining high classification accuracy. We propose and evaluate a compact CNN architecture on a dataset consisting of diverse textured surfaces with variously-shaped weakly-labeled anomalies. The proposed approach achieves state-of-the-art results in terms of anomaly segmentation as well as classification.
-
WACV - A Compact Convolutional Neural Network for Textured Surface Anomaly Detection
2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 2018Co-Authors: Domen Racki, Dejan Tomazevic, Danijel SkočajAbstract:Convolutional neural methods have proven to outperform other approaches in various computer vision tasks. In this paper we apply the Deep Learning Technique to the domain of automated visual surface inspection. We design a unified CNN-based framework for segmentation and detection of surface anomalies. We investigate whether a compact CNN architecture, which exhibit fewer parameters that need to be learned, can be used, while retaining high classification accuracy. We propose and evaluate a compact CNN architecture on a dataset consisting of diverse textured surfaces with variously-shaped weakly-labeled anomalies. The proposed approach achieves state-of-the-art results in terms of anomaly segmentation as well as classification.
Frederic Baret - One of the best experts on this subject based on the ideXlab platform.
-
ear density estimation from high resolution rgb imagery using Deep Learning Technique
Agricultural and Forest Meteorology, 2019Co-Authors: Simon Madec, Xiuliang Jin, Benoit De Solan, Shouyang Liu, Florent Duyme, Emmanuelle Héritier, Frederic BaretAbstract:Abstract Wheat ear density estimation is an appealing trait for plant breeders. Current manual counting is tedious and inefficient. In this study we investigated the potential of convolutional neural networks (CNNs) to provide accurate ear density using nadir high spatial resolution RGB images. Two different approaches were investigated, either using the Faster-RCNN state-of-the-art object detector or with the TasselNet local count regression network. Both approaches performed very well (rRMSE≈6%) when applied over the same conditions as those prevailing for the calibration of the models. However, Faster-RCNN was more robust when applied to a dataset acquired at a later stage with ears and background showing a different aspect because of the higher maturity of the plants. Optimal spatial resolution for Faster-RCNN was around 0.3 mm allowing to acquire RGB images from a UAV platform for high-throughput phenotyping of large experiments. Comparison of the estimated ear density with in-situ manual counting shows reasonable agreement considering the relatively small sampling area used for both methods. Faster-RCNN and in-situ counting had high and similar heritability (H²≈85%), demonstrating that ear density derived from high resolution RGB imagery could replace the traditional counting method.
-
Ear density estimation from high resolution RGB imagery using Deep Learning Technique
Agricultural and Forest Meteorology, 2019Co-Authors: Simon Madec, Xiuliang Jin, Benoit De Solan, Shouyang Liu, Florent Duyme, Emmanuelle Héritier, Frederic BaretAbstract:Wheat ear density estimation is an appealing trait for plant breeders. Current manual counting is tedious and inefficient. In this study we investigated the potential of convolutional neural networks (CNNs) to provide accurate ear density using nadir high spatial resolution RGB images. Two different approaches were investigated, either using the Faster-RCNN state-of-the-art object detector or with the TasselNet local count regression network. Both approaches performed very well (rRMSE approximate to 6%) when applied over the same conditions as those prevailing for the calibration of the models. However, Faster-RCNN was more robust when applied to a dataset acquired at a later stage with ears and background showing a different aspect because of the higher maturity of the plants. Optimal spatial resolution for Faster-RCNN was around 0.3 mm allowing to acquire RGB images from a UAV platform for high-throughput phenotyping of large experiments. Comparison of the estimated ear density with in-situ manual counting shows reasonable agreement considering the relatively small sampling area used for both methods. Faster-RCNN and in-situ counting had high and similar heritability (H-2 approximate to 85%), demonstrating that ear density derived from high resolution RGB imagery could replace the traditional counting method.
Fan Yang - One of the best experts on this subject based on the ideXlab platform.
