Dataset Card for Fruit-Ripeness-Classification dataset

This is a collection of ripe and unripe fruits (mangoes and bananas) in outside lighting and outside conditions.

Train - 80% (4k images) Test - 20% (1k images)

Dimensions of image : 640 x 480 The dataset has been collected from Mendeley data: https://data.mendeley.com/datasets/y3649cmgg6/3 (Mango and Banana Dataset (Ripe Unripe) : Indian RGB image datasets for YOLO object detection) Initially the data was for training YOLO… See the full description on the dataset page: https://huggingface.co/datasets/darthraider/fruit-ripeness-detection-dataset.

Description:

Welcome to the Fruit Ripeness Classification Dataset! This comprehensive dataset is designed for researchers, data scientists, and machine learning enthusiasts interested in fruit classification based on ripeness stages.

Dataset Overview:

This dataset contains a collection of images featuring five different types of fruits, categorized into three distinct ripeness stages: Unripe, Ripe, and Overripe. The fruits included in this dataset are:

1. Apple
2. Banana
3. Mango
4. Orange
5. Tomato

Key Features:

Image Categories: Each fruit is represented in three ripeness categories. Image Size: All images are uniformly sized at 300x300 pixels, ensuring consistency for model training and evaluation. Diversity: The dataset includes a variety of images for each fruit and ripeness stage, capturing different angles, lighting conditions, and backgrounds to enhance model robustness. Applications: This dataset is ideal for training and testing machine learning models for image classification, computer vision tasks, and agricultural technology applications. Usage:

Researchers can utilize this dataset to develop algorithms for automated fruit ripeness detection, which can be beneficial in agricultural practices, supply chain management, and consumer applications.

Data Format:

The dataset is organized in a structured format, with images stored in folders corresponding to each fruit and ripeness category. Each image is labeled appropriately for easy identification and access.

Fruit Ripening 2

## Overview

Fruit Ripening 2 is a dataset for object detection tasks - it contains Fruits 4yN0 annotations for 6,554 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

This dataset is a customized version of the Fruit Quality Classification dataset originally created by Ryan D. Park (https://www.kaggle.com/datasets/ryandpark/fruit-quality-classification), which provides detailed images of different fruits categorized by quality and type. I have adapted and expanded upon this dataset to create a unique collection focused specifically on detection across various fruit types.

Dataset Overview: - Total Images: 1,968 images - Training Set: 1,852 images - Validation Set: 116 images

Fruit Types:Apple, Banana, Guava, Lime, Orange, Pomegranate Quality Categories: This dataset categorizes fruits into different ripeness stages, capturing a wide range of ripening conditions: - Bad Quality - Good Quality

Use Case: This dataset can be particularly useful for: - Fruit Quality Classification: Aiming to distinguish between quality in fruits, which has applications in agricultural technology, quality control, and the food industry. - AI and Computer Vision Projects: Perfect for training deep learning models to detect ripeness levels from fruit images. - Agricultural Research: Facilitates research into automating the identification of fruit quality and ripeness, a key factor in food logistics and waste reduction.

Dataset Details: Image Dimensions: Images are primarily of size 256x256 pixels, sourced from diverse real-world environments, captured under varying lighting conditions and backgrounds (e.g., top views, front views, rotated orientations). Annotations: Each image is labeled with bounding box coordinates for detecting fruits, facilitating object detection tasks as well as classification of ripeness levels.

Credits: This dataset was developed using images from the publicly available Fruit Quality Classification dataset by Ryan D. Park (https://www.kaggle.com/datasets/ryandpark/fruit-quality-classification). All original credits go to the creator, and I extend my thanks for sharing this dataset. The original dataset contains a much larger collection of images across different fruit types and quality levels, which served as the basis for this specialized ripeness-focused version.

Fruit Ripening Process Dataset and Model

This dataset contains images of the classes below:

• freshripe
• freshunripe
• overripe
• ripe
• rotten
• unripe

Usage

This is an object detection model that can be used to possibly identify where in the Fruit Ripening Process fruit at stores are and when to take them off the shelves and put them in composting.

