Article

Blackleg Detection in Potato Plants using Convolutional Neural Networks

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Potato blackleg is a tuber-borne bacterial disease caused by species within the genera Dickeya and Pectobacterium that can cause decay of plant tissue and wilting through the action of cell wall degrading enzymes released by the pathogen. In case of serious infections, tubers may rot before emergence. Management is largely based on the use of pathogen-free seed potato tubers. For this, fields are visually monitored both for certification and also to take out diseased plants to avoid spread to neighboring plants. Imaging potentially offers a quick and non-destructive way to inspect the health of potato plants in a field. Early detection of blackleg diseased plants with modern vision techniques can significantly reduce costs. In this paper, we studied the use of deep learning for detecting blackleg diseased potato plants. Two deep convolutional neural networks were trained on RGB images with healthy and diseased plants. One of these networks (ResNet18) was experimentally found to produce a precision of 95 % and recall of 91 % for the disease class. These results show that convolutional neural networks can be used to detect blackleg diseased potato plants.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Hyperspectral imaging with remote sensing has shown the potential to detect the symptoms of potato virus Y (PVY) [89,90] and potato blackleg caused by Dickeya and Pectobacterium bacteria [91]. These diseases are especially harmful in seed potato crops, and their management is primarily based on the use of certified pathogen-free seed tubers and the removal of symptomatic plants that can serve as an inoculum source. ...
... The authors in [89] and [90] aimed to distinguish infested plants from healthy plants at individual plant level, using spectral reflectance. Image data were acquired using ground-based systems such as a hand-held field spectrometer [89] or tractor-mounted line-scan cameras [90,91]. Reference data were collected by visually monitoring the disease symptoms several times during the growing season. ...
... In addition, the authors in [89] confirmed the visual observations with laboratory analysis, i.e., the presence of PVY using enzyme-linked immunosorbent assay (ELISA) and the identification of the PVY strain using a reverse transcriptase polymerase chain reaction (RT-PCR). The positions of the infected plants were either marked in the field [89] or stored using a real-time kinematic global navigation satellite system (RTK-GNSS) [90,91] that allowed the infested (and healthy) plants to be linked to their acquired images. In contrast with the other disease studies mentioned earlier, the authors in [90,91] used artificial inoculation. ...
Article
Full-text available
The development of UAV (unmanned aerial vehicle) imaging technologies for precision farming applications is rapid, and new studies are published frequently. In cases where measurements are based on aerial imaging, there is the need to have ground truth or reference data in order to develop reliable applications. However, in several precision farming use cases such as pests, weeds, and diseases detection, the reference data can be subjective or relatively difficult to capture. Furthermore, the collection of reference data is usually laborious and time consuming. It also appears that it is difficult to develop generalisable solutions for these areas. This review studies previous research related to pests, weeds, and diseases detection and mapping using UAV imaging in the precision farming context, underpinning the applied reference measurement techniques. The majority of the reviewed studies utilised subjective visual observations of UAV images, and only a few applied in situ measurements. The conclusion of the review is that there is a lack of quantitative and repeatable reference data measurement solutions in the areas of mapping pests, weeds, and diseases. In addition, the results that the studies present should be reflected in the applied references. An option in the future approach could be the use of synthetic data as reference.
... The researchers used morphological op- To recognize damaged tubers, we must consider a set of factors related to the conditions in which tubers are selected. Most often, convolutional neural networks (CNNs) are used to solve such problems, which have recently significantly improved their performance [25][26][27][28][29][30][31]. However, as the authors of [32] have shown, convolutional neural networks working with high-resolution images are not intended to be implemented on devices with weak processors. ...
... We proposed using the Viola-Jones algorithm at the first stage of processing the image from a video camera, which, unlike convolutional neural networks, works in a real-time mode [58][59][60][61][62][63]. This method was created for recognizing human faces and did not give good results when used to detect potato tubers; however, by selecting preprocessing filters, we achieved a probability of 97%, which corresponds to the results of a convolutional neural network (from 91 to 95% in works on convolutional networks for the last three years) [25][26][27][28][29][30][31]. ...
