This dataset is recreated using offline augmentation from the original dataset. The original dataset can be found on this github repo. This dataset consists of about 87K rgb images of healthy and diseased crop leaves which is categorized into 38 different classes. The total dataset is divided into 80/20 ratio of training and validation set preserving the directory structure. A new directory containing 33 test images is created later for prediction purpose.

The authors of the DiaMOS Plant: A Dataset for Diagnosis and Monitoring Plant Disease contribute to the evolving field of foliar disease classification and recognition through the utilization of machine and deep learning concepts. It has 3505 images of pear fruit and leaves affected by four diseases: slug leaf, spot leaf, curl leaf, and healthy leaf. The study offers valuable guidelines for the research community to select and construct further datasets.

Data Set Information:

For Each feature, a 64 element vector is given per sample of leaf. These vectors are taken as a contigous descriptors (for shape) or histograms (for texture and margin).

Attribute Information:

For Each feature, a 64 element vector is given per sample of leaf. One file for each 64-element feature vectors. Each row begins with the class label. The remaining 64 elements is the feature vector.

Relevant Papers:

This is a new data set, provisional paper: 'Plant Leaf Classification Using

Probabilistic Integration of Shape, Texture and Margin Features' at SPPRA 2013. Authors: Charles Mallah, James Cope, and James Orwell or Kingston University London.

Previous parts of the data set relate to feature extraction of leaves from: J. Cope, P. Remagnino, S. Barman, and P. Wilkin. Plant texture classification using gabor cooccurrences. Advances in Visual Computing, pages 669–677, 2010.

T. Beghin, J. Cope, P. Remagnino, and S. Barman. Shape and texture based plant leaf classification. In Advanced Concepts for Intelligent Vision Systems, pages 345–353. Springer, 2010.

Source:

James Cope, Thibaut Beghin, Paolo Remagnino, Sarah Barman. The colour images are not included in this submission. The Leaves were collected in the Royal Botanic Gardens, Kew, UK. email: james.cope '@' kingston.ac.uk

This dataset consists of work carried out by James Cope, Charles Mallah, and James Orwell. Kingston University London. Donor of database Charles Mallah: charles.mallah '@' kingston.ac.uk; James Cope: james.cope '@' kingston.ac.uk

Medicinal Plant

## Overview

Medicinal Plant is a dataset for object detection tasks - it contains Medi annotations for 1,058 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).

A dataset of 61,486 images of plant leaves and backgrounds, with each image labeled with the disease or pest that is present. The dataset was created by researchers at the University of Wisconsin-Madison and is used for research in machine learning and computer vision tasks such as plant disease detection and pest identification.

There are two datasets and one table uploaded in this platform under the title "MED117_Medicinal Plant Leaf Dataset & Name Table". A folder is created with title "MED 117 Leaf Species". Inside this two sub folders with titles " Raw leaf image set of medicinal plants_v2" and "Segmented leaf set using UNET segmentation" are created. Raw leaf image set consists of leaf images of 117 medicinal plants found in Assam. All the samples are collected by visiting different (Govt, Public and Private) medicinal gardens situated in different places of Assam and some other general places where they are mostly found. Videos of 10 to 15 seconds duration were taken for two to three leaves of every species on a white background and video recording was done using a SLR Canon Camera. Individual videos were segregated into image frames and thus were able to get around 77,700 jpg image frames from the videos. The Raw leaf image set consists of folders with scientific name and common name within bracket. Second folder with title "Segmented leaf set using UNET segmentation" consists of 115 medicinal plant species with their segmented leaf image samples using UNET segmentation technique. Here two species are excluded from the original dataset due to small unpredictable size of the samples, so total 115 subfolders inside the segmented folder is achieved. Thirdly a table in doc format with title "Medicinal Plant Name Table" is uploaded and it includes Scientific name, Common name and Assamese name of the plants listed in the folders in the same sequence. The whole contribution is absolutely original and new, collected from different sources then processed for segmentation and prepared the table by discussing with taxonomy experts from Botany department of Gauhati University, Guwahati, Assam. India.

Plants Diseases Detection And Classification

## Overview

Plants Diseases Detection And Classification is a dataset for object detection tasks - it contains Plants annotations for 2,516 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).

