Fruit Images Research Articles

Radial grid reflectance correction for hyperspectral images of fruits with rounded surfaces

Over the last two decades, the viability of hyperspectral imaging (HSI) technology as a tool for determining food quality has been established. This technology has been successfully combined with chemometric tools and image-processing techniques to enhance its effectiveness. Despite the advances in imaging technology, significant challenges related to non-uniformity caused by object geometry still need to be addressed. The inappropriate processing of non-uniform food products can significantly affect subsequent calculations, including accurate measurements and precise analysis. A popular method used to face up non-uniformity is the Lambertian surface correction, which assumes spherical surfaces of food products; however, it presents some issues with non-spherical shapes. This work proposes a generalized reflectance correction method for HSI of rounded fruits that are not necessarily spherical. The method is based on the correlation between the pixel’s position and its reflectance. For proof of concept, a case study was designed considering the HSI of mango fruits (Mangifera indica L) Kent variety. For comparison, each image was corrected using both the Lambertian surface correction and the proposed method. Results show a strong correlation between the standard deviation of the spectral profiles of images and the roundness of the fruit, which is more evident in the case of the proposed radial grid correction method. Hence, the proposed radial correction method produced a more uniform texture in corrected hyperspectral images.

Fruit ripeness identification using YOLOv8 model

Deep learning-based visual object detection is a fundamental aspect of computer vision. These models not only locate and classify multiple objects within an image, but they also identify bounding boxes. The focus of this paper's research work is to classify fruits as ripe or overripe using digital images. Our proposed model extracts visual features from fruit images and analyzes fruit peel characteristics to predict the fruit's class. We utilize our own datasets to train two "anchor-free" models: YOLOv8 and CenterNet, aiming to produce accurate predictions. The CenterNet network primarily incorporates ResNet-50 and employs the deconvolution module DeConv for feature map upsampling. The final three branches of convolutional neural networks are applied to predict the heatmap. The YOLOv8 model leverages CSP and C2f modules for lightweight processing. After analyzing and comparing the two models, we found that the C2f module of the YOLOv8 model significantly enhances classification results, achieving an impressive accuracy rate of 99.5%.

A Real-Time Olive Fruit Detection for Harvesting Robot Based on YOLO Algorithms

Abstract Deep neural network models have become powerful tools of machine learning and artificial intelligence. They can approximate functions and dynamics by learning from examples. This paper reviews the state-of-art of deep learning-based object detection frameworks that are used for fruit detection in general and for olive fruit in particular. A dataset of olive fruit on the tree is built to train and evaluate deep models. The ultimate goal of this work is the capability of on-edge real-time olive fruit detection on the tree from digital videos. Recent work in deep neural networks has led to the development of a state-of-the-art object detector termed You Only Look Once version five (YOLOv5). This paper builds a dataset of 1.2 K source images of olive fruit on the tree and evaluates the latest object detection algorithms focusing on variants of YOLOv5 and YOLOR. The results of the YOLOv5 models show that the YOLOv5 new network models are able to extract rich olive features from images and detect the olive fruit with a high precision of higher than 0.75 mAP_0.5. YOLOv5s performs better for real-time olive fruit detection on the tree over other YOLOv5 variants and YOLOR.

RANCANG BANGUN SISTEM DETEKSI KEMATANGAN BUAH KELAPA SAWIT BERDASARKAN DETEKSI WARNA MENGGUNAKAN ALGORITMA K-NN

RANCANG BANGUN SISTEM DETEKSI KEMATANGAN BUAH KELAPA SAWIT BERDASARKAN DETEKSI WARNA MENGGUNAKAN ALGORITMA K-NN

YOLOv7-Plum: Advancing Plum Fruit Detection in Natural Environments with Deep Learning.