Coffee Fruit Maturity ☕🍒

A dataset of coffee (C. Arabica ) cherries at various levels of fruit maturity. Version 1.0 of this dataset is skewed towards green cherries and includes only images of cherries still on the plant, with natural background.

Labels

Number of cherries segmented (whole, partial and background)

Training Split

| Split | | Image count | | --- | --- | -- | |training| 70% | 600| |validation| 20% | 174| |testing| 10% | 85| |**Total images**| |859|

Una base de datos de frutos del cafeto (C. Arabica ) en diferentes niveles de maduración.

Learn more about the Fruit Ripening System Market Report by Market Research Intellect, which stood at USD 1.2 billion in 2024 and is forecast to expand to USD 2.5 billion by 2033, growing at a CAGR of 9.5%.Discover how new strategies, rising investments, and top players are shaping the future.

Fruit Ripening Systems Market Outlook

According to our latest research, the global Fruit Ripening Systems market size reached USD 2.13 billion in 2024. The market is currently experiencing robust expansion, driven by advancements in post-harvest technology and increasing demand for fruits with consistent quality and extended shelf life. With a projected CAGR of 6.8% from 2025 to 2033, the market is expected to reach USD 3.91 billion by 2033. This growth is primarily fueled by the rising consumption of tropical fruits, heightened awareness regarding food safety, and the need for efficient supply chain management in the fresh produce sector.

One of the key growth factors propelling the Fruit Ripening Systems market is the increasing global demand for fruits such as bananas, mangoes, avocados, and tomatoes. As consumer preferences shift towards healthier diets and fresh produce, the need for advanced ripening solutions has intensified. Modern fruit ripening systems ensure uniform ripening, reduce spoilage, and enhance the visual and nutritional appeal of fruits. These systems, including ethylene generators and ripening chambers, are being widely adopted by producers and distributors to meet strict quality standards and regulatory requirements. Furthermore, the integration of IoT and automation technologies into ripening systems is enabling real-time monitoring and control, thus optimizing the ripening process and minimizing losses.

Another significant driver for the Fruit Ripening Systems market is the globalization of the fruit trade and the expansion of organized retail. As supply chains become more complex and fruits are transported over longer distances, maintaining optimal ripening conditions becomes crucial. Ripening systems that can be precisely controlled and monitored help ensure that fruits arrive at their destination in peak condition, ready for sale. Additionally, the increasing presence of supermarkets, hypermarkets, and e-commerce platforms is creating new opportunities for the deployment of advanced ripening technologies, particularly in emerging economies where the demand for high-quality produce is rapidly growing.

Sustainability and food safety concerns are also shaping the trajectory of the Fruit Ripening Systems market. Consumers and regulatory bodies are placing greater emphasis on reducing the use of harmful chemicals and minimizing food waste. As a result, there is a growing preference for ethylene-based ripening methods, which are considered safer and more environmentally friendly compared to traditional practices involving calcium carbide or other hazardous substances. The adoption of eco-friendly ripening systems not only supports compliance with international food safety standards but also enhances brand reputation and consumer trust, further driving market growth.

In recent years, the introduction of the Fruit Ripeness Scanner has revolutionized the way producers and distributors assess the quality and readiness of fruits for the market. This innovative technology allows for the non-invasive and precise measurement of fruit ripeness, ensuring that only the best quality produce reaches consumers. By using advanced sensors and algorithms, the Fruit Ripeness Scanner can accurately determine the optimal harvest time, reducing waste and enhancing supply chain efficiency. As demand for high-quality, ripe fruits continues to grow, the adoption of such technologies is becoming increasingly important in maintaining competitive advantage in the fruit industry.

From a regional perspective, Asia Pacific remains the largest and fastest-growing market for Fruit Ripening Systems, accounting for a significant share of global revenue. This dominance is attributed to the regionÂ’s vast fruit production base, rapid urbanization, and increasing investments in cold chain infrastructure. North America and Europe are also witnessing steady growth, driven by technological advancements and stringent food safety regulations. Meanwhile, Latin America and the Middle East & Africa are emerging as lucrative markets, supported by expanding agricultural activities and rising export-oriented fruit production.

