Employment of Pre-trained Deep Learning Models for Date Classification: A Comparative Study

Al-Sabaawi, Aiman; Hasan, Reem Ibrahim; Fadhel, Mohammed A.; Al-Shamma, Omran; Alzubaidi, Laith

doi:10.1007/978-3-030-71187-0_17

Cited by 4 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, methods based on deep learning have shown better performance than the formerly cited ones. The proposed method outperforms the methods in [25], [17] and [16] by 9.62%, 9.93% and 10.24%, respectively. These results confirms once again the effectiveness of the proposed method.…”

Section: ) Comparison With State Of the Artmentioning

confidence: 96%

“…As instance, in [16], pre-trained CNN models, including MobileNet and InceptionNet, were considered to classify six date varieties namely Ajwa, Boroy, Medjool, Moriam, Sokire and Sugaey. Similarly, an experimental comparative study was conducted to compare pre-trained CNN models for the classification of five types of date, where ResNet-50 has outperformed the remaining networks [17]. Similarly, in [8], a customized CNN is proposed to classify nine date varieties including Ajwa, Galaxy, Medjool, Meneifi, Nabat Ali, Rutab, Shaishe, Sokari and Sugaey .…”

Section: Related Workmentioning

confidence: 99%

“…These methods adopt hand-designed features along with conventional classifiers for date fruit classification. We also consider comparing our method with deep learning-based methods in [25] (VGG-16), [16] (MobileNet) and [17] (ResNet-50). For a fair comparison, we consider a fine tuning process of these deep networks.…”

Section: ) Comparison With State Of the Artmentioning

confidence: 99%

“…These results confirms once again the effectiveness of the proposed method. Fine-tuned VGG-16 88.58% [17] Fine-tuned ResNet-50 88.27% [16] Fine-tuned MobileNet 87.96% Our method VGG-F + PCANet + DCA VGG-F + PCANet + CCA 98.20% 99.32%…”

Section: ) Comparison With State Of the Artmentioning

confidence: 99%

See 3 more Smart Citations

Date Fruit Sorting Based on Deep Learning and Discriminant Correlation Analysis

et al. 2022

View full text Add to dashboard Cite

Date fruit is among the major crops in the middle-east region, where millions of tons are harvested every year. Date is a healthy fruit, which involves sugars, minerals and vitamins. In addition, it helps preventing human body from several diseases such as cancer and heart diseases. Date sorting is a fundamental step in the date industry. However, manually conducting such an operation, by human labors, is expensive and time-consuming. In this paper, we propose a method for classifying the type of date fruit by incorporating supervised and unsupervised deep networks. Specifically, we use discriminant correlation analysis (DCA) algorithm to fuse features learned from convolution neural networks (VGG-F) and an unsupervised network called PCANet. DCA jointly performs feature fusion and dimensionality reduction with a low computational complexity. To carry out experiments, we introduce a new benchmark dataset of date fruit images from 20 date varieties. Our benchmark is, to the best of our knowledge, the largest one in terms of number of varieties. Note that the dataset is publicly available at https://unsat.000webhostapp.com/dataset . Experimental results demonstrate the utility of DCA as well as the complementarity of the fused features. It has also been shown the effectiveness of the proposed method compared to several relevant methods.

show abstract

Section: ) Comparison With State Of the Artmentioning

confidence: 96%

Section: Related Workmentioning

confidence: 99%

Section: ) Comparison With State Of the Artmentioning

confidence: 99%

Section: ) Comparison With State Of the Artmentioning

confidence: 99%

See 2 more Smart Citations

Date Fruit Sorting Based on Deep Learning and Discriminant Correlation Analysis

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The DTES achieves a maximum performance of 99.175% accuracy; the DMES achieves a maximum performance of 99.058% accuracy; and the DWES achieves a maximum performance of 84.27%. Al-Sabaawi et al. (2021) proposed a machine vision framework for date classification in an orchard environment using pre-trained deep learning models, with ResNet-50 achieving the highest F1-score (98.14%) and accuracy (97.37%).…”

Section: Literature Reviewmentioning

confidence: 99%

DPXception: a lightweight CNN for image-based date palm species classification

Safran,

Alrajhi,

Alfarhood

2024

Front. Plant Sci.