The plum is a kind of delicious and common fruit with high edible value and nutritional value. The accurate and effective detection of plum fruit is the key to fruit number counting and pest and disease early warning. However, the actual plum orchard environment is complex, and the detection of plum fruits has many problems, such as leaf shading and fruit overlapping. The traditional method of manually estimating the number of fruits and the presence of pests and diseases used in the plum growing industry has disadvantages, such as low efficiency, a high cost, and low accuracy. To detect plum fruits quickly and accurately in a complex orchard environment, this paper proposes an efficient plum fruit detection model based on an improved You Only Look Once version 7(YOLOv7). First, different devices were used to capture high-resolution images of plum fruits growing under natural conditions in a plum orchard in Gulin County, Sichuan Province, and a dataset for plum fruit detection was formed after the manual screening, data enhancement, and annotation. Based on the dataset, this paper chose YOLOv7 as the base model, introduced the Convolutional Block Attention Module (CBAM) attention mechanism in YOLOv7, used Cross Stage Partial Spatial Pyramid Pooling-Fast (CSPSPPF) instead of Cross Stage Partial Spatial Pyramid Pooling(CSPSPP) in the network, and used bilinear interpolation to replace the nearest neighbor interpolation in the original network upsampling module to form the improved target detection algorithm YOLOv7-plum. The tested YOLOv7-plum model achieved an average precision (AP) value of 94.91%, which was a 2.03% improvement compared to the YOLOv7 model. In order to verify the effectiveness of the YOLOv7-plum algorithm, this paper evaluated the performance of the algorithm through ablation experiments, statistical analysis, etc. The experimental results showed that the method proposed in this study could better achieve plum fruit detection in complex backgrounds, which helped to promote the development of intelligent cultivation in the plum industry.

Identificación automática de enfermedades en frutos de aguacate con base en máquinas de aprendizaje y descriptores cromáticos

Timely identification of phytosanitary problems in agricultural crops is essential to reduce production losses. Artificial intelligence algorithms facilitate their rapid and reliable identification. In this research, three learning classifiers, namely random forest (RF), support vector machine (SVM) and multilayer perceptron (MLP), were evaluated to identify three target classes (healthy fruit, anthracnose [Colletotrichum spp.] and scab [Sphaceloma perseae]) from digital fruit images. Two color descriptor extraction techniques (region selection and image subsampling) were compared with the RF classifier, and an overall classification accuracy (ACC) of 98±0.03 % with region selection and 84±0.08 % with subsampling was obtained. Subsequently, the classifiers were evaluated with color descriptors extracted with region selection. RF and MLP were superior to SVM, with an ACC of 98±0.03 %. Scab and anthracnose were identified with an F1 score of 98 %. %. The high performance of the classifiers shows the potential for applying artificial intelligence paradigms to identify phytosanitary problems in agricultural crops.

Comparison of Residual Network-50 and Convolutional Neural Network Conventional Architecture For Fruit Image Classification

Classification of fruit images using machine learning technology has had a significant impact on human life by enabling accurate recognition of various fruits. With the advancements in technology, machine learning architectures have become increasingly diverse and sophisticated, providing enhanced capabilities for fruit image classification. However, previous studies have primarily focused on classifying fruits at a basic level. Therefore, there is a growing need for the development and application of Fruit Image Classification systems within the community, particularly in the field of agriculture. Such applications can play a pivotal role in leveraging technology to benefit the agricultural sector, empowering users to gain satisfaction and knowledge regarding different fruits through the utilization of these applications. In this study, we employ both a conventional Convolutional Neural Network (CNN) architecture and a Residual Network-50 for fruit image classification. To ensure robust performance evaluation, the dataset is divided into training and testing subsets, with fruits categorized into specific classes. Furthermore, identical preprocessing and optimization techniques are applied to both architectures to maintain consistency and fairness during the evaluation process. The results of our classification experiments on a dataset consisting of 17 different fruit classes reveal that the conventional CNN architecture achieves an impressive accuracy of 0.998 (99%) with a minimal loss of 0.009. On the other hand, the Residual Network-50 demonstrates a slightly lower accuracy of 0.994 (99%) but with a slightly higher loss of 0.02. Despite the higher loss, the Residual Network-50's accuracy remains comparable to that of the conventional architecture, showcasing its potential for fruit image classification. By leveraging the power of machine learning and these advanced architectures, fruit image classification systems can provide valuable insights and assistance to users. They can facilitate informed decision-making in various domains, including agriculture, food production, and consumer education.

Study of light penetration depth of a Vis-NIR hyperspectral imaging system for the assessment of fruit quality. A case study in persimmon fruit