The size of the Fruit Ripening System market was valued at USD XXX million in 2024 and is projected to reach USD XXX million by 2033, with an expected CAGR of XX% during the forecast period.

The dataset includes:

OLIVE-RIPENING-DATASET.CSV: Contains, in CSV format, the measurements performed on the 110 olive samples. For each sample, 15 fruits were randomly selected and measured. The last two columns include the reference analysis of fat content per dry matter (FCDM) and fat content per fresh weight (FCFW).(conducted in the laboratory following official methodologies).

OLIVE_RIPENING_DATASET.JSON: Contains the metadata of the dataset.

README.TXT: This information in txt format.

Fruit Ripening

## Overview

Fruit Ripening is a dataset for classification tasks - it contains Fruit Ripening annotations for 2,688 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Fruit Ripening Systems Market Outlook

According to our latest research, the global fruit ripening systems market size reached USD 2.41 billion in 2024, driven by increasing demand for high-quality, uniformly ripened fruits across international supply chains. The market is projected to grow at a robust CAGR of 6.2% from 2025 to 2033, reaching an estimated USD 4.13 billion by 2033. This growth trajectory is underpinned by rapid advancements in ripening technologies, shifting consumer preferences for fresh produce, and the rising adoption of controlled ripening methods by commercial players worldwide.

Several key factors are fueling the expansion of the fruit ripening systems market. The globalization of fruit trade and the need to maintain optimal fruit quality throughout long-distance transportation have increased the reliance on advanced ripening solutions. Supermarkets and food processing companies are investing in state-of-the-art ripening chambers, ethylene generators, and control systems to ensure consistent ripening, minimize losses, and extend shelf life. Moreover, the rising awareness among consumers regarding the health benefits of fresh fruits has compelled retailers and distributors to adopt technologies that guarantee uniform flavor, color, and texture, further propelling market growth.

Technological innovation stands out as a pivotal driver in the fruit ripening systems market. The integration of IoT-enabled control systems, automation, and real-time monitoring capabilities has transformed traditional ripening processes. Fully automatic ripening chambers equipped with advanced sensors and precision gas control not only enhance efficiency but also reduce human error and operational costs. These advancements are particularly attractive to large-scale commercial warehouses and food processing companies seeking scalable, reliable, and energy-efficient solutions. Additionally, stringent regulations on the use of hazardous ripening chemicals have accelerated the shift towards safer, ethylene-based systems, bolstering the adoption of compliant and eco-friendly technologies.

The regional landscape of the fruit ripening systems market is characterized by diverse growth patterns. Asia Pacific dominates the global market, driven by the vast production and export of bananas, mangoes, and other tropical fruits. North America and Europe are witnessing increased adoption of automated ripening technologies, supported by sophisticated retail infrastructure and high consumer expectations for fruit quality. Meanwhile, Latin America and the Middle East & Africa are emerging as lucrative markets, benefiting from expanding fruit exports and investments in modern post-harvest management solutions. This regional dynamism is expected to intensify competition and foster innovation across the global market during the forecast period.

Product Type Analysis

The product landscape of the fruit ripening systems market encompasses ethylene generators, ripening chambers, ripening gas, control systems, and other specialized equipment. Ethylene generators are widely recognized for their efficiency and safety, providing a controlled release of ethylene gas to stimulate uniform ripening. Their portability, ease of use, and compliance with international standards have made them the preferred choice for commercial warehouses and exporters. Ripening chambers, on the other hand, offer a comprehensive solution by combining temperature, humidity, and gas concentration controls, allowing for precise management of the entire ripening process. These chambers are particularly popular among supermarkets and food processing companies that require large-scale, batch-wise ripening capabilities.

Ripening gas solutions, primarily based on ethylene, have gained traction as a safe alternative to traditional chemical ripening agents such as calcium carbide. The transition towards ripening gas is driven by regulatory bans on hazardous substances and growing consumer demand for residue-free fruits. Control systems, including advanced monitoring and automation platforms, are increasingly being integrated with other product types to provide real-time data analytics, remote operation, and predictive maintenance. This convergence of hardware and software is revolutionizing the market, enabling end-users to optimize energy consumption, reduce waste, and ensure consistent product quality.

