Deep learning in agriculture: A survey

Kamilaris, Andreas; Prenafeta-Boldú, Francesc X.

doi:10.1016/j.compag.2018.02.016

Cited by 2,881 publications

(1,408 citation statements)

References 57 publications

Supporting

Mentioning

1,373

Contrasting

Unclassified

Order By: Relevance

“…Deep learning, as an effective machine learning algorithm, has been widely studied (LeCun, Bengio, & Hinton, ) and now attracts more attentions from various fields such as remote sensing (G. Cheng & Han, ), agriculture production (Kamilaris & Prenafeta‐Boldu, ), medical science (Shen, Wu, & Suk, ), robotics (Pierson & Gashler, ), healthcare (Miotto, Wang, Wang, Jiang, & Dudley, ), human action recognition (D. Wu, Sharma, & Blumenstein, ), speech recognition (Noda, Yamaguchi, Nakadai, Okuno, & Ogata, ), and so on. Deep learning has showed significant advantages in automatically learning data representations (even for multidomain feature extraction), transfer learning (Ng, Nguyen, Vonikakis, & Winkler, ), dealing with the large amount of data, and obtaining better performance and higher precision (Kamilaris & Prenafeta‐Boldu, ). Convolutional neural network (CNN) and its derivative algorithms have been recognized as the key methods in most of the surveyed articles, which can automatically learn deep features of input digital information for subsequent classification or regression tasks.…”

Section: Introductionmentioning

confidence: 99%

“…Deep learning, as an effective machine learning algorithm, has been widely studied (LeCun, Bengio, & Hinton, 2015) and now attracts more attentions from various fields such as remote sensing (G. Cheng & Han, 2016), agriculture production (Kamilaris & Prenafeta-Boldu, 2018), medical science (Shen, Wu, & Suk, 2017), robotics (Pierson & Gashler, 2017), healthcare (Miotto, Wang, Wang, Jiang, & Dudley, 2018), human action recognition (D. Wu, Sharma, & Blumenstein, 2017), speech recognition (Noda, Yamaguchi, Nakadai, Okuno, & Ogata, 2015), and so on. Deep learning has showed significant advantages in automatically learning data representations (even for multidomain feature Figure 1-A typical CNN structure for image classification.…”

Section: Introductionmentioning

confidence: 99%

“…The black arrows between different layers denote the direction of data transmission. extraction), transfer learning (Ng, Nguyen, Vonikakis, & Winkler, 2015), dealing with the large amount of data, and obtaining better performance and higher precision (Kamilaris & Prenafeta-Boldu, 2018). Convolutional neural network (CNN) and its derivative algorithms have been recognized as the key methods in most of the surveyed articles, which can automatically learn deep features of input digital information for subsequent classification or regression tasks.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Application of Deep Learning in Food: A Review

Zhou

Zhang

Liu

et al. 2019

Comp Rev Food Sci Food Safe

388

166

View full text Add to dashboard Cite

Deep learning has been proved to be an advanced technology for big data analysis with a large number of successful cases in image processing, speech recognition, object detection, and so on. Recently, it has also been introduced in food science and engineering. To our knowledge, this review is the first in the food domain. In this paper, we provided a brief introduction of deep learning and detailedly described the structure of some popular architectures of deep neural networks and the approaches for training a model. We surveyed dozens of articles that used deep learning as the data analysis tool to solve the problems and challenges in food domain, including food recognition, calories estimation, quality detection of fruits, vegetables, meat and aquatic products, food supply chain, and food contamination. The specific problems, the datasets, the preprocessing methods, the networks and frameworks used, the performance achieved, and the comparison with other popular solutions of each research were investigated. We also analyzed the potential of deep learning to be used as an advanced data mining tool in food sensory and consume researches. The result of our survey indicates that deep learning outperforms other methods such as manual feature extractors, conventional machine learning algorithms, and deep learning as a promising tool in food quality and safety inspection. The encouraging results in classification and regression problems achieved by deep learning will attract more research efforts to apply deep learning into the field of food in the future.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Deep Learning in Food: A Review