Hyperspectral imaging (HSI) is one of the most studied optical techniques to estimate the internal quality of fruits and vegetables. Absorbance and reflectance of the light radiation are specific to each biological tissue and are directly related to its chemical composition and physical characteristics. These properties are influenced by other extrinsic factors, such as the instrumentation or the light source, which can reduce the reproducibility of the experiments. Determining the actual depth of light penetration into tissue could help validate non-contact methods as accurate tools to assess quality properties based on optical properties. In the case of HSI systems, it is crucial to know how far the light penetrates at each wavelength. A non-destructive approach, based on the spatially resolved spectroscopic principle, was proposed to estimate the light penetration depth of a HSI system in a Vis-NIR configuration (in the range 450–1050 nm). This method was applied to measure the light penetration depth in persimmon fruit. The absorption (μa) and scattering (μ's) coefficients from Farrell's diffusion theory were estimated using the backscattered light measured at different distances from the incident point light at each wavelength in hyperspectral images of persimmon fruit. The actual light penetration depth was obtained by measuring the reflectance of cut pieces of persimmon fruit with different thicknesses. Linear regression was used to relate the depth of penetrability obtained by both protocols, the estimated or non-destructive protocol and the actual or destructive protocol, showing a high relationship (R2 > 0.8 and RPD>2.5) in the range 610–1050 nm. This confirms that this non-destructive approach proposed for estimating the light penetration depth of a Vis-NIR HSI system in persimmon fruit is accurate, so it could be used as a valuable method to evaluate other HSI systems for different fruits.

Tomato Maturity Detection and Counting Model Based on MHSA-YOLOv8.

The online automated maturity grading and counting of tomato fruits has a certain promoting effect on digital supervision of fruit growth status and unmanned precision operations during the planting process. The traditional grading and counting of tomato fruit maturity is mostly done manually, which is time-consuming and laborious work, and its precision depends on the accuracy of human eye observation. The combination of artificial intelligence and machine vision has to some extent solved this problem. In this work, firstly, a digital camera is used to obtain tomato fruit image datasets, taking into account factors such as occlusion and external light interference. Secondly, based on the tomato maturity grading task requirements, the MHSA attention mechanism is adopted to improve YOLOv8's backbone to enhance the network's ability to extract diverse features. The Precision, Recall, F1-score, and mAP50 of the tomato fruit maturity grading model constructed based on MHSA-YOLOv8 were 0.806, 0.807, 0.806, and 0.864, respectively, which improved the performance of the model with a slight increase in model size. Finally, thanks to the excellent performance of MHSA-YOLOv8, the Precision, Recall, F1-score, and mAP50 of the constructed counting models were 0.990, 0.960, 0.975, and 0.916, respectively. The tomato maturity grading and counting model constructed in this study is not only suitable for online detection but also for offline detection, which greatly helps to improve the harvesting and grading efficiency of tomato growers. The main innovations of this study are summarized as follows: (1) a tomato maturity grading and counting dataset collected from actual production scenarios was constructed; (2) considering the complexity of the environment, this study proposes a new object detection method, MHSA-YOLOv8, and constructs tomato maturity grading models and counting models, respectively; (3) the models constructed in this study are not only suitable for online grading and counting but also for offline grading and counting.

Hyperspectral fruit image restoration using non-convex optimization

Hyperspectral (HS) imaging captured at low proximity ranges has become an effective method for assessing the quality and safety of food products in recent years. The majority of Hyperspectral cameras are push-broom type, which often contributes random noise and stripes to the spectral images. As a result, the quality of the collected HS images and the precision of the subsequent processing will both suffer. Despite the fact that there are several denoising techniques that have been studied and recorded in the literature, they frequently fail to fully restore the original HS images when there are strong stripe noises and other intricate mixed noises. In this study, we introduce a new method based on tensor logarithmic Schatten-p norm minimization with anisotropic spatial spectral total variation (ASSTV) regularization for simultaneous denoising and destriping of line scan-based hyperspectral images. Tensor logarithmic Schatten-p norm improves denoising performance by deleting the smaller singular values while protecting the larger singular values. Through the application of ASSTV, stripes and Gaussian noise are eliminated while maintaining the spatial–spectral smoothness of HS images and the directional characteristics of the stripes. The augmented Lagrange multiplier (ALM) approach is used to address the ensuing optimization problem. The quantitative and visual assessments reveal that the suggested technique has improved performance than its counterparts.

Implementing deep‐learning techniques for accurate fruit disease identification

AbstractTo overcome the problems of manual identification of fruit disease, this work proposes a deep‐learning model to analyse fruit images to detect diseases in the fruit. We are proposing here a convolutional neural network (CNN)‐based model for fruit disease classification. By including many layers, the proposed CNN model extracts numerous features from the fruit, deals with the large data set and finally evaluates it. With the MobileNetv2 model, the disease prediction accuracy for papaya, guava and citrus was 99.4%, 98.8% and 95.8% and the recall values were 99.4%, 98.8% and 93.8%, respectively. With VGG16, the disease prediction accuracy for papaya, guava and citrus was 97.7%, 99.6% and 94.2% and the recall values were 96.5%, 99.6% and 89.2%, respectively. Finally, with DenseNet121, the disease prediction accuracy for papaya, guava and citrus was 99.4%, 97.6% and 99.2%, and the recall values were 98.8%, 97.6% and 99.2%, respectively.

