Fruit Fly Classification via Convolutional Neural Network

Peng, Yingqiong; Liao, Muxin; Huang, Wenzhun; Deng, Hong Wen; Ao, Ling; Hua, Jing

doi:10.1109/cac.2018.8623178

Cited by 4 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If adopting the classic deep networks directly, e.g., the MobileNet-V2 [56], VGG16 [57], DenseNet121 [58], and ResNet50 [48], the roles of local features from local parts will not be well executed because the global high-level semantic features are used for the classification of species. Especially, most of the recent research on recognizing fruit flies [24,[27][28][29][30]60] directly utilized or combined the existing classic networks. Compared with them, in our MAMPNet, the local parts are located by and focused on the attention mechanism, and their features are combined with the global features for classifying the species.…”

Section: Discussion On Recognition Of Citrus Fliesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Recently, advancements in deep learning have led to a great deal of Convolution Neural Networks (CNNs)-based works for the identification of fruit flies' species [27][28][29][30][31], which demonstrates the strong robustness and capability of CNNs in contrast to the handcrafted descriptors. However, most work directly adopts existing pre-trained models or fine-trains them to perform classifications [27][28][29][30][31], which omits the characteristic of finegrained classification in this recognition task of citrus flies. Inspired by the advancements of CNNs in the FGVC domain [32][33][34][35][36][37][38], e.g., the network architectures detecting and combining parts [32][33][34] and the attention mechanism based schemes [35][36][37][38], we proposed a Multi-Attention and Multi-Part convolutional neural Network (MAMPNet) to exploit the discriminative features of local vital parts such as wings, thoraces, and abdomens according to the expert knowledge of identifying the species of citrus flies.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Motor-Driven and Computer Vision-Based Intelligent E-Trap for Monitoring Citrus Flies

et al. 2021

View full text Add to dashboard Cite

Citrus flies are important quarantine pests in citrus plantations. Electronic traps (e-traps) based on computer vision are the most popular types of equipment for monitoring them. However, most current e-traps are inefficient and unreliable due to requiring manual operations and lack of reliable detection and identification algorithms of citrus fly images. To address these problems, this paper presents a monitoring scheme based on automatic e-traps and novel recognition algorithms. In this scheme, the prototype of an automatic motor-driven e-trap is firstly designed based on a yellow sticky trap. A motor autocontrol algorithm based on Local Binary Pattern (LBP) image analysis is proposed to automatically replace attractants in the e-trap for long-acting work. Furthermore, for efficient and reliable statistics of captured citrus flies, based on the differences between two successive sampling images of the e-trap, a simple and effective detection algorithm is presented to continuously detect the newly captured citrus flies from the collected images of the e-trap. Moreover, a Multi-Attention and Multi-Part convolutional neural Network (MAMPNet) is proposed to exploit discriminative local features of citrus fly images to recognize the citrus flies in the images. Finally, extensive simulation experiments validate the feasibility and efficiency of the designed e-trap prototype and its autocontrol algorithm, as well as the reliability and effectiveness of the proposed detection and recognition algorithms for citrus flies.

show abstract

Section: Discussion On Recognition Of Citrus Fliesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Motor-Driven and Computer Vision-Based Intelligent E-Trap for Monitoring Citrus Flies

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The damage caused by economically important fruit flies could also be significantly reduced by using automatic or semi-automatic image analysis systems [22]. Due to the shortcomings of conventional fruit fly classification systems, Peng et al [122] proposed a convolutional neural network algorithm that automatically extracts features to build a classification model for the four Bactrocera species. The developed model automatically extracts the features of the fruit fly pests for effective identification with an accuracy rate of 97.19% and solves the problems caused by the manual classification methods.…”

Section: Fruit Flies (Tephritidae Drosophilidae)mentioning

confidence: 99%

Automatic Pest Monitoring Systems in Apple Production under Changing Climatic Conditions

et al. 2022

View full text Add to dashboard Cite

Apple is one of the most important economic fruit crops in the world. Despite all the strategies of integrated pest management (IPM), insecticides are still frequently used in its cultivation. In addition, pest phenology is extremely influenced by changing climatic conditions. The frequent spread of invasive species, unexpected pest outbreaks, and the development of additional generations are some of the problems posed by climate change. The adopted strategies of IPM therefore need to be changed as do the current monitoring techniques, which are increasingly unreliable and outdated. The need for more sophisticated, accurate, and efficient monitoring techniques is leading to increasing development of automated pest monitoring systems. In this paper, we summarize the automatic methods (image analysis systems, smart traps, sensors, decision support systems, etc.) used to monitor the major pest in apple production (Cydia pomonella L.) and other important apple pests (Leucoptera maifoliella Costa, Grapholita molesta Busck, Halyomorpha halys Stål, and fruit flies—Tephritidae and Drosophilidae) to improve sustainable pest management under frequently changing climatic conditions.

show abstract

“…The classification accuracy obtained is 96.75% [4]. Another classification model based on a convolutional neural network that is capable of extracting the features automatically with an accuracy of 97.19% [5]. A fully convolutional network (FCN) is trained and segmented the image in two categories: one in the fruit pixels and other in non-fruit pixels [6].…”

Section: Previous Workmentioning

confidence: 99%

Automatic Detection and Classification of Nutrients Deficiency in Fruit Based on Automated Machine Learning

Yogesh*,

Dubey,

Ratan

2019

IJEAT

View full text Add to dashboard Cite

Machine learning-based classification and detection of surface defect of fruit involve manual feature identification and selection from input datasets. Deep learning discovers the useful features from the input data. This approach simplifies the training of the neural network and makes them faster. The selection of useful patterns from the fruit features results in better accuracy. The number of layers represents the depth of the model. Neural network provides learning to the model. As the dataset contains many features. It is obvious that all features are not relevant to the system. The proposed system learns from these features by identifying the pattern and select the relevant features. This is the most crucial phase of the machine learning to identify the appropriate features to make the system faster and accurate. In this paper, we propose solving fruit surface defect detection using Automated Machine Learning (AML). The outcome is the prediction of the fruit surface defect in terms of probability due to nutrient deficiency

show abstract

Fruit Fly Classification via Convolutional Neural Network

Cited by 4 publications

References 7 publications

A Motor-Driven and Computer Vision-Based Intelligent E-Trap for Monitoring Citrus Flies

A Motor-Driven and Computer Vision-Based Intelligent E-Trap for Monitoring Citrus Flies

Automatic Pest Monitoring Systems in Apple Production under Changing Climatic Conditions

Automatic Detection and Classification of Nutrients Deficiency in Fruit Based on Automated Machine Learning

Contact Info

Product

Resources

About