An Effective Data Augmentation Strategy for CNN-Based Pest Localization and Recognition in the Field

Li, Rui; Jia, Xiufang; Hu, Min; Zhou, Man; Li, Dengshan; Liu, Wancai; Wang, Rujing; Zhang, Jie; Xie, Chengjun; Liu, Liu; Wang, Fangyuan; Chen, Hongbo; Chen, Tianjiao; Hu, Haiying

doi:10.1109/access.2019.2949852

Cited by 72 publications

(29 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then we compare NSGT with Geometric Transformation, which has been used as data augmentation [24][25][26] Geometric Transformation provides geometric variations, e.g., rotation and rescale, to increase the dataset's size by enriching data variations. This method can improve recognition performance by 7.8% compared to the original dataset without data augmentation techniques.…”

Section: Analysis and Discussionmentioning

confidence: 99%

“…Geometric Transformation is a data augmentation technique for generating new images with geometric variations, e.g., rotation and rescale [25]. This technique provides variations on the dataset to represent various geometric conditions on the object.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…Geometric Transformation was proposed to overcome insufficient training data to improve recognition performance on Indonesian batik using variations in rotation and scaling [24]. Related research has been carried out by applying augmentation techniques by providing rotations with various degrees to provide data variations in Pest localization and recognition [25]. A similar technique has been applied as data augmentation on Optical Remote Sensing Imagery to improve recognition performance [26].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Neural Style Transfer and Geometric Transformations for Data Augmentation on Balinese Carving Recognition using MobileNet

Darma¹,

Suciati²,

Siahaan³

2020

IJIES

View full text Add to dashboard Cite

The preservation of Balinese carving data is a challenge in recognition of Balinese carving. Balinese carvings are a cultural heritage found in traditional buildings in Bali. The collection of Balinese carving images from public images can be a solution for preserving cultural heritage. However, the lousy quality of taking photographs, e.g., skewed shots, can affect the recognition results. Research on the Balinese carving recognition has existed but only recognizes a predetermined image. We proposed a Neural Style Geometric Transformation (NSGT) as a data augmentation technique for Balinese carvings recognition. NSGT is combining Neural Style Transfers and Geometric Transformations for a small dataset solution. This method provides variations in color, lighting, rotation, rescale, zoom, and the size of the training dataset, to improve recognition performance. We use MobileNet as a feature extractor because it has a small number of parameters, which makes it suitable to be applied on mobile devices. Eight scenarios were tested based on image styles and geometric transformations to get the best results. Based on the results, the proposed method can improve accuracy by up to 16.2%.

show abstract

Section: Analysis and Discussionmentioning

confidence: 99%

Section: Proposed Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Neural Style Transfer and Geometric Transformations for Data Augmentation on Balinese Carving Recognition using MobileNet

Darma¹,

Suciati²,

Siahaan³

2020

IJIES

View full text Add to dashboard Cite

show abstract

“…Thenmozhi and Reddy [64] and Dawei et al [65] proposed techniques for the recognition of pests by image-based transfer learning. Li et al [66] proposed an effective data augmentation strategy for CNN-based pest recognition and localization in the field.…”

Section: F Pest Recognitionmentioning

confidence: 99%

“…The experimental results show the effectiveness of the proposed data augmentation method. [66] "Recognition pest by image-based transfer learning"…”

Section: Synthetic Datasets and Hyperspectral Images (Hsi) Datasetsmentioning

confidence: 99%

Smart Farming Becomes Even Smarter With Deep Learning—A Bibliographical Analysis

Ünal

2020

IEEE Access

View full text Add to dashboard Cite

Smart farming is a new concept that makes agriculture more efficient and effective by using advanced information technologies. The latest advancements in connectivity, automation, and artificial intelligence enable farmers better to monitor all procedures and apply precise treatments determined by machines with superhuman accuracy. Farmers, data scientists and, engineers continue to work on techniques that allow optimizing the human labor required in farming. With valuable information resources improving day by day, smart farming turns into a learning system and becomes even smarter. Deep learning is a type of machine learning method, using artificial neural network principles. The main feature by which deep learning networks are distinguished from neural networks is their depth and that feature makes them capable of discovering latent structures within unlabeled, unstructured data. Deep learning networks that do not need human intervention while performing automatic feature extraction have a significant advantage over previous algorithms. The focus of this study is to explore the advantages of using deep learning in agricultural applications. This bibliography reviews the potential of using deep learning techniques in agricultural industries. The bibliography contains 120 papers from the database of the Science Citation Index on the subject that were published between 2016 and 2019. These studies have been retrieved from 39 scientific journals. The papers are classified into the following categories as disease detection, plant classification, land cover identification, precision livestock farming, pest recognition, object recognition, smart irrigation, phenotyping, and weed detection.

show abstract

Machine learning for pest detection and infestation prediction: A comprehensive review

Mittal,

Gupta,

Aamash

et al. 2024

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Pests pose a major danger to a variety of industries, including agriculture, public health, and ecosystems. Fast and precise pest detection, as well as the ability to predict infestations, are required for effective pest management tactics. This paper provides a comprehensive literature review on this subject to provide an overview of the state of research on pest detection and infestation prediction. The paper investigates and presents background information on the necessity of pest control as well as the difficulty in recognizing pests and forecasting. Several strategies, including approaches to data collection, modeling, and assessment of models, are reviewed in the research described. The authors examine various pest detection methods involving the utilization of convolutional neural networks and several object detection architectures categorized broadly into one‐stage and two‐stage object detection algorithms. Methods for predicting pest infestations that involve regression, classification, and time series forecasting are also thoroughly investigated. The challenges of recognizing pests and predicting infestations are underlined, as are issues with data quality, feature selection, and model interpretability. The report also indicates the limitations to pest detection and infestation prediction as well as intriguing topics for further research on the same. The findings of the literature research demonstrate how Artificial Intelligence, Computer Vision, and the Internet of Things have been applied for Pest Detection and Infestation Prediction. The research serves as a base for surveying and summarizing the approaches utilized for the task of pest detection (an object detection problem) and pest infestation prediction (a forecasting problem) and its findings and recommendations serve as a platform for future study and the development of effective pest management solutions.This article is categorized under: Application Areas > Health Care Technologies > Machine Learning Technologies > Prediction

show abstract

An Effective Data Augmentation Strategy for CNN-Based Pest Localization and Recognition in the Field

Cited by 72 publications

References 27 publications

Neural Style Transfer and Geometric Transformations for Data Augmentation on Balinese Carving Recognition using MobileNet

Neural Style Transfer and Geometric Transformations for Data Augmentation on Balinese Carving Recognition using MobileNet

Smart Farming Becomes Even Smarter With Deep Learning—A Bibliographical Analysis

Machine learning for pest detection and infestation prediction: A comprehensive review

Contact Info

Product

Resources

About