The "others" category within th

The booming fruit ripening system market, projected at $500 million in 2025 and growing at a 7% CAGR, is analyzed in this report. Discover key trends, leading companies (EHO, Interko, Thermal Tech), and regional market shares. Learn about the impact of technology, regulations, and consumer preferences on this dynamic sector.

Fruit ripening is an important process that affects fruit quality. A QTL in melon, ETHQV6.3, involved in climacteric ripening regulation, has been found to be encoded by CmNAC-NOR, a homologue of the tomato NOR gene. To further investigate CmNAC-NOR function, we obtained two CRISPR/Cas9-mediated mutants (nor-3 and nor-1) in the climacteric Védrantais background. nor-3, containing a 3-bp deletion altering the NAC domain A, resulted in ~8 days delay in ripening without affecting fruit quality. In contrast, the 1-bp deletion in nor-1 resulted in a fully disrupted NAC domain, which completely blocked climacteric ripening. The nor-1 fruits did not produce ethylene, no abscission layer was formed and there was no external color change. Additionally, volatile components were dramatically altered, seeds were not well developed and flesh firmness was also altered. There was a delay in fruit ripening with the nor-1 allele in heterozygosis of ~20 days. Our results provide new information regarding the function of CmNAC-NOR in melon fruit ripening, suggesting that it is a potential target for modulating shelf life in commercial climacteric melon varieties.

The global market for ripening chambers is experiencing robust growth, driven by an increasing consumer demand for consistently ripened fruits, year-round availability, and a growing awareness of the benefits of controlled ripening processes. The market size is estimated to be substantial, likely in the range of several hundred million USD, with a projected Compound Annual Growth Rate (CAGR) of approximately 6-8% over the forecast period of 2025-2033. This growth is fueled by the expansion of the fruit processing and export industries, particularly in emerging economies where post-harvest losses are a significant concern. Ripening chambers play a crucial role in mitigating these losses by optimizing the ripening process, extending shelf life, and ensuring uniform quality, thus meeting the stringent standards of international markets. The application segment is dominated by high-volume fruits like bananas, mangoes, and papayas, which benefit significantly from controlled ethylene release and temperature management. The ripening chamber market is characterized by technological advancements, including sophisticated climate control systems, ethylene management technologies, and automation, which are becoming increasingly integrated into these chambers. This trend is supported by a growing number of companies offering innovative solutions and customized designs to cater to diverse operational needs, from small-scale producers to large industrial facilities. While the market presents significant opportunities, certain restraints such as high initial investment costs for advanced systems and the need for specialized technical expertise for operation and maintenance might pose challenges for smaller players. However, the overarching trend towards improved food quality, reduced wastage, and enhanced supply chain efficiency will continue to propel the demand for efficient and reliable ripening chamber solutions, particularly for units designed for larger production volumes (More Than 10 Ton capacity) across key regions like Asia Pacific and Europe. The global ripening chambers market is characterized by a moderate concentration, with a significant presence of both established refrigeration and cold chain solutions providers, alongside specialized ripening chamber manufacturers. Key innovation hubs are concentrated in regions with strong agricultural outputs and export-oriented fruit production, particularly in Asia, South America, and parts of Europe. The primary characteristics of innovation revolve around:

Energy Efficiency: Development of advanced insulation materials, optimized airflow systems, and smart temperature/humidity control to reduce operational costs, estimated to save up to 15% on energy bills for advanced models. Precision Control Systems: Integration of IoT and AI for real-time monitoring, predictive analytics, and precise ethylene management, leading to improved quality consistency and reduced spoilage rates, potentially by 5-10%. Scalability and Customization: Offering modular designs and bespoke solutions to cater to diverse operational needs, from small-scale farms producing less than 10 tons to large commercial operations exceeding 10 tons.