-
Deep Learning Technique for process fault detection and diagnosis in the presence of incomplete data
Chinese Journal of Chemical Engineering, 2020Co-Authors: Cen Guo, Fan Yang, Dexian HuangAbstract:Abstract In modern industrial processes, timely detection and diagnosis of process abnormalities are critical for monitoring process operations. Various fault detection and diagnosis (FDD) methods have been proposed and implemented, the performance of which, however, could be drastically influenced by the common presence of incomplete or missing data in real industrial scenarios. This paper presents a new FDD approach based on an incomplete data imputation Technique for process fault recognition. It employs the modified stacked autoencoder, a Deep Learning structure, in the phase of incomplete data treatment, and classifies data representations rather than the imputed complete data in the phase of fault identification. A benchmark process, the Tennessee Eastman process, is employed to illustrate the effectiveness and applicability of the proposed method.
-
study on a fast solver for poisson s equation based on Deep Learning Technique
IEEE Transactions on Antennas and Propagation, 2020Co-Authors: Tao Shan, Xunwang Dang, Wei Tang, Fan YangAbstract:Fast and efficient computational electromagnetic simulation is a long-standing challenge. In this article, we propose a data-driven model to solve Poisson’s equation that leverages the Learning capacity of Deep Learning Techniques. A Deep convolutional neural network (ConvNet) is trained to predict the electric potential with different excitations and permittivity distribution in 2-D and 3-D models. With a careful design of cost function and proper training data generated from finite-difference solvers, the proposed network enables a reliable simulation with significant speedup and fairly good accuracy. Numerical experiments show that the same ConvNet architecture is effective for both 2-D and 3-D models, and the average relative prediction error of the proposed ConvNet model is less than 3% in both 2-D and 3-D simulations with a significant reduction in computation time compared to the finite-difference solver. This article shows that Deep neural networks have a good Learning capacity for numerical simulations. This could help us to build some fast solvers for some computational electromagnetic problems.
-
Study on a 3D Possion's Equation Slover Based on Deep Learning Technique
2018 IEEE International Conference on Computational Electromagnetics (ICCEM), 2018Co-Authors: Tao Shan, Xunwang Dang, Fan YangAbstract:In this study, we investigate the feasibility of applying Deep Learning Technique to build a 3D electrostatic solver. A Deep convolutional neural network (CNN) is proposed to take advantage of the power of CNN in approximation of highly nonlinear functions and prediction of the potential distribution of electrostatic field. Compared with traditional numerical solvers based on finite difference scheme, this method uses a data-driven end-to-end model. Numerical experiments show that the prediction error can reach below 3 percent and the computing time can be significantly reduced compared with traditional finite difference solvers.
-
Synthesis of Refiectarray Based on Deep Learning Technique
2018 Cross Strait Quad-Regional Radio Science and Wireless Technology Conference (CSQRWC), 2018Co-Authors: Tao Shan, Fan YangAbstract:In this work, we investigate feasibility of applying Deep Learning Techniques to synthesis of reflectarrays. A Deep convolutional neural network is proposed based on AlexNet to predict phase-shift in an reflectarray antenna given a reflected direction. The proposed network takes radiation pattern and beam direction as input, with training and testing data obtained by array theory. After cafefully training, the proposed network demonstrates strong approximation ability and makes correct prediction of phase-shift. Preliminary numerical experiments show that the prediction error of phase-shift can reach below 0.4%. This paper shows that Deep convolutional neural networks can mimic the phase synthesis process of reflectarrays and it has a great potential for real-time phase prediction in more complex problems of array synthesis.
-
Study on a Poisson's Equation Solver Based On Deep Learning Technique
arXiv: Computational Physics, 2017Co-Authors: Tao Shan, Xunwang Dang, Wei Tang, Fan YangAbstract:In this work, we investigated the feasibility of applying Deep Learning Techniques to solve Poisson's equation. A Deep convolutional neural network is set up to predict the distribution of electric potential in 2D or 3D cases. With proper training data generated from a finite difference solver, the strong approximation capability of the Deep convolutional neural network allows it to make correct prediction given information of the source and distribution of permittivity. With applications of L2 regularization, numerical experiments show that the predication error of 2D cases can reach below 1.5\% and the predication of 3D cases can reach below 3\%, with a significant reduction in CPU time compared with the traditional solver based on finite difference methods.
Domen Racki - One of the best experts on this subject based on the ideXlab platform.
