Identification of sunflower seeds with deep convolutional neural networks

Kurtulmuş, Ferhat

doi:10.1007/s11694-020-00707-7

Cited by 33 publications

(23 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Additionally, the ROC (Receiver Operating Characteristic) curves and the values of TP (True Positive) Rate, Precision, Recall, F-Measure, ROC (Receiver Operating Characteristic) Area, and PRC (Precision-Recall) Area are included. These values were calculated with the use of the Weka application and manually using the following formulas reported by Kurtulmuş (2020):…”

Section: Discussionmentioning

confidence: 99%

“…Additionally, the ROC (Receiver Operating Characteristic) curves and the values of TP (True Positive) Rate, Precision, Recall, F‐Measure, ROC (Receiver Operating Characteristic) Area, and PRC (Precision‐Recall) Area are included. These values were calculated with the use of the Weka application and manually using the following formulas reported by Kurtulmuş (2020):

Precision = TP / ((), TP + FP)

Recall = TP / ((), TP + FN)

normalF 1 - Measure = 2 \times ((), ((), Precision \times Recall) / ((), Precision + Recall))

where TP is True Positive; FP is False Positive; and FN is False Negative.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A comparative analysis of the discrimination of pepper (Capsicum annuum L.) based on the cross‐section and seed textures determined using image processing

Ropelewska

Szwejda‐Grzybowska

2021

J Food Process Engineering

View full text Add to dashboard Cite

The aim of this study was to develop the models based on the texture parameters of images of selected parts of pepper fruit for cultivar discrimination. This study was aimed to compare the usefulness of textures from cross-sections (slices) and seeds of pepper for distinguishing the different cultivars using the discriminative classifiers.The textures from the cross-sections and seeds were calculated based on images converted to individual color channels. The texture selections and discriminant analyzes were performed separately for color spaces RGB, Lab, XYZ

show abstract

Section: Discussionmentioning

confidence: 99%

Precision = TP / ((), TP + FP)

Recall = TP / ((), TP + FN)

normalF 1 - Measure = 2 \times ((), ((), Precision \times Recall) / ((), Precision + Recall))

where TP is True Positive; FP is False Positive; and FN is False Negative.…”

Section: Methodsmentioning

confidence: 99%

A comparative analysis of the discrimination of pepper (Capsicum annuum L.) based on the cross‐section and seed textures determined using image processing

Ropelewska

Szwejda‐Grzybowska

2021

J Food Process Engineering

View full text Add to dashboard Cite

show abstract

“…Derin öğrenme, günümüzde birçok uygulamada kullanılan; yapay sinir ağlarının ilkelerine dayanan çoklu işlem katmanlarından oluşan bir hesaplama modelidir [11]. Derin öğrenmenin tarım alanında ise arazi örtüsü tanımlaması, hastalık tespiti, akıllı sulama, hassas hayvancılık, bitki sınıflandırması, haşere tanıma, yabancı ot tespiti ve fenotipleme gibi uygulamaları mevcuttur [12][13].…”

