Cotton pests classification in field-based images using deep residual networks

Alves, Adão Nunes; Souza, Witenberg Santiago Rodrigues; Borges, Díbio Leandro

doi:10.1016/j.compag.2020.105488

Cited by 74 publications

(29 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These proves the possibility for multispectral images to detect waterlogging stress of cotton. RGB images are common materials for classification with deep learning [38][39][40] . This paper proved that hyperspectral images of cotton leaves with different waterlogging stress could be classified with CNN models.…”

Section: Detection Of Waterlogging Stressmentioning

confidence: 99%

Detection of cotton waterlogging stress based on hyperspectral images and convolutional neural network

Zhao

Pan

et al. 2021

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

Waterlogging in the early stage of cotton will reduce the number of bolls and do harm to yield. Early detection of waterlogging will help farmers to adjust cotton management and save the loss. To evaluate the application of deep learning for the detection of early waterlogging, this study applied a convolutional neural network (CNN) to classify different durations of waterlogging stress (0, 2, 4, 6, 8, 10 d) based on hyperspectral images (HSIs) of cotton leaves. An experiment was designed to simulate the situation of cotton under waterlogging stress and collect HSIs of visible and near-infrared (VNIR 450-950 nm) spectra with 126 bands 66 d after cotton sowing (66 DAS). It was found the spectral curve reflectance of waterlogging cotton was higher than that of non-waterlogging cotton. Especially near 550 nm and 750 nm, and the spectral curve increased with durations of waterlogging stress and there were 'blue shift' phenomena for the position of the red edge of the spectra. The first principal components of HSIs after band randomly discarding and principal component analysis (PCA) were used to build a dataset. GoogLeNet Inception-v3 (GLNI-v3) and VGG-16 models were selected to detect cotton waterlogging stress with the dataset. The results showed that the average time for a round training for GLNI-v3 was 13.337 s, with a classification accuracy of 96.95% and a loss value of 0.09431. The average time for a round training for VGG-16 was 21.470 s, with a classification accuracy of 97.00% and a loss value of 0.17912. Though these two models had similar classification accuracy and loss value, GLNI-v3 achieved a high accuracy with fewer training iterations. The durations of waterlogging stress of cotton in a short-term can be detected by HSIs of cotton leaves and CNN models are suitable for the classification of HSIs, and this method can provide support for cotton yield estimation and loss assessment after waterlogging.

show abstract

Section: Detection Of Waterlogging Stressmentioning

confidence: 99%

Detection of cotton waterlogging stress based on hyperspectral images and convolutional neural network

Zhao

Pan

et al. 2021

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

show abstract

“…The above studies all use unsupervised clustering and threshold segmentation methods. [15] presents a diseases detection method of cotton leaf spot using the SVM classifier. However, due to the complex background of crop image data and small differences in some details, sometimes such methods are difficult to obtain good results.…”

Section: A Image Preprocessingmentioning

confidence: 99%

“…For example, to prevent overfitting in the training depth separable convolution model, Kamal et al (2019) [16] use image rotation, flipping and shifts enhance the data. Alves et al (2020) [17] enhance the data on the premise of only 100 pieces of data for each category in the data set, increase the original 1600 pictures to 11,520, and improve the accuracy of their ResNet34* model to 98.1%.…”

Section: A Image Preprocessingmentioning

confidence: 99%

“…The above equations are more detailed derivations of the forward process of the Batch Normalization network layer. Equation ( 13) refers to the solution of mini-batch mean; Equation (14) refers to the solution of mini-batch variance; Equation (15) refers to the normalization of each feature x i in mini-batch; And equation ( 16) refers to the post-processing of features by using scaling parameter γ and offset parameter This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ This article has been accepted for publication in a future issue of this journal, but has not been fully edited.…”

Section: ) Bnmentioning

confidence: 99%

See 1 more Smart Citation

An Improved CNN-Based Apple Appearance Quality Classification Method With Small Samples

et al. 2021

View full text Add to dashboard Cite

Apple quality classification is an important means to refine apple sales market and promote apple sales. At present, most of classification methods based on a convolutional neural network (CNN) depend on the quantity of training samples to get good performance. But due to the lack of large-scale public apple appearance dataset, it is a big challenge to obtain high accuracy of apple appearance quality classification with small samples. Therefore, we propose an improved method based on CNN for apple appearance, quality classification with small samples. Firstly, support vector machine (SVM) is used for image segmentation to avoid the decrease of recognition accuracy caused by environmental noise. Secondly, the segmented image data are input into deep convolutional generative adversarial networks (DCGAN) model, which is used for data expansion. Thirdly, the improved ResNet50 (Imp-ResNet50) is proposed as follows: Replace the fully-connected layer with global average pooling layer; Add the dropout algorithm and batch normalization algorithm at the fully-connected layer; Replace the activation function ReLU with Swish. Through comparative experiments with 360 apple images, we verify the performance of the proposed method including the training image quality, the running time, and classification accuracy. The result shows that the proposed method can obtain high quality training samples and reduce the running time of the method effectively. At the same time, it can realize higher classification accuracy that is up to 96.5%, which is higher than the previous classification method.INDEX TERMS Apple quality classification, SVM, DCGAN, ResNet50.

show abstract

“…Their experimental results showed that the deep CNN model performed much better than other approaches. Alves et al [22] adopted deep residual networks to identify cotton pests. They provided a field-based image dataset containing 1600 images of 15 pests.…”

Section: Related Workmentioning

confidence: 99%

Classification Accuracy Improvement for Small-Size Citrus Pests and Diseases Using Bridge Connections in Deep Neural Networks

Xing

Lee

2020

Sensors

View full text Add to dashboard Cite

Due to the rich vitamin content in citrus fruit, citrus is an important crop around the world. However, the yield of these citrus crops is often reduced due to the damage of various pests and diseases. In order to mitigate these problems, several convolutional neural networks were applied to detect them. It is of note that the performance of these selected models degraded as the size of the target object in the image decreased. To adapt to scale changes, a new feature reuse method named bridge connection was developed. With the help of bridge connections, the accuracy of baseline networks was improved at little additional computation cost. The proposed BridgeNet-19 achieved the highest classification accuracy (95.47%), followed by the pre-trained VGG-19 (95.01%) and VGG-19 with bridge connections (94.73%). The use of bridge connections also strengthens the flexibility of sensors for image acquisition. It is unnecessary to pay more attention to adjusting the distance between a camera and pests and diseases.

show abstract

Cotton pests classification in field-based images using deep residual networks

Cited by 74 publications

References 13 publications

Detection of cotton waterlogging stress based on hyperspectral images and convolutional neural network

Detection of cotton waterlogging stress based on hyperspectral images and convolutional neural network

An Improved CNN-Based Apple Appearance Quality Classification Method With Small Samples

Classification Accuracy Improvement for Small-Size Citrus Pests and Diseases Using Bridge Connections in Deep Neural Networks

Contact Info

Product

Resources

About