Detection and classification of bruises of pears based on thermal images

Zeng, Xiangyu; Miao, Yu; Ubaid, Saima; Gao, Xiumin; Zhuang, Songlin

doi:10.1016/j.postharvbio.2019.111090

Cited by 68 publications

(28 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In 43 of the 71 papers that used CA as a metric, most of the accuracy was higher than 90%, indicating good performance. The highest CA results had values higher than 98%, constituting remarkable results, which were obtained by Amara et al 41 (99.72% with a LeNet model), Feng et al 87 (99.62-100% with a CNN), Zeng et al 36 (99.25% with a modified LeNet model), Brahimi et al 46 (99.18% with GoogLeNet and 98.66% with AlexNet), Alruwaili et al 98 (99.11% with a modified AlexNet model), Neupane et al 78 (98.7% with the Faster R-CNN Inception-V2 model), Giefer et al 56 (98.36% with the VGG-16 model), Karthik et al 92 (98% with a residual CNN), Bauer et al 105 (higher than 98% with a CNN), and Sun et al 100 (93.3%–100% with a DBN). Of the surveyed papers, the results obtained by Zhang et al 85 had the lowest CA (77.8%–84.5% with an FCN model); however, the SVM model used in this particular task (the detection of internal bruises in blueberries) also obtained a low CA (22.5%–67.9%).…”

Section: Summary Discussion and Future Perspectivesmentioning

confidence: 79%

“…The property of a highly hierarchical structure along with the massive learning capability of deep-learning models enables them to carry out predictions and classifications particularly well with good flexibility and adaptability to a wide range of highly complicated data analysis tasks 28 . With the robust capability of automatic feature learning, many complex problems in the field of horticultural science can be solved in an effective and rapid way by utilizing deep-learning methods, includin g various recognition 29 – 31 , yield estimation 32 , 33 , quality detection 27 , 34 , stress phenotyping detection 35 , 36 , growth monitoring 37 , 38 , and other applications 39 , 40 . In the next section, we introduce these applications in detail.…”

Section: Brief Overview Of Deep Learningmentioning

confidence: 99%

“…Examples of CNN architectures that have been used for classification or regression tasks include LeNet 36 , 41 , AlexNet 30 , 42 , VGGNet 43 – 45 , GoogLeNet 46 , and ResNet 47 , 48 (the typical CNNs and corresponding parameters are shown in Table 1 ). For instance, Fig.…”

Section: Brief Overview Of Deep Learningmentioning

confidence: 99%

“…Nondestructive testing technologies, such as near-infrared spectrographs 84 , hyperspectral imagers 85 , 86 and thermal imagers 36 , which can detect the internal state of an object without destroying it, have been considered feasible solutions to traditional detection and analysis techniques 82 . Processing large amounts of hyperspectral image data rapidly and accurately is a great challenge.…”

Section: Applications Of Deep Learning In Horticulture Cropsmentioning

confidence: 99%

See 3 more Smart Citations

Applications of deep-learning approaches in horticultural research: a review

Yang

2021

Hortic Res

View full text Add to dashboard Cite

Deep learning is known as a promising multifunctional tool for processing images and other big data. By assimilating large amounts of heterogeneous data, deep-learning technology provides reliable prediction results for complex and uncertain phenomena. Recently, it has been increasingly used by horticultural researchers to make sense of the large datasets produced during planting and postharvest processes. In this paper, we provided a brief introduction to deep-learning approaches and reviewed 71 recent research works in which deep-learning technologies were applied in the horticultural domain for variety recognition, yield estimation, quality detection, stress phenotyping detection, growth monitoring, and other tasks. We described in detail the application scenarios reported in the relevant literature, along with the applied models and frameworks, the used data, and the overall performance results. Finally, we discussed the current challenges and future trends of deep learning in horticultural research. The aim of this review is to assist researchers and provide guidance for them to fully understand the strengths and possible weaknesses when applying deep learning in horticultural sectors. We also hope that this review will encourage researchers to explore some significant examples of deep learning in horticultural science and will promote the advancement of intelligent horticulture.

show abstract

Section: Summary Discussion and Future Perspectivesmentioning

confidence: 79%

Section: Brief Overview Of Deep Learningmentioning

confidence: 99%

Section: Brief Overview Of Deep Learningmentioning

confidence: 99%

Section: Applications Of Deep Learning In Horticulture Cropsmentioning

confidence: 99%

See 2 more Smart Citations

Applications of deep-learning approaches in horticultural research: a review

Yang

2021

Hortic Res

View full text Add to dashboard Cite

show abstract

“…Evrişimsel sinir ağlarına termal kameradan aldıkları görüntüleri girdi olarak vermişler ve yaraları, ezikleri tespit etmişlerdir. %99.25'lik bir doğrulukla başarılı sonuçlar elde etmişlerdir [14]. Zhao ve arkadaşları [15], nanegiller ailesinden olan sağlık ve gıda sektöründe kullanılan Perilla bitkisinin makine öğrenmesi ile sınıflandırılması işlemini gerçekleştirmişlerdir.…”