Article
Full-text available
The article discusses the problem of detecting sick or mechanically damaged potatoes using machine learning methods. We proposed an algorithm and developed a system for the rapid detection of damaged tubers. The system can be installed on a conveyor belt in a vegetable store, and it consists of a laptop computer and an action camera, synchronized with a flashlight system. The algorithm consists of two phases. The first phase uses the Viola-Jones algorithm, applied to the filtered action camera image, so it aims to detect separate potato tubers on the conveyor belt. The second phase is the application of a method that we choose based on video capturing conditions. To isolate potatoes infected with certain types of diseases (dry rot, for example), we use the Scale Invariant Feature Transform (SIFT)—Support Vector Machine (SVM) method. In case of inconsistent or weak lighting, the histogram of oriented gradients (HOG)—Bag-of-Visual-Words (BOVW)—neural network (BPNN) method is used. Otherwise, Otsu’s threshold binarization—a convolutional neural network (CNN) method is used. The first phase’s result depends on the conveyor’s speed, the density of tubers on the conveyor, and the accuracy of the video system. With the optimal setting, the result reaches 97%. The second phase’s outcome depends on the method and varies from 80% to 97%. When evaluating the performance of the system, it was found that it allows to detect and classify up to 100 tubers in one second, which significantly exceeds the performance of most similar systems.
... On the other hand, this solution opens the challenge of more sophisticated annotation, which is one of the bottlenecks in Deep Learning in precision agriculture (Chandra et al., 2020). Some related papers have previously asked about the possible improvement of transfer learning by using more related weights to the target problem (Afonso et al., 2019;Yi et al., 2020). In our previous work , this performanceboosting was verified for weeds identification, but in this paper, the results have been the contrary. ...
Article
Early diagnosis of nutrient deficiencies can play a major role in avoiding significant agricultural losses and increasing the final yield while preserving the environment through efficient fertilizer usage. In this work, we study how well nutrient deficiency symptoms can be recognized in RGB images by using deep neural networks and transfer learning. Two different datasets, presenting real-world conditions, were used for this purpose. The first one was the Deep Nutrient Deficiency for Sugar Beet (DND-SB) dataset, which contains 5648 images of sugar beets presenting nitrogen (N), phosphorous (P), and potassium (K) deficiencies, the omission of liming (Ca) and full fertilization. The second one, collected on the field for this research and currently publicly available, was a dataset combining different orange tree images with iron (Fe), potasssium (K), magnesium (Mg), and manganese (Mn) deficiencies. Image classification via fine-tuning with EfficientNetB4, whose original weights came from a noisy student training on ImageNet, obtained the best performances on both datasets with 98.65% and 98.52% Top-1 accuracies. Additionally, the Grad-CAM++ analysis showed that the models were performing an accurate analysis of the most relevant part inside the images. Finally, the use of agricultural transfer learning did not report improvement in the performances.
... In recent years, as a representative of deep learning technology, convolutional neural networks (CNNs) develop rapidly and are widely used for image recognition (Afonso et al., 2019;Altuntaş et al., 2019;Gao et al., 2020;Zhang C. et al., 2020). Compared with traditional machine learning technology, CNNs are naturally embedded with a feature learning part through the combination of low-level features to form more abstract highlevel features. ...
Article
Full-text available
Corn seed materials of different quality were imaged, and a method for defect detection was developed based on a watershed algorithm combined with a two-pathway convolutional neural network (CNN) model. In this study, RGB and near-infrared (NIR) images were acquired with a multispectral camera to train the model, which was proved to be effective in identifying defective seeds and defect-free seeds, with an averaged accuracy of 95.63%, an averaged recall rate of 95.29%, and an F1 (harmonic average evaluation) of 95.46%. Our proposed method was superior to the traditional method that employs a one-pathway CNN with 3-channel RGB images. At the same time, the influence of different parameter settings on the model training was studied. Finally, the application of the object detection method in corn seed defect detection, which may provide an effective tool for high-throughput quality control of corn seeds, was discussed.
... Recently, the performances of CNNs have been significantly improved [19][20][21][22][23][24][25]. When using this type of neural network in combination with powerful graphics-processing units [26], the CNN is the key technology behind new developments in driverless driving and facial recognition. ...