A study on phenotypic micro-variation of stored melon based on weight loss rate

This study proposes a novel deep learning algorithm that uses weight loss rate as a basis for classification and incorporates phenotypic micro-variation features for the dynamic prediction and analysis of melon storage processes. The Resnet50 backbone network was used as a basis to construct deformable residual blocks for nonrigid objects with high similarity over time, allowing the convolutional kernel shape to adapt to the melon surface shape. A hybrid spatial and channel attention mechanism was used to focus more attentional resources on the target regions requiring precise attention. The experimental results indicate that the proposed method outperforms traditional computer vision and machine learning methods in terms of effectiveness, performance, and generalization ability. We evaluate our method on a large dataset of melon fruit images and show that it outperforms existing methods in accurately predicting storage status and optimizing control strategies in time. The proposed method will serve as a powerful tool for other nondestructive detection and accurate prediction of the shelf life of large fruit.

Date Fruit Classification Based on Surface Quality Using Convolutional Neural Network Models

Classifying the quality of dates after harvesting the crop plays a significant role in reducing waste from date fruit production. About one million tons of date fruit is produced annually in Saudi Arabia. Part of this production goes to local factories to be produced and packaged to be ready for use. Classifying and sorting edible dates from inedible dates is one of the first and most important stages in the production process in the date fruit industry. As this process is still performed manually in date production factories in Saudi Arabia, this may cause an increase in the waste of date fruit and reduce the efficiency of production. Therefore, in our paper, we propose a system to automate the classification of dates fruit production. The proposed system focuses on classifying the quality of date fruit at the postharvesting stage. By automating the process of classifying date fruit at this stage, we can increase the production efficiency, raise the classification accuracy, control the product quality, and perform data analysis within the industry. As a result, this increases the market competitiveness, reduces production costs, and increases the productivity. The system was developed based on convolutional neural network models. For the purpose of training the models, we constructed a new image dataset that contains two main classes that have images of date fruit with excellent surface quality and another class for date fruit with poor surface quality. The results show that the used model can classify date fruit based on their surface quality with an accuracy of 97%.

Does this fruit look appetizing? Psychometric modeling of fruit consumption preferences

Consumers’ sensory evaluation of fruits to determine the expected quality is a frequent practice. However, consumers’ assessment of fruit quality is an ambiguous concept. This research aimed to determine the preferred fruit image when consumers decide that it is ready to eat, or it is too old. This within-subjects experimental design was conducted through an online survey using four fruits: avocado, banana, lulo, and guava. The questionnaire used a two-alternative forced-choice method: From a pair of fruit images, participants chose which one they preferred to eat, and which was too old. The results showed that participants do not always agree on the fruit image they find to be ready to eat, whereas the results for assessing an old fruit mimic the fruit maturity condition. Thus, food quality standards should use sensory evaluations that assess ideas that matter to the consumer. The value of this research is to provide a methodological approach to evaluate the consumers’ expectations, which will be helpful within agricultural processes and the distribution chain.

FruitQ: a new dataset of multiple fruit images for freshness evaluation

FruitQ: a new dataset of multiple fruit images for freshness evaluation

Perancangan Awal Sistem Automatic Self-Checkout Untuk Produk Buah Berbasis CNN dan Sensor Berat Loadcell


 
 
 The check-out system is one of the most important systems when we make purchases at a shopping center, shops, supermarkets, or mini markets. Determining different types of fruit is one of the problems faced in making payments, especially in supermarkets, because cashiers must determine the category labeling and weight of a particular fruit to determine the price. In this research, a design is proposed which utilizes Deep Learning in the field of image processing using the Convolutional Neural Network (CNN) algorithm utilizing RaspberryPi3. In making a classification system that uses deep learning, there are several main process stages, such as dataset collection, system design, training, and testing to see the results of the designed CNN model. The processed dataset in this research is a fruit image dataset derived from the Fruits-360. The results of the learning process obtained CNN models with 100% accuracy and loss of ≤ 0.026. The results of the CNN model that has been carried out will be combined with the load cell sensor which is expected to be used as an automatic self-checkout, especially for fruits. On the other hand, the calibration process of the loadcell weight measurement sensor is conducted which resulting an error measurement rate of 0.2 grams.
 