Dataset Overview: The Leaf Disease Dataset is a comprehensive collection of images designed for the classification and detection of various leaf diseases. This dataset is ideal for training and evaluating machine learning models in the field of plant pathology, agricultural research, and computer vision.

Classes: The dataset consists of images categorized into three distinct classes representing different types of leaf diseases:

Mildew:

Description: Mildew is a fungal disease that affects a wide range of plants, characterized by a white, powdery coating on the surface of the leaves. It can cause significant damage to crops by interfering with photosynthesis and reducing plant vigor. Visual Features: White or gray powdery spots on the leaves, which may spread and cover large areas as the infection progresses. Rose_P01:

Description: This class represents a specific type of disease affecting rose plants. It is designated as 'Rose_P01' and includes various symptoms that are detrimental to the health of rose plants. Visual Features: Symptoms may include discolored spots, lesions, or patches on the leaves, which can lead to reduced blooming and overall plant health. Rose_R02:

Description: Similar to 'Rose_P01', the 'Rose_R02' class represents another disease variant affecting rose plants. This class includes different symptoms and manifestations specific to this disease type. Visual Features: Symptoms may vary from spots and lesions to more severe signs such as leaf curling, yellowing, or premature leaf drop, indicating a different disease pathology compared to 'Rose_P01'. Dataset Specifications:

Image Format: The images in this dataset are in high-resolution JPEG format. Image Size: Each image is standardized to a consistent size to ensure uniformity across the dataset. Annotations: Each image is labeled with its corresponding class, facilitating supervised learning tasks. Applications:

Disease Detection and Classification: This dataset can be used to train machine learning models to accurately detect and classify leaf diseases in real-time. Agricultural Research: Researchers can utilize this dataset to study the spread and impact of different leaf diseases on crop health. Precision Agriculture: The dataset supports the development of automated systems for early disease detection, helping farmers take proactive measures to protect their crops. Usage:

Training and Testing: Suitable for splitting into training and testing subsets for machine learning experiments. Model Benchmarking: Can be used to benchmark the performance of different algorithms in leaf disease classification tasks. Conclusion: The Leaf Disease Dataset provides a valuable resource for the development of robust and accurate models for disease detection in plants. By leveraging this dataset, researchers and practitioners can advance the field of plant pathology and contribute to more sustainable agricultural practices.

Plant species cover-abundance and presence observed in multi-scale plots. Plant species and associated percent cover in 1m2 subplots and plant species presence in 10m2 and 100m2 subplots are reported from 400m2 plots. Archived plant vouchers and foliar tissue support the data and additional analyses.

Here are a few use cases for this project:

1. Agricultural disease and pest monitoring: The "plant" model could be used to monitor crops for early signs of disease or pest infestations by identifying specific leaf conditions, enabling farmers to apply timely treatments and prevent damage to large portions of their crops.

2. Plant care and maintenance: Gardeners and horticulture enthusiasts could use the "plant" model to diagnose the health of their plants and determine necessary treatment or care methods, leading to better maintenance and improved plant growth.

3. Botanical research and education: Researchers and educators can use the "plant" model as a teaching tool to help students identify and study various plant leaves and their diseases, promoting a deeper understanding of botany and plant pathology.

4. Plant identification and biodiversity tracking: Environmental scientists and nature enthusiasts can utilize the "plant" model to identify plant species in a given area. This can contribute to research on biodiversity, conservation efforts, and the tracking of invasive species.

5. Horticulture industry quality control: The "plant" model could be used by horticulture industry professionals to monitor plant quality and diagnose potential diseases, allowing them to maintain high standards and address issues proactively to keep consumers satisfied with healthy, attractive plants.

Juliekyungyoon/plant-kaggle-seg-data dataset hosted on Hugging Face and contributed by the HF Datasets community

This dataset was created as part of a study project on plant disease classification. The self-imposed requirements for the dataset were as follows: large amount of images, for each plant at least healthy and one disease, most common diseases, annotated images, laboratory and field images, important staple food and highest global production plant species. Because of the requirements towards the dataset, no existing dataset could be used, but a new dataset was compiled by combining images from 14 different existing datasets. All included datasets, their properties and the imported images are listed in the table below along with the proper references.. This new dataset contains laboratory as well as field images. Images of non-food plants, singular condition classes, watermarked images and classes with less than 50 examples were removed. The final dataset used for the training within the project contains 88 classes with above 76,000 images of overall size of 17.6GB. What can not be avoided in general is a bias among the classes, since in some cases different shooting conditions were used for the images (e.g. classes with mainly laboratory images or different soil in the background).