Article
Full-text available
The sustainable functioning of the transport system requires solving the problems of identifying and classifying road users in order to predict the likelihood of accidents and prevent abnormal or emergency situations. The emergence of unmanned vehicles on urban highways significantly increases the risks of such events. To improve road safety, intelligent transport systems, embedded computer vision systems, video surveillance systems, and photo radar systems are used. The main problem is the recognition and classification of objects and critical events in difficult weather conditions. For example, water drops, snow, dust, and dirt on camera lenses make images less accurate in object identification, license plate recognition, vehicle trajectory detection, etc. Part of the image is overlapped, distorted, or blurred. The article proposes a way to improve the accuracy of object identification by using the Canny operator to exclude the damaged areas of the image from consideration by capturing the clear parts of objects and ignoring the blurry ones. Only those parts of the image where this operator has detected the boundaries of the objects are subjected to further processing. To classify images by the remaining whole parts, we propose using a combined approach that includes the histogram-oriented gradient (HOG) method, a bag-of-visual-words (BoVW), and a back propagation neural network (BPNN). For the binary classification of the images of the damaged objects, this method showed a significant advantage over the classical method of convolutional neural networks (CNNs) (79 and 65% accuracies, respectively). The article also presents the results of a multiclass classification of the recognition objects on the basis of the damaged images, with an accuracy spread of 71 to 86%.
... Also, the same type of network is seen being used in [11] for developing a smart agriculture model. Considering the neural network Deep Con-volution Neural Network (DCNN), [12] have used the same neural network model trained to classify corn plant disease and had achieved an accuracy of 88.46%. A CNN model was developed to identify 3 different maize diseases in [13]. ...
... In order to classify plants in the natural environment on a large scale, V Bodhwani et al. 18 designed a 50-layer deep residual learning framework consisting of five stages. M Afonso et al. 19 proposed a quick and non-destructive method based on ResNet18 to identify blackleg disease of potato plants in the field. In order to improve the classification accuracy of cucumber leaf disease spots MA Khan et al. 20 used the Sharif saliency method and pre-trained VGG model to extract deep features which were finally fed to multiclassification SVM for disease recognition. ...
Article
Full-text available
Due to the complex environments in real fields, it is challenging to conduct identification modeling and diagnosis of plant leaf diseases by directly utilizing in-situ images from the system of agricultural Internet of things. To overcome this shortcoming, one approach, based on small sample size and deep convolutional neural network, was proposed for conducting the recognition of cucumber leaf diseases under field conditions. One two-stage segmentation method was presented to acquire the lesion images by extracting the disease spots from cucumber leaves. Subsequently, after implementing rotation and translation, the lesion images were fed into the activation reconstruction generative adversarial networks for data augmentation to generate new training samples. Finally, to improve the identification accuracy of cucumber leaf diseases, we proposed dilated and inception convolutional neural network that was trained using the generated training samples. Experimental results showed that the proposed approach achieved the average identification accuracy of 96.11% and 90.67% when implemented on the data sets of lesion and raw field diseased leaf images with three different diseases of anthracnose, downy mildew, and powdery mildew, significantly outperforming those existing counterparts, indicating that it offered good potential of serving field application of agricultural Internet of things.
... The ResNet-18 and ResNet-50 architectures were retrained by Afonso et al [43] to identify potato blackleg diseases implemented on the Pytorch framework. The datasets, which consist of images of diseased and healthy plants acquired by the authors, were trained for 100epochs on a workstation comprising the Geforce GTX 1080Ti GPU, 12 core intel Xenon E5-1650 processor. ...
Conference Paper
Full-text available
The proliferation in the sizes of data and the tenacity for precision in classification or detection tasks has made machine learning techniques highly relevant other than the traditional classifiers which rely on hand-crafted features. This facilitated the advent of deep learning (DL) which has been lauded for its automatic feature extraction ability and short testing times. However, due to its large number of parameters, it is computationally intensive. Several approaches have been put forward to manage this challenge and a salient one involves the use of DL hardware accelerators such as Graphical Processing Units (GPU), Field Programmable Gate Array (FPGA) and others. To the best of authors knowledge, no significant review has been done as regards DL hardware accelerators in the agricultural domain. Hence, this research is focused on deep learning and various optimization techniques, DL accelerators with impacts and limitations. Finally, recommendations have been proffered which is geared towards improving the performance and efficiency of DL accelerators.
... The ResNet-18 and ResNet-50 architectures were retrained by Afonso et al [43] to identify potato blackleg diseases implemented on the Pytorch framework. The datasets, which consist of images of diseased and healthy plants acquired by the authors, were trained for 100epochs on a workstation comprising the Geforce GTX 1080Ti GPU, 12 core intel Xenon E5-1650 processor. ...