Section: Introductionunclassified

Makine Öğrenmesi Algoritmaları Kullanılarak Kayısı İç Çekirdeklerinin Sınıflandırılması

Şenel

2020

Bitlis Eren Üniversitesi Fen Bilimleri Dergisi

View full text Add to dashboard Cite

ÖzKayısı çekirdeği üretimi ve tüketimi fazla olan bir gıda ürünüdür. Kayısı iç çekirdeklerinin makine öğrenmesi algoritmaları kullanılarak, tatlı veya acı olarak sınıflandırılması bu çalışmanın konusunu oluşturmaktadır. Hem tatlı hem de acı kayısı iç çekirdeği için talep miktarı oldukça fazladır. Depolama şartları gibi nedenlerden dolayı kayısı iç çekirdekleri zaman zaman birbirine karışabilmektedir. Bu durum tüketiciler tarafından istenmeyen bir durumdur. Kayısı iç çekirdeğinin ayrıştırılması, gözle her zaman mümkün olmamaktadır. Bu çalışmanın amacı, insan faktörünü ortadan kaldırabilecek bir sınıflandırma yönteminin geliştirilmesidir. Bu sınıflandırma işlemi için k En Yakın Komşu, Destek Vektör Makinesi, Karar Ağacı, Rasgele Orman, Adaptive Boosting, Gaussian Naive Bayes ve Çok Katmanlı Algılayıcı algoritmaları kullanılmıştır. Yeterli sayıda öznitelik ile algoritmaların yarıdan fazlası sınıflandırma işlemini %100 başarı ile elde edebilmektedir. En az sayıda öznitelik kullanarak en iyi başarı Rasgele Orman algoritması ile elde edilmiştir. Sonuçlar göstermiştir ki, kayısı iç çekirdeklerinin sınıflandırılması işlemi makine öğrenmesi algoritmaları ile başarılı bir şekilde gerçekleştirilebilmektedir.

show abstract

Detection of early bruises on apples using hyperspectral reflectance imaging coupled with optimal wavelengths selection and improved watershed segmentation algorithm

Tian¹,

Liu

He³

et al. 2023

J Sci Food Agric

View full text Add to dashboard Cite

BACKGROUNDBruises caused by mechanical collision during the harvesting and storage and transportation period are difficult to detect using traditional machine vision technologies because there is no obvious difference in appearance between bruised and sound tissues. As a result of its fast and non‐destructive characteristics, hyperspectral imaging technology is a potential tool for non‐destructive detection of fruit surface defects.RESULTSIn the present study, visible near infrared hyperspectral reflectance images of healthy apples and bruised apples at 6, 12 and 24 h were obtained. To reduce hyperspectral data dimension, optimal wavelength selection algorithms including principal component analysis (PCA) and band ratio methods were utilized to select the effective wavelengths and enhance the contrast between bruised and sound tissues. Then pseudo‐color image transformation technology combining with improved watershed segmentation algorithm (IWSA) were employed to recognize the bruise spots. The result obtained showed that band ratio images obtained better detection performance than that of PCA. The G component derived from pseudo‐color image of followed by IWSA obtained the best segmentation performance for bruise spots. Finally, a multispectral imaging system for the detection of bruised apple was developed to verify the effectiveness of the proposed two‐band ratio algorithm, obtaining recognition rates of 93.3%, 92.2% and 92.5% for healthy, bruised and overall apples, respectively.CONCLUSIONThe bruise detection algorithm proposed in the present study has potential to detect bruised apple in online practical applications and hyperspectral reflectance imaging offers a useful reference for the detection of surficial defects of fruit. © 2023 Society of Chemical Industry.

show abstract

Detection and classification of bruises of pears based on thermal images

Cited by 68 publications

References 23 publications

Applications of deep-learning approaches in horticultural research: a review

Applications of deep-learning approaches in horticultural research: a review

Makine Öğrenmesi Algoritmaları Kullanılarak Kayısı İç Çekirdeklerinin Sınıflandırılması

Detection of early bruises on apples using hyperspectral reflectance imaging coupled with optimal wavelengths selection and improved watershed segmentation algorithm

Contact Info

Product

Resources

About