Section: Derin öğRenmeunclassified

Antep fıstığının derin öğrenme ile dış kabuk rengine göre sınıflandırılması

Aktaş¹

2022

Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi

View full text Add to dashboard Cite

Antep fıstığı, ticari değeri yüksek bir ürün olup; Türkiye bu alanda ciddi bir üretim ve ihracat potansiyeline sahiptir. Bu ürünlerin yetiştirilmesi kadar toplanması ve ayıklanması da bir o kadar önemli bir işlemdir. Antep fıstıklarının toplandıktan sonra dış kabuk renklerine göre sınıflandırılması fıstığın pazarlanmasından önce yapılması gereken önemli işlemlerden bir tanesidir. Bu çalışmada Antep fıstığının dış rengine göre ayıklanması için derin öğrenme teknikleri kullanılmıştır. Ayıkla işlemi için gerekli olan veri seti endüstriyel bir deney düzeneği kullanarak elde edilmiştir. AlexNet yapısı, elde edilen bu veri setleri ile eğitilip test edilmiştir. Yine farklı yüzdelerdeki ve sayılardaki eğitim, doğrulama ve test verilerinin test doğruluğuna etkisini araştırmak için iki farklı yüzde (%70,%15,%15 ve %60,%20,%20) ve üç farklı sayıda veri seti için ağ yapısı eğitilmiş ve test edilmiştir. En yüksek test doğruluğu %60,%20,%20 oranlarına ait eğitim, doğrulama ve test için sırasıyla 580x2, 193x2 ve 193x2 adet verinin kullanılması ile %98.44 olarak hesaplanmıştır. Ayıklama işlemi derin öğrenme teknikleri ile yüksek doğruluklarda gerçekleştirilmiş olup; geliştirilen endüstriyel veri seti ile eğitilmiş ağ yapıları endüstriyel ayıklama makinelerinde yüksek doğrulukta çalışabilecek seviyededir.Pistachio is a product with high commercial value and Turkey has a serious production and export potential in this field. The harvesting and sorting of these products is as important process as their cultivation. Classification of pistachios according to their outer shell color after harvest is one of the important processes that must be done before presenting the pistachio to market. In this study, deep learning techniques were used to sort the pistachios according to their outer color. The data set required for the extract process was obtained using an industrial experimental setup. The AlexNet structure was trained and tested with these data sets. The network structure was trained and tested for two different percentages (70%, 15%, 15% and 60%, 20%, 20%) and three different data numbers to investigate the effect of training, validation and test data in different percentages and numbers on test accuracy. The highest test accuracy was calculated as 98.44% by using of 60%, 20%, 20% percentages and 580x2, 193x2 and 193x2 data for training, validation and testing, respectively. Classification process has been performed with deep learning techniques with high accuracy. Network structures trained with the developed industrial data set are at a level to obtain high accuracy in industrial sorting machines.

show abstract

“…The network is trained on a small sample set of 200-500 cases in 8 categories, and the classification accuracy reaches 97%. Kurtulmuş (2021) adopted AlexNet ( Krizhevsky, Sutskever & Hinton, 2012 ), GoogleNet, and ResNet to identify sunflower seed varieties, and then they were also evaluated in terms of both accuracy and training time, GoogleNet obtained the highest classification accuracy (95%).…”

Section: Related Workmentioning

confidence: 99%

“…In the last three years, mainly due to the advances of deep learning, more concretely convolutional neural networks (CNNs), the quality of image classification ( Krizhevsky, Sutskever & Hinton, 2012 ; Han et al, 2018 ), object detection ( Ren et al, 2015 ; Sun et al, 2019 ; Bochkovskiy, Wang & Liao, 2020 ) and semantic segmentation ( Chen et al, 2014 ) has been progressing at a dramatic pace. Recently, some researchers also adopted deep learning technology in crop identification tasks and achieved good performance ( Ni et al, 2019 ; Kurtulmus, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

SeedSortNet: a rapid and highly effificient lightweight CNN based on visual attention for seed sorting

Liu

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

Seed purity directly affects the quality of seed breeding and subsequent processing products. Seed sorting based on machine vision provides an effective solution to this problem. The deep learning technology, particularly convolutional neural networks (CNNs), have exhibited impressive performance in image recognition and classification, and have been proven applicable in seed sorting. However the huge computational complexity and massive storage requirements make it a great challenge to deploy them in real-time applications, especially on devices with limited resources. In this study, a rapid and highly efficient lightweight CNN based on visual attention, namely SeedSortNet, is proposed for seed sorting. First, a dual-branch lightweight feature extraction module Shield-block is elaborately designed by performing identity mapping, spatial transformation at higher dimensions and different receptive field modeling, and thus it can alleviate information loss and effectively characterize the multi-scale feature while utilizing fewer parameters and lower computational complexity. In the down-sampling layer, the traditional MaxPool is replaced as MaxBlurPool to improve the shift-invariant of the network. Also, an extremely lightweight sub-feature space attention module (SFSAM) is presented to selectively emphasize fine-grained features and suppress the interference of complex backgrounds. Experimental results show that SeedSortNet achieves the accuracy rates of 97.33% and 99.56% on the maize seed dataset and sunflower seed dataset, respectively, and outperforms the mainstream lightweight networks (MobileNetv2, ShuffleNetv2, etc.) at similar computational costs, with only 0.400M parameters (vs. 4.06M, 5.40M).

show abstract

Identification of sunflower seeds with deep convolutional neural networks

Cited by 33 publications

References 20 publications

A comparative analysis of the discrimination of pepper (Capsicum annuum L.) based on the cross‐section and seed textures determined using image processing

A comparative analysis of the discrimination of pepper (Capsicum annuum L.) based on the cross‐section and seed textures determined using image processing

Antep fıstığının derin öğrenme ile dış kabuk rengine göre sınıflandırılması

SeedSortNet: a rapid and highly effificient lightweight CNN based on visual attention for seed sorting

Contact Info

Product

Resources

About