Conference Paper
Full-text available
The proliferation in the size of data and the tenacity for precision in classification/detection tasks has carved a niche for better machine learning techniques other than the traditional classifiers which rely on hand-crafted features. This facilitated the advent of deep learning (DL) which has been lauded for its automatic feature extraction ability and short testing times however due to its large number of parameters, it is computationally intensive. Several approaches have been put forward to manage this challenge and a salient one involves the use of DL hardware accelerators such as Graphical Processing Units (GPU), Field Programmable Gate Array(FPGA), etc. No significant review has been done as regards DL hardware accelerators in the agricultural domain hence this review paper sets out to briefly carry out a background study on deep learning and various optimization techniques, describe the DL accelerators in question; identifying their impacts and limitations. Finally, it would proffer recommendations geared towards improving the performance of DL accelerators.
Chapter
Self-driving cars is rapidly developing area in modern world. Many companies, such as Tesla, are using computer vision technologies to automate driving process by computers using a lot of cameras, integrated in car bodies. One of the problems is weather. We are solving the following task: One day a self-driving car was driving and suddenly it started to rain. The main camera has lost image clarity, except random square area. We need to find out, either a man or a car is in this square area. It is guaranteed that there is a car or a man there. Classes are balanced. For train dataset we have images, positions of square areas with their size and labels. We do not have test dataset, but it is known, that it has only images. So, we need to create algorithm to locate areas, where image is not blurred and only then solve classification task. Finally, model scored using cross-validation.
Chapter
Full-text available
This paper examines the problem of detecting potatoes with mechanical damage using machine learning techniques. In this article, the authors proposed an algorithm for detecting damaged potato tubers on a conveyor belt that is characterized by speed and accuracy of recognition. The distinctive features of the algorithm are combining the methods of Viola-Jones and the convolutional networks, the application of two complementary classifiers, working in the usual gray color and inverted color. Also, the distinguishing feature is that the identified tubers are processed by the classifiers only once, regardless of the time in front of the video camera. The Viola-Jones method was used to identify individual tubers on the conveyor belt, and the convolutional networks were only used to recognize damaged tubers. Moreover, two complementary networks were used for classification, one of which worked in gray gradation and the other in inverted color. The algorithm was implemented using the OpenCV library in Python. Testing was carried out in conditions close to the conditions of potato storage at vegetable bases. The percentage of properly-recognized damaged tubers was 92,1%.
Article
Potatoes are the world’s most important root and tuber crop. A diseased seed potato can produce approximately 10 potato tubers, and the disease can propagate through the seed potato production cycle. To promote stable potato production, quality seed potatoes that are healthy and disease-free should be supplied. The Japanese government established a propagation system for the production and distribution of seed potatoes. Experienced laborers are required in the fields for visual inspection and removal of abnormal plants during seed potato production. To aid visual detection, reduce labor effort, and improve assessment time, we developed an automated abnormal potato plant detection system that utilizes a portable video camera and deep learning models. The proposed system detects abnormal plants or leaves considering the stage of growth. It detects three cases: (i) abnormal potato plants in the early growth stage, (ii) abnormal potato plants in comparison to the surrounding plants, and (iii) abnormal potato leaves. For the abnormal and healthy potato plant classification, the accuracy was ~90%, and the average precision (AP) for detection was 78.2%. Furthermore, the classification accuracy of the abnormal and healthy potato leaf classification was 96.7%, and the AP for detection was 90.5%. Therefore, the proposed system can be used to detect abnormal potato plants.
Article
Full-text available
Deep learning with convolutional neural networks (CNNs) has achieved great success in the classification of various plant diseases. However, a limited number of studies have elucidated the process of inference, leaving it as an untouchable black box. Revealing the CNN to extract the learned feature as an interpretable form not only ensures its reliability but also enables the validation of the model authenticity and the training dataset by human intervention. In this study, a variety of neuron-wise and layer-wise visualization methods were applied using a CNN, trained with a publicly available plant disease image dataset. We showed that neural networks can capture the colors and textures of lesions specific to respective diseases upon diagnosis, which resembles human decision-making. While several visualization methods were used as they are, others had to be optimized to target a specific layer that fully captures the features to generate consequential outputs. Moreover, by interpreting the generated attention maps, we identified several layers that were not contributing to inference and removed such layers inside the network, decreasing the number of parameters by 75% without affecting the classification accuracy. The results provide an impetus for the CNN black box users in the field of plant science to better understand the diagnosis process and lead to further efficient use of deep learning for plant disease diagnosis.