Impact of Regulations: Stringent food safety regulations and quality standards, particularly those related to post-harvest handling and export requirements, significantly influence the adoption of advanced ripening chambers. Compliance with these regulations often necessitates investments in sophisticated equipment. Product Substitutes: While direct substitutes for controlled ripening chambers are limited, traditional methods like natural ripening in ambient conditions or simpler cold storage solutions pose indirect competition. However, these methods lack the precision and consistency offered by dedicated chambers. End-User Concentration: The market is largely concentrated among large-scale fruit producers, commercial aggregators, distributors, and export houses dealing with high-volume, perishable commodities. Small and medium-sized enterprises are increasingly adopting these technologies as costs become more accessible. Level of M&A: The level of M&A activity is moderate, with larger refrigeration companies acquiring smaller, specialized ripening chamber manufacturers to expand their product portfolios and market reach. This trend is expected to continue as the market matures.

tomatOD

tomatOD is a dataset for tomato fruit localization and ripening classification, containing images of tomato fruits in a greenhouse and high-quality expert annotations from agriculturists. It is a task-specific object detection dataset for tomato fruits, suitable for precision agriculture applications that typically require highly-accurate localization.

The tomatOD dataset consists of 277 images with 2418 annotated tomato fruit samples of unripe, semi-ripe and fully-ripe classes.

The images and the annotations are licensed under CC BY-NC-SA 4.0 license. The contents of this repository are released under the license.

Sample images with tomato fruit annotations are shown below.

https://github.com/nexuswho/tomatOD/blob/master/assets/tomatOD_img1.png?raw=true"> https://github.com/nexuswho/tomatOD/blob/master/assets/tomatOD_img1.png?raw=true">

Data organization

The dataset was split into train and test set according to a 80%/20% train-test split ratio. Please, note that the selection of the training and test data was conducted in a semi-random manner. The following table shows the number of images and annotated boxes of train and test sets of the tomatOD dataset.

Data Format

The annotations of the tomatOD dataset are provided in a COCO compatible format.

Fix for test annotations error in with categorical ids contributed by ARTURO-BANDINI-JR

Statistics and data analysis

tomatOD classes

The table below shows the number of annotated objects for each class of the tomatOD dataset.

Additionally, the following figure illustrates the relative appearance frequencies of those three classes of the dataset. The classes of the tomatOD dataset are clearly not balanced, however their relative proportion is in line with the actual appearance frequency of each class in a realistic scenario.

https://github.com/nexuswho/tomatOD/blob/master/assets/classes_proportions_tomatOD.png?raw=true">

Size distribution of bounding boxes

The percentile relative size of each bounding box is calculated, which indicates the proportion of the diagonal length of each box over the diagonal length of the image. In the image below, the histogram of the percentile relative size distribution of the tomatOD bounding boxes is presented. Most of the bounding boxes have a size of 3% to 15% relative to the image size.

https://github.com/nexuswho/tomatOD/blob/master/assets/histogramm_boxes.png?raw=true">

Number of labelled instances per image

Only 1% of images have one category per image and 11% of images include 8 instances, while the maximum number of instances per image, which is 20, is found only in 0.72% of the images. The tomatOD dataset has an average of 8.7 instances per image. The image displays the histogram of the number of annotation instances per image.

Number of categories in images

As the next figure shows, more than 50% of the tomatOD images contain objects of all 3 categories, while less than 8% of the images have objects of a single category.

https://github.com/nexuswho/tomatOD/blob/master/assets/categories_in_images.png?raw=true">

Experiment

Six state-of-the-art detectors are evaluated at the proposed tomatOD dataset. In detail, Faster RCNN with Inception v2, SSD with both Inception v2 and Mobilenet v2, PPN with Inception v2, RetinaNet (ResNet 101) and Yolo v3 are trained on tomatOD train set for 450 epochs, all of them pretrained on COCO dataset. Afterwards, they are evaluated on test set. Hyperparameter fine-tuning was performed for all networks in order to perform optimally on the tomatOD dataset.

The figure below illustrates the accuracy over epochs for both the train and the test set for every trained model.

https://github.com/nexuswho/tomatOD/blob/master/assets/accuracy_vs_epochs.png?raw=true">

Retina outperformed the rest detectors, yielding an accuracy of 79.4 %. The average precision of each class, the mAP metrics and precision-recall curves for classes of RetinaNet are listed.

