Dark Mode
Machine Learning Date Fruit Dataset
Food & Beverage Consumption
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This dataset is designed for the classification of date fruit types using machine learning methods. It addresses the challenge that determining fruit varieties by external appearance often requires specialised expertise, which can be time-consuming and effort-intensive. The study aims to successfully apply machine learning techniques for this task. The dataset consists of 898 images representing seven distinct types of date fruit. From these images, a total of 34 features, encompassing morphological characteristics, shape, and colour, have been extracted using image processing techniques via a computer vision system.
Columns
The dataset includes 35 attributes, primarily comprising morphological, shape, and colour features, along with a classification label.
- AREA: Integer
- PERIMETER: Real
- MAJOR_AXIS: Real
- MINOR_AXIS: Real
- ECCENTRICITY: Real
- EQDIASQ: Real
- SOLIDITY: Real
- CONVEX_AREA: Integer
- EXTENT: Real
- ASPECT_RATIO: Real
- ROUNDNESS: Real
- COMPACTNESS: Real
- SHAPEFACTOR_1: Real
- SHAPEFACTOR_2: Real
- SHAPEFACTOR_3: Real
- SHAPEFACTOR_4: Real
- MeanRR: Real (Mean Red component)
- MeanRG: Real (Mean Green component)
- MeanRB: Real (Mean Blue component)
- StdDevRR: Real (Standard Deviation Red component)
- StdDevRG: Real (Standard Deviation Green component)
- StdDevRB: Real (Standard Deviation Blue component)
- SkewRR: Real (Skewness Red component)
- SkewRG: Real (Skewness Green component)
- SkewRB: Real (Skewness Blue component)
- KurtosisRR: Real (Kurtosis Red component)
- KurtosisRG: Real (Kurtosis Green component)
- KurtosisRB: Real (Kurtosis Blue component)
- EntropyRR: Real (Entropy Red component)
- EntropyRG: Real (Entropy Green component)
- EntropyRB: Real (Entropy Blue component)
- ALLdaub4RR: Real
- ALLdaub4RG: Real
- ALLdaub4RB: Real
- Class: Categorical, representing the date fruit types {BERHI, DEGLET, DOKOL, IRAQI, ROTANA, SAFAVI, SOGAY}
Distribution
The dataset is available in ARFF and CSV file formats. The ARFF file (
Date_Fruit_Datasets.arff) is approximately 252.54 kB, while the CSV version (Date_Fruit_Datasets.csv) is around 504.97 kB. It contains 898 records, each corresponding to an image of a date fruit, with 34 extracted features plus a class label for each.Usage
This dataset is suitable for developing and evaluating various machine learning models aimed at fruit classification. It can be utilised for:
- Training and testing machine learning algorithms such as Logistic Regression, Artificial Neural Networks, and stacking models.
- Research in computer vision and image processing for agricultural applications.
- Developing automated systems for sorting and quality control of date fruits.
- Educational purposes in data science and artificial intelligence courses focusing on classification tasks.
Coverage
The dataset specifically covers seven types of date fruit: BERHI, DEGLET, DOKOL, IRAQI, ROTANA, SAFAVI, and SOGAY. Information regarding the geographic origin, specific time range of data collection, or demographic scope is not provided in the available sources.
License
CC BY-NC-SA 4.0
Who Can Use It
This dataset is ideal for:
- Machine Learning Engineers and Researchers: For building and testing fruit classification models.
- Computer Vision Specialists: For applications in image analysis and feature extraction.
- Agricultural Technologists: For developing automated fruit sorting and quality control solutions.
- Data Scientists: For practicing classification tasks and exploring feature importance in image data.
- Students and Educators: For learning and teaching concepts related to machine learning, image processing, and data classification.
Dataset Name Suggestions
- Date Fruit Varieties Classification
- Image-Based Date Fruit Type Data
- Machine Learning Date Fruit Dataset
- Agricultural Fruit Classification Images
Attributes
Original Data Source: Machine Learning Date Fruit Dataset
QUALITY