Article
Full-text available
Virus diseases are of high concern in the cultivation of seed potatoes. Once found in the field, virus diseased plants lead to declassification or even rejection of the seed lots resulting in a financial loss. Farmers put in a lot of effort to detect diseased plants and remove virus-diseased plants from the field. Nevertheless, dependent on the cultivar, virus diseased plants can be missed during visual observations in particular in an early stage of cultivation. Therefore, there is a need for fast and objective disease detection. Early detection of diseased plants with modern vision techniques can significantly reduce costs. Laboratory experiments in previous years showed that hyperspectral imaging clearly could distinguish healthy from virus infected potato plants. This paper reports on our first real field experiment. A new imaging setup was designed, consisting of a hyperspectral line-scan camera. Hyperspectral images were taken in the field with a line interval of 5mm. A fully convolutional neural network was adapted for hyperspectral images and trained on two experimental rows in the field. The trained network was validated on two other rows, with different potato cultivars. For three of the four row/date combinations the precision and recall compared to conventional disease assessment exceeded 0.78 and 0.88 respectively. This proves the suitability of this method for real world disease detection.
Article
Full-text available
Soft rot is a severe bacterial disease of potatoes, and soft rot infection can cause significant economic losses during the storage period of potatoes. In this study, potato soft rot was selected as the research object, and a type of potato tuber soft rot disease early detection method based on the electronic nose technology was proposed. An optimized bionic electronic nose gas chamber and a scientific and reasonable sampling device were designed to detect a change in volatile substances of the infected soft rot disease of potato tuber. The infection of soft rot disease in potato tuber samples was detected and identified by using the RBF NN algorithm and SVM algorithm. The results revealed that the proposed bionic electronic nose system can be utilized for early detection of potato tuber soft rot disease. Through comparison and analysis, the recognition rate using the SVM algorithm reached up to 89.7%, and the results were superior to the RBF NN algorithm.
Article
Full-text available
Plant Diseases and Pests are a major challenge in the agriculture sector. An accurate and a faster detection of diseases and pests in plants could help to develop an early treatment technique while substantially reducing economic losses. Recent developments in Deep Neural Networks have allowed researchers to drastically improve the accuracy of object detection and recognition systems. In this paper, we present a deep-learning-based approach to detect diseases and pests in tomato plants using images captured in-place by camera devices with various resolutions. Our goal is to find the more suitable deep-learning architecture for our task. Therefore, we consider three main families of detectors: Faster Region-based Convolutional Neural Network (Faster R-CNN), Region-based Fully Convolutional Network (R-FCN), and Single Shot Multibox Detector (SSD), which for the purpose of this work are called “deep learning meta-architectures”. We combine each of these meta-architectures with “deep feature extractors” such as VGG net and Residual Network (ResNet). We demonstrate the performance of deep meta-architectures and feature extractors, and additionally propose a method for local and global class annotation and data augmentation to increase the accuracy and reduce the number of false positives during training. We train and test our systems end-to-end on our large Tomato Diseases and Pests Dataset, which contains challenging images with diseases and pests, including several inter- and extra-class variations, such as infection status and location in the plant. Experimental results show that our proposed system can effectively recognize nine different types of diseases and pests, with the ability to deal with complex scenarios from a plant’s surrounding area.
Article
Full-text available
Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.
Article
Full-text available
The soft rot Enterobacteriaceae (SRE) Pectobacterium and Dickeya species (formerly classified as pectinolytic Erwinia spp.) cause important diseases on potato and other arable and horticultural crops. They may affect the growing potato plant causing blackleg and are responsible for tuber soft rot in storage thereby reducing yield and quality. Efficient and cost-effective detection and identification methods are essential to investigate the ecology and pathogenesis of the SRE as well as in seed certification programmes. The aim of this review was to collect all existing information on methods available for SRE detection. The review reports on the sampling and preparation of plant material for testing and on over thirty methods to detect, identify and differentiate the soft rot and blackleg causing bacteria to species and subspecies level. These include methods based on biochemical characters, serology, molecular techniques which rely on DNA sequence amplification as well as several less-investigated ones.
