Detection of Strawberry Diseases Using a Convolutional Neural Network

Xiao, Jia-Rong; Chung, Pei-Che; Wu, Hsin-Ying; Phan, Quoc-Hung; Yeh, J. Andrew; Hou, Max Ti-Kuang

doi:10.3390/plants10010031

Cited by 66 publications

(38 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Researchers were further motivated by the significant improvement in human healthcare system as contributed by machine learning and internet of things (IoT) [35]- [39]. Hence, the concept of an automated plant disease detection system was proposed [40]. Machine learning has been utilized to analyze and classify the input data for automatically detecting plant disease [41]- [43].…”

Section: Machine Learning For Ganoderma Disease Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Discovering the Ganoderma Boninense Detection Methods Using Machine Learning: A Review of Manual, Laboratory, and Remote Approaches

et al. 2021

View full text Add to dashboard Cite

Ganoderma disease is a kind of infection that actuates oil palm death. Early detection of Ganoderma disease is the most recommended strategy for proper treatment and disease control plan to be taken promptly. In this paper, the detection methods for Ganoderma disease were reviewed and categorized accordingly. It was found that the combination of remote sensors and machine learning techniques could identify the disease up to four severity levels, including the early stage of infection. It also significantly reduced the labor and time costs compared to the traditional visual inspection and lab-based approaches. In terms of machine learning, support vector machine (SVM) using the idea of finding a hyperplane was suggested as the best classifier in several studies. Despite only one research was done on ANN and no research evaluating CNN and GAN in Ganoderma disease detection; ANN, CNN and GAN were recognized as the potential machine learning techniques that could enhance the detection system.INDEX TERMS Basal stem rot, Ganoderma, machine learning, oil palm, remote sensors.

show abstract

Section: Machine Learning For Ganoderma Disease Detectionmentioning

confidence: 99%

“…Xiao et al [40] proposed a CNN model to detect strawberry diseases thru digital images. The proposed model managed to get a satisfactory classification accuracy rate at 100% for leaf blight cases affecting the crown, leaf, and fruit; 98% for gray mold cases; and 98% for powdery mildew cases.…”

Section: H Convolutional Neural Network (Cnn)mentioning

confidence: 99%

Discovering the Ganoderma Boninense Detection Methods Using Machine Learning: A Review of Manual, Laboratory, and Remote Approaches

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Early works in the area used Convolutional Neural Networks (CNN) to extract features from images and subsequently classify them into different categories (Mohanty et al, 2016). This idea has been applied to various types of crops such as tomato (Fuentes et al, 2017a), cassava (Ramcharan et al, 2017), grapes , strawberry (Xiao et al, 2020), among others. However, limitations in this concept rely, for instance, on situations when multiple diseases appear in the same sample or the type of affection has a local or global influence in the plant.…”

Section: Plant Disease Recognitionmentioning

confidence: 99%

Open Set Self and Across Domain Adaptation for Tomato Disease Recognition With Deep Learning Techniques

et al. 2021

View full text Add to dashboard Cite

Recent advances in automatic recognition systems based on deep learning technology have shown the potential to provide environmental-friendly plant disease monitoring. These systems are able to reliably distinguish plant anomalies under varying environmental conditions as the basis for plant intervention using methods such as classification or detection. However, they often show a performance decay when applied under new field conditions and unseen data. Therefore, in this article, we propose an approach based on the concept of open-set domain adaptation to the task of plant disease recognition to allow existing systems to operate in new environments with unseen conditions and farms. Our system specifically copes diagnosis as an open set learning problem, and mainly operates in the target domain by exploiting a precise estimation of unknown data while maintaining the performance of the known classes. The main framework consists of two modules based on deep learning that perform bounding box detection and open set self and across domain adaptation. The detector is built based on our previous filter bank architecture for plant diseases recognition and enforces domain adaptation from the source to the target domain, by constraining data to be classified as one of the target classes or labeled as unknown otherwise. We perform an extensive evaluation on our tomato plant diseases dataset with three different domain farms, which indicates that our approach can efficiently cope with changes of new field environments during field-testing and observe consistent gains from explicit modeling of unseen data.

show abstract

“…The first step toward food security is the reduction of waste and loss of food. According to the Food and Agriculture Organization (FAO), ∼1.3 billion tons of food are lost/wasted in the food chain from production to retail and by consumers annually (Wieben, 2017), which highlights the importance of the circular economy and consumer education. In addition, economic barriers should be addressed to give access to healthier and sustainable food to low-income consumers (Hirvonen et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Insight on Current Advances in Food Science and Technology for Feeding the World Population

Valoppi¹,

Agustin²,

Abik³

et al. 2021

Front. Sustain. Food Syst.

View full text Add to dashboard Cite

While the world population is steadily increasing, the capacity of Earth to renew its resources is continuously declining. Consequently, the bioresources required for food production are diminishing and new approaches are needed to feed the current and future global population. In the last decades, scientists have developed novel strategies to reduce food loss and waste, improve food production, and find new ingredients, design and build new food structures, and introduce digitalization in the food system. In this work, we provide a general overview on circular economy, alternative technologies for food production such as cellular agriculture, and new sources of ingredients like microalgae, insects, and wood-derived fibers. We present a summary of the whole process of food design using creative problem-solving that fosters food innovation, and digitalization in the food sector such as artificial intelligence, augmented and virtual reality, and blockchain technology. Finally, we briefly discuss the effect of COVID-19 on the food system. This review has been written for a broad audience, covering a wide spectrum and giving insights on the most recent advances in the food science and technology area, presenting examples from both academic and industrial sides, in terms of concepts, technologies, and tools which will possibly help the world to achieve food security in the next 30 years.

show abstract

Detection of Strawberry Diseases Using a Convolutional Neural Network

Cited by 66 publications

References 29 publications

Discovering the Ganoderma Boninense Detection Methods Using Machine Learning: A Review of Manual, Laboratory, and Remote Approaches

Discovering the Ganoderma Boninense Detection Methods Using Machine Learning: A Review of Manual, Laboratory, and Remote Approaches

Open Set Self and Across Domain Adaptation for Tomato Disease Recognition With Deep Learning Techniques

Insight on Current Advances in Food Science and Technology for Feeding the World Population

Contact Info

Product

Resources

About