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F11839378%2Fae7dbbbf4e96ec87f8055303a618b24c%2FKaggleTableData.png?generation=1677868803290050&alt=media" alt="">

[1] F. Nahian, “Plant disease [65 classes],” kaggle dataset: https://www.kaggle.com/datasets/fabinahian/plant-disease-65-classes, 09 2022, accessed: 26.12.2022. [2] D. Singh, N. Jain, P. Jain, P. Kayal, S. Kumawat, and N. Batra, “Plantdoc: A dataset for visual plant disease detection,” in Proceedings of the 7th ACM IKDD CoDS and 25th COMAD, ser. CoDS COMAD 2020. New York, NY, USA: Association for Computing Machinery, 2020, p. 249–253. doi: 10.1145/3371158.3371196. ISBN 9781450377386. [Online]. Available: https://doi.org/10.1145/3371158.3371196 [3] C. Disease, “Coffee plant disease,” kaggle dataset: https://www.kaggle.com/datasets/coffeedisease/coffee-plant-disease, 2021, last accessed: 23.02.2023. [4] O. Getch, “Wheat leaf dataset,” kaggle dataset: https://www.kaggle.com/datasets/olyadgetch/wheat-leaf-dataset, 2021, last accessed: 23.02.2023. [5] D. D. Prakoso, “Chili plant disease,” kaggle dataset: https://www.kaggle.com/datasets/dhenyd/chili-plant-disease, 2021, last accessed: 23.02.2023. [6] M. E. Mignoni, “Images of soybean leaves,” mendeley dataset: https://data.mendeley.com/datasets/bycbh73438/1, December 2021, last accessed: 23.02.2023. [7] D. V. Prajapati HB, Shah JP, “Rice leaf diseases dataset (detection and classification of rice plant diseases. intelligent decision technologies.),” kaggle dataset: https://www.kaggle.com/datasets/vbookshelf/rice-leaf-diseases, pp. 357–73, January 2017. [8] S. Riyaz, “Rice leafs,” kaggle dataset: https://www.kaggle.com/datasets/shayanriyaz/riceleafs, 2019, last accessed: 23.02.2023. [9] K. Negm, “Cucumber plant diseases dataset,” kaggle dataset: https://www.kaggle.com/datasets/kareem3egm/cucumber-plant-diseases-dataset, 2021, last accessed: 23.02.2023. [10] S. S. Mahi, “Plant disease expert,” kaggle dataset: https://www.kaggle.com/datasets/sadmansakibmahi/plant-disease-expert, 12 2022, accessed: 26.12.2022. [11] H. A. Iranga, “Leaf disease dataset (combination),” kaggle dataset: https://www.kaggle.com/datasets/asheniranga/leaf-disease-dataset-combination, 2022, last accessed: 23.02.2023. [12] L. V. S. T. T. BARBEDO, J. G. A.; KOENIGKAN, “Identifying multiple plant diseases using digital image processing,” Biosystems Engineering, vol. 147, pp. 104–116, 07 2016. [13] P. Soundar, “Sugarcane disease dataset,” kaggle dataset: https://www.kaggle.com/datasets/prabhakaransoundar/sugarcane-disease-dataset, 2022, last accessed: 23.02.2023. [14] R. B. A. R. Pungliya Vithika, Atharva Purohit, “Sugarcane leaf disease classification,” kaggle dataset: https://www.kaggle.com/datasets/pungliyavithika/sugarcaneleaf-disease-classification, 2022, last accessed: 23.02.2023.

