A Novel Classification Model of Date Fruit Dataset Using Deep Transfer Learning

Abstract

Date fruits are the most common fruit in the Middle East and North Africa. There are a wide variety of dates with different types, colors, shapes, tastes, and nutritional values. Classifying, identifying, and recognizing dates would play a crucial role in the agriculture, commercial, food, and health sectors. Nevertheless, there is no or limited work to collect a reliable dataset for many classes. In this paper, we collected the dataset of date fruits by picturing dates from primary environments: farms and shops (e.g., online or local markets). The combined dataset is unique due to the multiplicity of items. To our knowledge, no dataset contains the same number of classes from natural environments. The collected dataset has 27 classes with 3228 images. The experimental results presented are based on five stages. The first stage applied traditional machine learning algorithms for measuring the accuracy of features based on pixel intensity and color distribution. The second stage applied a deep transfer learning (TL) model to select the best model accuracy of date classification. In the third stage, the feature extraction part of the model was fine-tuned by applying different retrained points to select the best retraining point. In the fourth stage, the fully connected layer of the model was fine-tuned to achieve the best classification configurations of the model. In the fifth stage, regularization was applied to the classification layer of the best-selected model from the fourth stage, where the validation accuracy reached 97.21% and the best test accuracy was 95.21%.

Classification of Dates Quality Using Deep Learning Technology Based on Captured Images

“…The dataset was trained with three different pre-trained models by using transfer learning as shown in Figure . 6. As our data is small transfer learning is better for getting high performance than the full-scale scratched models (Alsirhani et al, 2023). The selected pre-trained models were Inception-v3, Inception-ResNet-v2, and VGG 19, they were chosen according to their high accuracy in classification (Alzubaidi et al, 2021).…”

Categorization of Dehydrated Food through Hybrid Deep Transfer Learning Techniques

“…Researchers in [38] proposed a model called "ConvNet" that can detect several faces with different emotions collaborating with CNN; this model succeeds in achieving an accuracy of 98.13%. Exploring recent advancements in date fruit classification [39], emphasizing a novel dataset collected from primary environments. With 27 classes and 3228 images, the study employs a five-stage experimental approach, incorporating traditional machine learning, deep transfer learning, fine-tuning, and regularization.…”

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

“…In recent years, deep learning has shown remarkable success in image classification tasks in plant species identification and other domains ( Kussul et al., 2017 ; He et al., 2018 ; Kamilaris and Prenafeta-Boldú, 2018 ; Li et al., 2018 ; Zhang et al., 2021 ; Bouguettaya et al., 2022 ). As a result, deep learning methods have emerged as a promising alternative for date palm variety identification ( Haidar et al., 2012 ; Altaheri et al., 2019 ; Nasiri et al., 2019 ; Albarrak et al., 2022 ; Jintasuttisak et al., 2022 ; Alsirhani et al., 2023 ; Noutfia and Ropelewska, 2023a ; Noutfia and Ropelewska, 2023b ). Deep learning is a branch of machine learning that uses artificial neural networks with multiple layers to learn complex features from large amounts of data ( LeCun et al., 2015 ; Goodfellow et al., 2016 ).…”

“…Deep learning methods have several advantages over traditional and molecular methods: they are fast and easy to use; they do not require expert knowledge or manual intervention; and they can work with any parts of the date palm plant (such as leaves, stems, or fruits). Recent deep learning methods have been proposed to identify date palm species based on their fruits ( Haidar et al., 2012 ; Altaheri et al., 2019 ; Nasiri et al., 2019 ; Albarrak et al., 2022 ; Jintasuttisak et al., 2022 ; Alsirhani et al., 2023 ; Noutfia and Ropelewska, 2023a ; Noutfia and Ropelewska, 2023b ). The main drawback of these methods is that they are designed for harvesting purposes when fruits are present; however, they cannot be used to identify date palm species when the fruits are not present or visible.…”