Zhou

Zhang

Liu

et al. 2019

Comp Rev Food Sci Food Safe

388

166

View full text Add to dashboard Cite

show abstract

“…The CNN used in this approach was a modified for transfer learning of imagenet-caffe-alex network [7] using two extra fully connected layers to the last layer afterfully-connected (FC) layers having different hidden layers (six layers) receptive fields of 11*11*96, 5*5*256, 3*3*384, 3*3*384, 3*3*256, and 1*4096 from C1 to FCa, respectively [20]. A review paper on the application of deep learning in agriculture field, which usually summarized image processing and smart farming and food systems by overviewing 40 researches employing deep learning techniques [21]. Another method uses deep learning for agricultural research was an automatic quality evaluation of fresh-cut iceberg lettuce through packaging material, which deployed CNN through minimum color distortions due to packing defects.…”

Section: Introductionmentioning

confidence: 99%

Application of Deep Learning in Infrared Non-Destructive Testing

Yousefi¹,

Kalhor²,

Usamentiaga³

et al. 2018

Proceedings of the 2018 International Conference on Quantitative InfraRed Thermography

View full text Add to dashboard Cite

Convolutional Neural Networks (CNN) is already known as strong tools in various fields particularly in image processing and computer vision. This paper aims to exploit the power of CNN for transform learning and utilizes it as an unsupervised feature extractor for analyzing defects in a steel specimen with float batten holes and Carbon Fiber Reinforced Plastic (CFRP) composite materials. A pre-trained CNN (ImageNet-VGG-f) has been used for extraction of the vectorized features along with a spectral angler mapper (SAM) to provide a score for defects presented in the image. Empirical results on two aforementioned datasets indicate a promising performance for application of heating and cooling based active thermography with a reasonable computational cost due to unsupervised nature of the algorithm.

show abstract

“…land cover classification (Kamilaris and Prenafeta-Boldú, 2018). We have not seen much application of deep learning in DSM, except for Song et al (2016) which used the deep belief network for predicting soil moisture.…”

mentioning

confidence: 99%

Using deep learning for Digital Soil Mapping

Padarian¹,

Minasny²,

McBratney³

2018

Preprint

View full text Add to dashboard Cite

Abstract. Digital soil mapping has been widely used as a cost-effective method for generating soil maps. However, current DSM data representation rarely incorporate contextual information of the landscape. DSM models are usually calibrated using point observations intersected with spatially corresponding point covariates. Here, we demonstrate the use of the convolutional neural network model that incorporates contextual information surrounding an observation to significantly improve the prediction accuracy over conventional DSM models. We describe a convolutional neural network (CNN) model that takes inputs 5 as images of covariates and explores spatial contextual information by finding non-linear local spatial relationships of neighbouring pixels. Unique features of the proposed model include: input represented as 3D stack of images, data augmentation to reduce overfitting, and simultaneously predicting multiple outputs. Using a soil mapping example in Chile, the CNN model was trained to simultaneously predict soil organic carbon at multiples depths across the country. The results showed the CNN model reduced the error by 30% compared with conventional techniques that only used point information of covariates. In the 10 example of country-wide mapping at 100 m resolution, the neighbourhood size from 3 to 9 pixels is more effective than at a point location and larger neighbourhood sizes. In addition, the CNN model produces less prediction uncertainty and it is able to predict soil carbon at deeper soil layers more accurately. Because the CNN model takes covariate represented as images, it offers a simple and effective framework for future DSM models.

show abstract

Deep learning in agriculture: A survey

Cited by 2,881 publications

References 57 publications

Application of Deep Learning in Food: A Review

Application of Deep Learning in Food: A Review

Application of Deep Learning in Infrared Non-Destructive Testing

Using deep learning for Digital Soil Mapping

Contact Info

Product

Resources

About