 

Automatic Fruit Quality Inspection System Using Image Processing

The demand for high-quality fruits has increased significantly, driven by consumers' growing emphasis on health and nutrition. To ensure consistent quality control and efficient fruit grading processes, an automatic fruit quality inspection system using image processing techniques has been developed. This system leverages Convolutional Neural Network (CNN) algorithms to achieve an impressive accuracy rate of 99% in fruit quality assessment. The proposed system involves a multi-step process starting with the acquisition of high-resolution fruit images. These images undergo pre-processing to enhance clarity and eliminate noise or artifacts. Subsequently, the pre-processed images are fed into a trained CNN model for feature extraction and classification based on learned patterns. The CNN model has been trained on a large dataset of labeled fruit images, enabling it to recognize quality attributes such as colour, size, shape, and defects. The system's evaluation involved a diverse range of fruits, encompassing various species, varieties, and maturity stages. The output demonstrate the system's exceptional accuracy, with a 99% success rate in correctly identifying and grading fruit quality attributes. This automatic fruit quality inspection system offers several advantages, including real-time processing, high efficiency, and reduced labor costs, making it suitable for integration into fruit processing facilities and supply chains. [1]

Fruit Detection and Recognition Based on Deep Learning for Automatic Harvesting: An Overview and Review

Continuing progress in machine learning (ML) has led to significant advancements in agricultural tasks. Due to its strong ability to extract high-dimensional features from fruit images, deep learning (DL) is widely used in fruit detection and automatic harvesting. Convolutional neural networks (CNN) in particular have demonstrated the ability to attain accuracy and speed levels comparable to those of humans in some fruit detection and automatic harvesting fields. This paper presents a comprehensive overview and review of fruit detection and recognition based on DL for automatic harvesting from 2018 up to now. We focus on the current challenges affecting fruit detection performance for automatic harvesting: the scarcity of high-quality fruit datasets, fruit detection of small targets, fruit detection in occluded and dense scenarios, fruit detection of multiple scales and multiple species, and lightweight fruit detection models. In response to these challenges, we propose feasible solutions and prospective future development trends. Future research should prioritize addressing these current challenges and improving the accuracy, speed, robustness, and generalization of fruit vision detection systems, while reducing the overall complexity and cost. This paper hopes to provide a reference for follow-up research in the field of fruit detection and recognition based on DL for automatic harvesting.

Apple ripeness identification from digital images using transformers

We describe a non-destructive test of apple ripeness using digital images of multiple types of apples. In this paper, fruit images are treated as data samples, artificial intelligence models are employed to implement the classification of fruits and the identification of maturity levels. In order to obtain the ripeness classifications of fruits, we make use of deep learning models to conduct our experiments; we evaluate the test results of our proposed models. In order to ensure the accuracy of our experimental results, we created our own dataset, and obtained the best accuracy of fruit classification by comparing Transformer model and YOLO model in deep learning, thereby attaining the best accuracy of fruit maturity recognition. At the same time, we also combined YOLO model with attention module and gave the fast object detection by using the improved YOLO model.

Rapid detection of Yunnan Xiaomila based on lightweight YOLOv7 algorithm.

Real-time fruit detection is a prerequisite for using the Xiaomila pepper harvesting robot in the harvesting process. To reduce the computational cost of the model and improve its accuracy in detecting dense distributions and occluded Xiaomila objects, this paper adopts YOLOv7-tiny as the transfer learning model for the field detection of Xiaomila, collects images of immature and mature Xiaomila fruits under different lighting conditions, and proposes an effective model called YOLOv7-PD. Firstly, the main feature extraction network is fused with deformable convolution by replacing the traditional convolution module in the YOLOv7-tiny main network and the ELAN module with deformable convolution, which reduces network parameters while improving the detection accuracy of multi-scale Xiaomila targets. Secondly, the SE (Squeeze-and-Excitation) attention mechanism is introduced into the reconstructed main feature extraction network to improve its ability to extract key features of Xiaomila in complex environments, realizing multi-scale Xiaomila fruit detection. The effectiveness of the proposed method is verified through ablation experiments under different lighting conditions and model comparison experiments. The experimental results indicate that YOLOv7-PD achieves higher detection performance than other single-stage detection models. Through these improvements, YOLOv7-PD achieves a mAP (mean Average Precision) of 90.3%, which is 2.2%, 3.6%, and 5.5% higher than that of the original YOLOv7-tiny, YOLOv5s, and Mobilenetv3 models, respectively, the model size is reduced from 12.7 MB to 12.1 MB, and the model's unit time computation is reduced from 13.1 GFlops to 10.3 GFlops. The results shows that compared to existing models, this model is more effective in detecting Xiaomila fruits in images, and the computational complexity of the model is smaller.