Article
Full-text available
The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions. This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenges of collecting large-scale ground truth annotation, highlight key breakthroughs in categorical object recognition, provide detailed a analysis of the current state of the field of large-scale image classification and object detection, and compare the state-of-the-art computer vision accuracy with human accuracy. We conclude with lessons learned in the five years of the challenge, and propose future directions and improvements.
Article
Full-text available
Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day
Technical Report
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively.
Conference Paper
We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 dif- ferent classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implemen- tation of the convolution operation. To reduce overfitting in the fully-connected layers we employed a recently-developed regularization method called dropout that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry
Conference Paper
State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [7] and Fast R-CNN [5] have reduced the running time of these detection networks, exposing region pro-posal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully-convolutional network that simultaneously predicts object bounds and objectness scores at each position. RPNs are trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. With a simple alternating optimization, RPN and Fast R-CNN can be trained to share convolu-tional features. For the very deep VGG-16 model [18], our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007 (73.2% mAP) and 2012 (70.4% mAP) using 300 proposals per image. The code will be released.
Article
Automated conductance measurements in polypectate medium were used for the detection of pathogenic soft rot Erwinia spp. in potato peel extracts. The detection threshold for Erwinia carotovora subsp. atroseptica (Eca) in inoculated peel extracts was ca. 104 colony forming units (cfu) ml-1 when samples were considered positive on the basis of a response within 48 h at 20 C. Detection of E. chrysanthemi (Ech) was less sensitive, only 105 cfu ml-1 peel extract were detected within 36 h at 25 C. The linear correlation between detection times in conductimetry and inoculum levels of Eca and Ech in peel extracts was used for a quantitative estimation of Eca and Ech in naturally contaminated peel extracts. Samples giving a positive conductimetric response had to be confirmed with an enzyme-linked immunosorbent assay (ELISA) or polymerase chain reaction (PCR) for the presence of Eca and Ech, because E. carotovora subsp. carotovora (Ecc) also generated a conductance response. Conductimetry was sensitive and efficient for detection of contamination levels of Eca higher than 104 cfu ml-1 peel extract. For Ech, conductimetric detection was less sensitive and inefficient due to low contamination levels of Ech and the presence of high numbers of Ecc in many samples after enrichment, which interfered with the test. Immunofluorescence cell staining (IF) combined with enrichment and immunofluorescence colony staining (IFC) were suited to detect and quantify low numbers of Eca and Ech at less than 104 cfu ml-1 in peel extracts. However, since false positive and negative reactions in serology were observed, the use of PCR after enrichment, or in combination with IFC to confirm positive results, was required for accurate detection.
Article
Soft rot erwiniae are a group of notorious plant pathogens for which currently available detection methods are inadequate. Based on the polymerase chain reaction, specific and sensitive detection of Erwinia carotovora subsp. atroseptica and E. chrysanthemi in potato tubers has been achieved. The composition of the PCR primers used in two specific detection systems is based on identification of the consensus of sequences of metalloprotease-coding genes present in soft rot erwiniae. Bacterial DNA was extracted from the potato tuber matrix by differential centrifugation in order to avoid interference of potato-derived compounds with the performance of the PCR assay. The PCR assay jjerformed with the E. carotovora subsp. atroseptica specific primer set was found to be capable of distinguishing £. carotovora subsp. atroseptica from all other Erwinia species and the closely related subspecies E. carotovora subsp. carotovora. With the E. chrysanthemi specific primer set, agarose gel electrophoresis is required for unequivocal differentiation between E. chrysanthemi and other erwiniae. Combined with the efficient extraction procedure, the assay allowed specific detection of less than lO' culturable erwiniae per tuber. The specificity and sensitivity of the assay were not reduced in the presence of a 100-fold excess of DNA from both related and unrelated bacteria. This PCR-based method for detection of erwiniae in potato tubers provides a relatively fast and sensitive alternative to routinely applied serological methods.
Deep learning in agriculture: A survey. Computers and electronics in agriculture
  • A Kamilaris
  • F X Prenafeta-Boldú
Kamilaris, A. and Prenafeta-Boldú, F.X. (2018). Deep learning in agriculture: A survey. Computers and electronics in agriculture, 147, 70-90.
Soybean plant disease identification using convolutional neural network
  • S Wallelign
  • M Polceanu
  • C Buche
Wallelign, S., Polceanu, M., and Buche, C. (2018). Soybean plant disease identification using convolutional neural network. In The Thirty-First International Flairs Conference.