Ripeness Classification of Bananas Using an Artificial Neural Network

Mazen, Fatma Mazen Ali; Nashat, Ahmed A.

doi:10.1007/s13369-018-03695-5

Cited by 131 publications

(66 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our second dataset, consisting of real images, is a collection drawn from three sources. First, images were taken from the dataset [38] originally used for ripeness classification networks. Second, the "Top Indian Fruits" dataset contains many images of bananas in various states of ripeness and health [39]; from this, we selected only the examples of healthy bananas and discarded the associated per-image ripeness and quality labels.…”

Section: Training Datasetmentioning

confidence: 99%

GANana: Unsupervised Domain Adaptation for Volumetric Regression of Fruit

et al. 2021

View full text Add to dashboard Cite

3D reconstruction of fruit is important as a key component of fruit grading and an important part of many size estimation pipelines. Like many computer vision challenges, the 3D reconstruction task suffers from a lack of readily available training data in most domains, with methods typically depending on large datasets of high-quality image-model pairs. In this paper, we propose an unsupervised domain-adaptation approach to 3D reconstruction where labelled images only exist in our source synthetic domain, and training is supplemented with different unlabelled datasets from the target real domain. We approach the problem of 3D reconstruction using volumetric regression and produce a training set of 25,000 pairs of images and volumes using hand-crafted 3D models of bananas rendered in a 3D modelling environment (Blender). Each image is then enhanced by a GAN to more closely match the domain of photographs of real images by introducing a volumetric consistency loss, improving performance of 3D reconstruction on real images. Our solution harnesses the cost benefits of synthetic data while still maintaining good performance on real world images. We focus this work on the task of 3D banana reconstruction from a single image, representing a common task in plant phenotyping, but this approach is general and may be adapted to any 3D reconstruction task including other plant species and organs.

show abstract

Section: Training Datasetmentioning

confidence: 99%

GANana: Unsupervised Domain Adaptation for Volumetric Regression of Fruit

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Melalui confusion matrix dapat dihitung nilai akurasi, sensitivitas, presisi, spesifisitas, dan nilai prediksi negatif yang menggambar kinerja jaringan saraf tiruan. Nilai akurasi, sensitivitas, presisi, spesifisitas, dan nilai prediksi negatif dihitung dengan Persamaan 2 -6 (Mazen & Nashat, 2019).…”

Section: Perancangan Jaringan Saraf Tiruanunclassified

Sistem Identifikasi Tingkat Kematangan Buah Nanas Secara Non-Destruktif Berbasis Computer Vision

Prasetyo

Surtono

Junaidi

et al. 2021

J. Energy Mater. Instrum. Technol.

View full text Add to dashboard Cite

A computer vision-based non-destructive pineapple maturity level identification system has been realized. This research was conducted to create a system capable of identifying six indexes of pineapple maturity level. An artificial neural network is used as a classifier for the level of maturity pineapples. Artificial neural network input is a statistical parameter consisting of mean, standard deviation, variance, kurtosis, and skewness of RGB and HSV color models pineapple images. Statistical parameters of the color model with a Pearson correlation value greater than 0.5 were used to characterize pineapple images. A total of 360 pineapple images were used in the training process with a percentage of 75% of training data and 25% of validation data. An image segmentation process is applied to separate the pineapple image from the image background. The result of this research is a pineapple maturity level identification system consisting of software and hardware which is able to identify six indexes of pineapple maturity level with average accuracy value of 98,4%.

show abstract

“…Metode Computer Vision (CV) yang mengandalkan perekaman citra TBS oleh kamera digital dan program pengolahan citra telah banyak digunakan karena lebih sederhana. Metode ini telah digunakan untuk mengestimasi tingkat kematangan TBS kelapa sawit antara lain mengunakan color computer vision [21], mengunakan metode fluorosensi [22], pengolahan data dan program klasifikasi mengunakan jaringan syaraf tiruan [23]. Pengunaan metode pencitraan hiperspektral untuk TBS kelapa sawit juga telah mulai dilakukan mengunakan spectrograph specim beserta mengevaluasi kadar minyak buah [24].…”

Section: Pendahuluanunclassified

Pencitraan Hiperspekral untuk Membedakan Asal Tanah Tumbuh Dari Tandan Buah Segar Kelapa Sawit

Veranita

Shiddiq

Candra

et al. 2020

mib

View full text Add to dashboard Cite

Hyperspectral imaging is a non destructive method that has been used to evaluate internal characteristics of fruits and vegetables. Plant genetics, soil characteristics, and plant management are some of key factors to define the quality of oil palm fresh fruit bunches (FFB) produced. This research was aimed to discriminate the Tenera oil palm FFBs produced by oil palm trees grown from mineral soil and peat soil using a hyperspectral imaging system which utilized a Specim V10 spektrograf. The discrimination was based on their ripeness level, mesocarp firmness, and classification using K-mean clustering. The samples consisted of 61 mineral soil FFBs and 60 peat soil FFBs with three ripeness levels as unripe, ripe, and overripe. Hyperspectral images were recorded and processed using Matlab programs. The spectral reflectance intensities showed the discrimination between both origin soils at wavelength ranges of 700 nm  900 nm. The results also showed higher reflectance intensities of peat soil FFBs than mineral soil FFBs. Correspondingly, Fruit firmness of peat soil FFBs are higher than mineral soil FFBs. Classification using K- mean clustering between reflectance intensities and fruit firmness showed significant clusters for three ripeness levels. These results will be useful for an oil palm FFB sorting machine based on spectral imaging method

show abstract

Ripeness Classification of Bananas Using an Artificial Neural Network

Cited by 131 publications

References 20 publications

GANana: Unsupervised Domain Adaptation for Volumetric Regression of Fruit

GANana: Unsupervised Domain Adaptation for Volumetric Regression of Fruit

Sistem Identifikasi Tingkat Kematangan Buah Nanas Secara Non-Destruktif Berbasis Computer Vision

Pencitraan Hiperspekral untuk Membedakan Asal Tanah Tumbuh Dari Tandan Buah Segar Kelapa Sawit

Contact Info

Product

Resources

About