-
a compact convolutional neural network for textured surface anomaly detection
Workshop on Applications of Computer Vision, 2018Co-Authors: Domen Racki, Dejan Tomazevic, Danijel SkočajAbstract:Convolutional neural methods have proven to outperform other approaches in various computer vision tasks. In this paper we apply the Deep Learning Technique to the domain of automated visual surface inspection. We design a unified CNN-based framework for segmentation and detection of surface anomalies. We investigate whether a compact CNN architecture, which exhibit fewer parameters that need to be learned, can be used, while retaining high classification accuracy. We propose and evaluate a compact CNN architecture on a dataset consisting of diverse textured surfaces with variously-shaped weakly-labeled anomalies. The proposed approach achieves state-of-the-art results in terms of anomaly segmentation as well as classification.
-
WACV - A Compact Convolutional Neural Network for Textured Surface Anomaly Detection
2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 2018Co-Authors: Domen Racki, Dejan Tomazevic, Danijel SkočajAbstract:Convolutional neural methods have proven to outperform other approaches in various computer vision tasks. In this paper we apply the Deep Learning Technique to the domain of automated visual surface inspection. We design a unified CNN-based framework for segmentation and detection of surface anomalies. We investigate whether a compact CNN architecture, which exhibit fewer parameters that need to be learned, can be used, while retaining high classification accuracy. We propose and evaluate a compact CNN architecture on a dataset consisting of diverse textured surfaces with variously-shaped weakly-labeled anomalies. The proposed approach achieves state-of-the-art results in terms of anomaly segmentation as well as classification.
Simon Madec - One of the best experts on this subject based on the ideXlab platform.
-
ear density estimation from high resolution rgb imagery using Deep Learning Technique
Agricultural and Forest Meteorology, 2019Co-Authors: Simon Madec, Xiuliang Jin, Benoit De Solan, Shouyang Liu, Florent Duyme, Emmanuelle Héritier, Frederic BaretAbstract:Abstract Wheat ear density estimation is an appealing trait for plant breeders. Current manual counting is tedious and inefficient. In this study we investigated the potential of convolutional neural networks (CNNs) to provide accurate ear density using nadir high spatial resolution RGB images. Two different approaches were investigated, either using the Faster-RCNN state-of-the-art object detector or with the TasselNet local count regression network. Both approaches performed very well (rRMSE≈6%) when applied over the same conditions as those prevailing for the calibration of the models. However, Faster-RCNN was more robust when applied to a dataset acquired at a later stage with ears and background showing a different aspect because of the higher maturity of the plants. Optimal spatial resolution for Faster-RCNN was around 0.3 mm allowing to acquire RGB images from a UAV platform for high-throughput phenotyping of large experiments. Comparison of the estimated ear density with in-situ manual counting shows reasonable agreement considering the relatively small sampling area used for both methods. Faster-RCNN and in-situ counting had high and similar heritability (H²≈85%), demonstrating that ear density derived from high resolution RGB imagery could replace the traditional counting method.
-
Ear density estimation from high resolution RGB imagery using Deep Learning Technique
Agricultural and Forest Meteorology, 2019Co-Authors: Simon Madec, Xiuliang Jin, Benoit De Solan, Shouyang Liu, Florent Duyme, Emmanuelle Héritier, Frederic BaretAbstract:Wheat ear density estimation is an appealing trait for plant breeders. Current manual counting is tedious and inefficient. In this study we investigated the potential of convolutional neural networks (CNNs) to provide accurate ear density using nadir high spatial resolution RGB images. Two different approaches were investigated, either using the Faster-RCNN state-of-the-art object detector or with the TasselNet local count regression network. Both approaches performed very well (rRMSE approximate to 6%) when applied over the same conditions as those prevailing for the calibration of the models. However, Faster-RCNN was more robust when applied to a dataset acquired at a later stage with ears and background showing a different aspect because of the higher maturity of the plants. Optimal spatial resolution for Faster-RCNN was around 0.3 mm allowing to acquire RGB images from a UAV platform for high-throughput phenotyping of large experiments. Comparison of the estimated ear density with in-situ manual counting shows reasonable agreement considering the relatively small sampling area used for both methods. Faster-RCNN and in-situ counting had high and similar heritability (H-2 approximate to 85%), demonstrating that ear density derived from high resolution RGB imagery could replace the traditional counting method.