In the precision-recall curves diagram, the unripe class is indicated by the green line, the semi-ripe class by the orange line, while the fully-ripe class by red line.

<img...

Discover the booming fruit ripening system market! Learn about its $500 million (2025) valuation, 7% CAGR, key drivers, leading companies (EHO, Interko, Thermal Tech), and future trends impacting this dynamic sector. Explore market segmentation and regional insights for strategic planning.

Trihelix proteins are plant-specific transcription factors that play crucial roles in plant development and stress responses. However, the involvement of trihelix proteins in fruit ripening and transcriptional regulatory mechanisms remains largely unclear. In this study, we cloned a trihelix gene SlGT31, whose relative expression was significantly induced by the application of exogenous ethylene but repressed by 1-methylcyclopropene (1-MCP). Suppression of SlGT31 resulted in delayed fruit ripening, decreased accumulation of total carotenoids and ethylene content, and inhibition of relative expression of genes related to ethylene and fruit ripening. Conversely, the opposite results were observed in SlGT31-overexpression lines. Yeast one-hybrid and dual-luciferase assays suggested that SlGT31 could bind to the promoters of two key ethylene biosynthesis genes ACO1 and ACS4. These results indicate that SlGT31 may act as a positive modulator during fruit ripening., Plant Materials and Growth Conditions Tomato (Solanum lycopersicum Mill.var. Ailsa Craig) was used as the wild type (WT) in this study. WT and transgenic lines were grown in a glasshouse under controlled conditions with 16-h-light/8-h-dark cycles, 25°C-day/18°C-night temperatures, 80% relative humidity, and 250 μmol m−2 sec−1 luminous intensity. Flowers were tagged at the anthesis stage, immature green was defined as 20 DPA (days post-anthesis), and mature green was defined as 35 DPA. Breaker fruits were defined as fruits of 38 DPA with the color starting to generate a slight yellow color. Other fruits from the 4th and 7th days after breaker were also used. Fruits at different ripening stages were collected, frozen immediately in liquid nitrogen, and stored at -80°C until use. Sequence analysis and subcellular localization For SlGT31-GFP construction, the cDNA with the termination codon removed from SlGT31 was amplified with SlGT31-GFP-F/R primers (Supplementary Table.S1). The amplified..., , ## Trihelix transcription factor SlGT31 regulates fruit ripening mediated by ethylene in tomato

https://doi.org/10.5061/dryad.vdncjsz18

Description of the data and file structure

In this study, all tomato plants were grown in a glasshouse under controlled conditions with 16-h-light/8-h-dark cycles, 25°C-day/18°C-night temperatures, 80% relative humidity, and 250 μmol m−2 sec−1 luminous intensity. The independent overexpression lines and RNA interference (RNAi) lines were obtained through genetic transformation mediated by Agrobacterium tumefaciens strain LBA4404. All data are means ± standard deviation of at least three independent experiments. A single asterisk (*) and double asterisks (**) in the figures indicate significant differences of P < 0.05 and significant differences of P < 0.01, respectively. These datasets contain the mean and standard deviation (SD) of the data corresponding to the experiments and figures in ...

The tomato (Solanum lycopersicum) MADS box FRUITFULL homologs FUL1 and FUL2 act as key ripening regulators and interact with the master regulator MADS box protein RIPENING INHIBITOR (RIN). Here, we report the large-scale identification of direct targets of FUL1 and FUL2 by transcriptome analysis of FUL1/FUL2 suppressed fruits and chromatin immunoprecipitation coupled with microarray analysis (ChIP-chip) targeting tomato gene promoters. The ChIP-chip and transcriptome analysis identified FUL1/FUL2 target genes that contain at least one genomic region bound by FUL1 or FUL2 (regions that occur mainly in their promoters) and exhibit FUL1/FUL2-dependent expression during ripening. These analyses identified 860 direct FUL1 targets and 878 direct FUL2 targets; this set of genes includes both direct targets of RIN and nontargets of RIN. Functional classification of the FUL1/FUL2 targets revealed that these FUL homologs function in many biological processes via the regulation of ripening-related...