View full text Add to dashboard Cite

IntroductionDate palm species classification is important for various agricultural and economic purposes, but it is challenging to perform based on images of date palms alone. Existing methods rely on fruit characteristics, which may not be always visible or present. In this study, we introduce a new dataset and a new model for image-based date palm species classification.MethodsOur dataset consists of 2358 images of four common and valuable date palm species (Barhi, Sukkari, Ikhlas, and Saqi), which we collected ourselves. We also applied data augmentation techniques to increase the size and diversity of our dataset. Our model, called DPXception (Date Palm Xception), is a lightweight and efficient CNN architecture that we trained and fine-tuned on our dataset. Unlike the original Xception model, our DPXception model utilizes only the first 100 layers of the Xception model for feature extraction (Adapted Xception), making it more lightweight and efficient. We also applied normalization prior to adapted Xception and reduced the model dimensionality by adding an extra global average pooling layer after feature extraction by adapted Xception.Results and discussionWe compared the performance of our model with seven well-known models: Xception, ResNet50, ResNet50V2, InceptionV3, DenseNet201, EfficientNetB4, and EfficientNetV2-S. Our model achieved the highest accuracy (92.9%) and F1-score (93%) among the models, as well as the lowest inference time (0.0513 seconds). We also developed an Android smartphone application that uses our model to classify date palm species from images captured by the smartphone’s camera in real time. To the best of our knowledge, this is the first work to provide a public dataset of date palm images and to demonstrate a robust and practical image-based date palm species classification method. This work will open new research directions for more advanced date palm analysis tasks such as gender classification and age estimation.

show abstract

Innovative Date Fruit Classifier Based on Scatter Wavelet and Stacking Ensemble

Al-Kharaz,

Alwahhab,

Sabeeh

2024

HighTech. Innov. J.

View full text Add to dashboard Cite

Dates are essential fruits loaded with vital nutrients that keep bones healthy and prevent bone-related disorders. Approximately 8.46 million tons of different types of dates are cultivated and produced annually around the globe. There are more than 400 types of dates that are time-consuming and expensive to produce. Classifying them using conventional methods is labor-intensive, and this is one of the biggest problems for the date industry. Dataset fruit classification plays a vital role in the food industry. Dates can be classified from a luxury class to a less quality class. Accordingly, the food industry needs an automotive date fruit classifier that can work in food factories. This study proposes a pioneering method to classify date fruit that relies on extracting features from the texture of dates using Scattering Wavelet Transformation (SWT). The SWT yields in numeric coefficients were found to be immune to the deformation of invariants. This feature set trains an ensemble classifier that combines a voting mechanism to eliminate overfitting. The ensemble classifier consists of a random forest, a support vector machine classifier, and a logistic regression hyper-learner. Our novel approach was tested on two benchmarked datasets. The first data set scored F1 between 0.95 and 1.0 at the same time. The second dataset registered F1 between 0.96 and 1.0 in each of the 20 date classes. Some dates are close to each other in texture, resulting in high false positives or recall, causing a lower F1 score accuracy degree. The novelty of this approach comes from the featured representative of each date class, relying on the texture of the fruit as a discriminative feature, not on the fruit shape or color, which may not be robust enough as distinguishable features, especially in date classes that are close to each other in shape. Doi: 10.28991/HIJ-2024-05-02-010 Full Text: PDF

show abstract

Employment of Pre-trained Deep Learning Models for Date Classification: A Comparative Study

Cited by 4 publications

References 18 publications

Date Fruit Sorting Based on Deep Learning and Discriminant Correlation Analysis

Date Fruit Sorting Based on Deep Learning and Discriminant Correlation Analysis

DPXception: a lightweight CNN for image-based date palm species classification

Innovative Date Fruit Classifier Based on Scatter Wavelet and Stacking Ensemble

Contact Info

Product

Resources

About