Indian Biological Images Archive

Project Accession:	IBIAP_1000000005
Title:	FruitNet: Indian fruits image dataset with quality for machine learning applications
Representative Image:
Description:	Fast and precise fruit classification or recognition as per quality parameter is the unmet need of agriculture business. This is an open research problem, which always attracts researchers. Machine learning and deep learning techniques have shown very promising results for the classification and object detection problems. Neat and clean dataset is the elementary requirement to build accurate and robust machine learning models for the real-time environment. With this objective we have created an image dataset of Indian fruits with quality parameter which are highly consumed or exported. Accordingly, we have considered six fruits namely apple, banana, guava, lime, orange, and pomegranate to create a dataset. The dataset is divided into three folders (1) Good quality fruits (2) Bad quality fruits, and (3) Mixed quality fruits each consists of six fruits subfolders. Total 19,500+ images in the processed format are available in the dataset. We strongly believe that the proposed dataset is very helpful for training, testing and validation of fruit classification or reorganization machine leaning model.
Publications:	https://www.sciencedirect.com/science/article/pii/S2352340921009616
Funding agency:	There is no funding for the present effort.
Grant Number:	N/A
Ethics Statement:	N/A
Any Other Information :	N/A
Additional File:	N/A
Acknowledgments:	N/A

Sr.No	First name	Last name	Email	Organization	Designation
1	Vishal	Meshram	vishal.meshram-020@vupune.ac.in	Vishwakarma University, India	Principal Investigator
2	Kailas	Patil	kailas.patil@vupune.ac.in	Vishwakarma University, India	Principal Investigator

Study Accession:	PPS_1000000009
Title:	FruitNet: Indian Fruits Dataset with quality (Good, Bad & Mixed quality)
Imaging Type:	Plant Photography (PP)
Imaging Sub-type:	Not Applicable
Summary:	The profit percentage share of fruit market is substantial with respect to the total agriculture output. In the agro-industry fast and accurate fruit classification is the highest need. The fruits can be classified into different classes as per their external features like shape, size and color using some computer vision and deep learning techniques. High quality images of fruits are required to solve fruit classification and recognition problem. To build the machine learning models, neat and clean dataset is the elementary requirement. With this objective we have created the dataset of six popular Indian fruits named as “FruitNet”. This dataset consists of 19500+ high-quality images of 6 different classes of fruits in the processed format. The images are divided into 3 sub-folders 1) Good quality fruits 2) Bad quality fruits and 3) Mixed quality fruits. Each sub-folder contains the 6 fruits images i.e. apple, banana, guava, lime, orange, and pomegranate. Mobile phone with a high-end resolution camera was used to capture the images. The images were taken at the different backgrounds and in different lighting conditions. The proposed dataset can be used for training, testing and validation of fruit classification or reorganization model.
Keywords:	Convolutional neural network; Computer vision; Deep learning; Fruit classification; Fruit detection; Fruit image dataset; Machine learning
Additional / Any Other Information:	N/A
Release Date:	Oct. 23, 2024
Access Licence Type:	Open Access

Table 1. The sample types registered under this study are as follows:

Sample Type ID	Organism	Taxon ID	Biological Entity	Laterality	Source Tissue	Source Cell/Cell-line	Cell Organelle
PPSMT_10000000008	Malus pumila	283210	Fruit	Not Applicable	N/A	N/A	N/A
PPSMT_10000000009	Musa	4640	Fruit	Not Applicable	N/A	N/A	N/A
PPSMT_10000000010	Psidium guajava	120290	Fruit	Not Applicable	N/A	N/A	N/A
PPSMT_10000000012	Citrus sinensis	2711	Fruit	Not Applicable	N/A	N/A	N/A
PPSMT_10000000013	Punica granatum	22663	Fruit	Not Applicable	N/A	N/A	N/A
PPSMT_10000000011	Citrus aurantiifolia	159033	Fruit	Not Applicable	N/A	N/A	N/A

Table 2. The samples registered under this study are as follows:

Sample Type ID	Sample ID	Plant Part Used	Plant Variety Name	Sample Source	Geographic Location (latitude)	Geographic Location (longitude)	Quality class
PPSMT_10000000010	PPSM_10000012260	Fruit	N/A	Vishwakarma University, Pune; Hubtown Countrywoods Society, Pune	18.4603° N; 18.442866 ° N	73.8836° E; 73.884894° E	Bad quality
PPSMT_10000000010	PPSM_10000012261	Fruit	N/A	Vishwakarma University, Pune; Hubtown Countrywoods Society, Pune	18.4603° N; 18.442866 ° N	73.8836° E; 73.884894° E	Bad quality
PPSMT_10000000010	PPSM_10000012262	Fruit	N/A	Vishwakarma University, Pune; Hubtown Countrywoods Society, Pune	18.4603° N; 18.442866 ° N	73.8836° E; 73.884894° E	Bad quality
PPSMT_10000000010	PPSM_10000012263	Fruit	N/A	Vishwakarma University, Pune; Hubtown Countrywoods Society, Pune	18.4603° N; 18.442866 ° N	73.8836° E; 73.884894° E	Bad quality
PPSMT_10000000010	PPSM_10000012264	Fruit	N/A	Vishwakarma University, Pune; Hubtown Countrywoods Society, Pune	18.4603° N; 18.442866 ° N	73.8836° E; 73.884894° E	Bad quality
PPSMT_10000000010	PPSM_10000012265	Fruit	N/A	Vishwakarma University, Pune; Hubtown Countrywoods Society, Pune	18.4603° N; 18.442866 ° N	73.8836° E; 73.884894° E	Bad quality

Table 3. The experiment types registered under this study are as follows:

Experiment Type ID	Instrument Name	Instrument Type	Manufacturer	Model
PPET_10000000004	Camera	Smart Phone	Apple/ZUK/Realme	iPhone 6/Z2 Plus/Realme 5 Pro

Experimental Design Summary (PPET_10000000004)
The fruit images were acquired using three different make of camera's i.e. iPhone6 (Apple), ZUK (Z2 Plus), and Realme (Realme 5 Pro) mobile's high resolution rear camera. In all 19500+ images were captured using camera and then were segregated and saved in respective folders as per their quality and classification. The fruit images are captured in the natural and artificial lighting conditions with different directions/angles (front direction, top view, backward direction, bottom view, direction rotated 180 degrees) and background (dark color, grass, light color, ground, multicolor) in months of July to October. Images pre-processing is done using python script. In the pre-processing we changed the dimensions to 256 × 256 which is standard resolution required to build object classification or object detection model. The fruit images are captured using Apple iphone 6 with rear camera of 8 megapixels, Z2 plus with rear camera of 13 megapixel, and realme 5 pro with rear camera of 48 megapixels. All dataset images of original size 3024 × 3024 were resized to 256 × 256 dimensions using a python script. The images are in .jpg images. The images acquired in variety of environmental conditions such as different light conditions, different background, and from different angles. For more details, please refer to table 2 and table 3 (in the published article).

Experimental Design Summary (PPET_10000000004)

The fruit images were acquired using three different make of camera's i.e. iPhone6 (Apple), ZUK (Z2 Plus), and Realme (Realme 5 Pro) mobile's high resolution rear camera. In all 19500+ images were captured using camera and then were segregated and saved in respective folders as per their quality and classification. The fruit images are captured in the natural and artificial lighting conditions with different directions/angles (front direction, top view, backward direction, bottom view, direction rotated 180 degrees) and background (dark color, grass, light color, ground, multicolor) in months of July to October. Images pre-processing is done using python script. In the pre-processing we changed the dimensions to 256 × 256 which is standard resolution required to build object classification or object detection model. The fruit images are captured using Apple iphone 6 with rear camera of 8 megapixels, Z2 plus with rear camera of 13 megapixel, and realme 5 pro with rear camera of 48 megapixels. All dataset images of original size 3024 × 3024 were resized to 256 × 256 dimensions using a python script. The images are in .jpg images. The images acquired in variety of environmental conditions such as different light conditions, different background, and from different angles. For more details, please refer to table 2 and table 3 (in the published article).

Acquired Images Annotation Description (PPET_10000000004)
After capturing the images were organized as Bad quality, Good quality, and Mixed quality folders. Further each quality folder has six different folders of fruit classes i.e. apple, banana, guava, lime, orange, and pomegranate, respectively.

Table 4. The experiments registered under this study are as follows:

Sample ID	Experiment Type ID	Experiment ID	Image type (Original / Derived / Unknown)	Any Other Information	Light Source	Camera Specifications	Images Resolution (in MP)	Data Repository Name (If already deposited in a repository)	Direct URL to Data Download (Other than IBIA portal)	Type of Images
PPSM_10000026272	PPET_10000000004	PPE_10000026272	Derived	N/A	Natural/Artificial	Mobile phone rear camera	Not specified	Mendeley Data	https://data.mendeley.com/datasets/b6fftwbr2v/1	Raw
PPSM_10000026279	PPET_10000000004	PPE_10000026279	Derived	N/A	Natural/Artificial	Mobile phone rear camera	Not specified	Mendeley Data	https://data.mendeley.com/datasets/b6fftwbr2v/1	Raw
PPSM_10000026287	PPET_10000000004	PPE_10000026287	Derived	N/A	Natural/Artificial	Mobile phone rear camera	Not specified	Mendeley Data	https://data.mendeley.com/datasets/b6fftwbr2v/1	Raw
PPSM_10000026293	PPET_10000000004	PPE_10000026293	Derived	N/A	Natural/Artificial	Mobile phone rear camera	Not specified	Mendeley Data	https://data.mendeley.com/datasets/b6fftwbr2v/1	Raw
PPSM_10000026302	PPET_10000000004	PPE_10000026302	Derived	N/A	Natural/Artificial	Mobile phone rear camera	Not specified	Mendeley Data	https://data.mendeley.com/datasets/b6fftwbr2v/1	Raw
PPSM_10000026308	PPET_10000000004	PPE_10000026308	Derived	N/A	Natural/Artificial	Mobile phone rear camera	Not specified	Mendeley Data	https://data.mendeley.com/datasets/b6fftwbr2v/1	Raw

Experiment ID	Image File Name (with path)	Image Preview	Image Size
PPE_10000016620	FruitNet_Processed_Images/Processed_Images_Fruits/Bad_Quality_Fruits/Orange_Bad/IMG_20190824_174911_1.jpg	Download Image	20K
PPE_10000016621	FruitNet_Processed_Images/Processed_Images_Fruits/Bad_Quality_Fruits/Orange_Bad/IMG_20190824_174911.jpg	Download Image	20K
PPE_10000016622	FruitNet_Processed_Images/Processed_Images_Fruits/Bad_Quality_Fruits/Orange_Bad/IMG_20190824_174912.jpg	Download Image	20K
PPE_10000016623	FruitNet_Processed_Images/Processed_Images_Fruits/Bad_Quality_Fruits/Orange_Bad/IMG_20190824_174913_1.jpg	Download Image	20K
PPE_10000016624	FruitNet_Processed_Images/Processed_Images_Fruits/Bad_Quality_Fruits/Orange_Bad/IMG_20190824_174913.jpg	Download Image	20K
PPE_10000016625	FruitNet_Processed_Images/Processed_Images_Fruits/Bad_Quality_Fruits/Orange_Bad/IMG_20190824_174914_1.jpg	Download Image	20K
PPE_10000016626	FruitNet_Processed_Images/Processed_Images_Fruits/Bad_Quality_Fruits/Orange_Bad/IMG_20190824_174914.jpg	Download Image	20K
PPE_10000016627	FruitNet_Processed_Images/Processed_Images_Fruits/Bad_Quality_Fruits/Orange_Bad/IMG_20190824_174915_1.jpg	Download Image	20K
PPE_10000016628	FruitNet_Processed_Images/Processed_Images_Fruits/Bad_Quality_Fruits/Orange_Bad/IMG_20190824_174915.jpg	Download Image	20K
PPE_10000016629	FruitNet_Processed_Images/Processed_Images_Fruits/Bad_Quality_Fruits/Orange_Bad/IMG_20190824_174916_1.jpg	Download Image	20K

Study Complete Details

Address

Quick Links

Study Complete Details

Project

Authors/Collaborators

Study

Sample(s)

Experiment(s)

Image Files

Address

Quick Links