The data file contains occurrence data based on historical observations and records between 1651 and 2004. Ten plant species have been studied : Alnus incana (L.) Moench, 1794 ; Buddleja davidii Franch., 1887 ; Castanea sativa Mill., 1798 ; Helianthus tuberosus L., 1753 ; Impatiens glandulifera Royle, 1833 ; Prunus cerasifera Ehrh., 1784 ; Prunus laurocerasus L., 1753 ; Reynoutria japonica Houtt., 1777 ; Robinia pseudoacacia L., 1753 ; and Spiraea japonica L.f., 1782. The data file is the result of a geo-historical study conducted over five months on the invasive plants species's introduction and distribution in Occitania (France), carried out within the framework of the EI2P-VALEEBEE project (Invasive species and pollinators, between constraints and potentials). Historical sources have been consulted during 2020 in order to find the oldest elements about the ten species. Each data corresponds to an historical observation or mention on one of the ten species of the study mainly on Metropolitan French territory since their introduction. Without an historical analysis, it is difficult to understand the current local distribution dynamics of invasive plant species, especially when some of them have been introduced on Metropolitan French territory for several centuries. All the interest of these occurrence data is to bring an historical depth allowing us to apprehend the local distribution of the ten species of the study over time. This can be allowed thanks to the record of several elements on their places of introduction, the comments from authors and observers on their abundance, and elements on the historical context of introduction. More generally, this historical data file is part of a multidisciplinary approach proposed by the members of EI2P project whose objective is to better take into account the ecological socio-cultural and economic issues raised by the issue of invasive alien plants.

This work was endorsed by the CNRS/INEE Zone Atelier Pyrénées Garonne (ZA PYGAR). The Zones Ateliers network (RZA) is recognized by ALLENVI, as an eLTER (European Long-Term Ecological Research).

A data paper explains precisely this dataset: Claudel M, Lerigoleur E, Brun C, Guillerme S (2022) Geohistorical dataset of ten plant species introduced into Occitania (France). Biodiversity Data Journal 10: e76283. https://doi.org/10.3897/BDJ.10.e76283

The authors of the PlantDoc: A Dataset for Visual Plant Disease Detection recognized the importance of training models with real-life images to account for the complexities of the real world. In light of this, they decided to create a dataset for accurate plant disease detection in the farm setting by downloading images from Google Images and Ecosia. Collecting large-scale plant disease data through fieldwork would have required significant effort, so they gathered approximately 20,900 images making the final dataset having a total of 27 classes spanning over 13 species with 2,598 images. Numbers in the claimed and the actual dataset differ.

Here we present version 2.0 of the China Plant Trait Database, which contains information on morphometric, physical, chemical, photosynthetic and hydraulic traits from 1529 unique species in 140 sites spanning a diversity of vegetation types. Version 2 has five improvements compared to the previous version: (1) new data from a 4-km elevation transect on the edge of Tibetan Plateau, including alpine vegetation types not sampled previously; (2) inclusion of traits related to hydraulic processes, including specific sapwood conductance, the area ratio of sapwood to leaf, wood density and leaf turgor loss point; (3) inclusion of information on soil properties to complement the existing data on climate and vegetation (4) assessments of the reliability of individual trait measurements; and (5) inclusion of standardized checklists and templates for systematical field sampling and measurements. See detailed descriptions here: Wang, H., Harrison, S.P., Li, M. et al. The China plant trait database version 2. Sci Data 9, 769 (2022). https://doi.org/10.1038/s41597-022-01884-4

Waterwise plant information. Includes information like botanical names; water, climate, soil and light needs; level of maintenance required etc.

This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 United States License.

# Data origins
The dataset is originally hosted at PlantVillage Disease Classification Challenge.
We use the modified version in this github repository to do controlled experiments.
We only use the raw color images dataset and delete the unconventional characters in the classes directory name and `.csv` filenames.

# Directory explanation
The `80-20` direcotry has multiple `.txt` files which contain the training (~80%), validation(~10%) and testing (~10%) datasets instances filenames and the corresponding label indexes. The validation dataset quantity is `5430` in all data separation. In our experiment code (not included in this archive), the validation and testing dataset are merged together.

# Data usage
## Replicate our experiments
We have used this dataset in writing our paper. The reference information can be seen at https://gitlab.com/huix/leaf-disease-plant-village.

### Steps
1. `cd` to the direcotry (e.g. `/home/usrname/plantvillage_deeplearning_paper_dataset`) that contains the `color` directory.
2. run `python change_filename_prefix.py --prefix /home/usrname/plantvillage_deeplearning_paper_dataset` to modify the prefix path (which is `/home/h/plantvillage_deeplearning_paper_dataset` in our former generated datasets).
3. Fin. You can use our opens ource codes repository to do the later experiments.

## Generate your own training/validation/testing datasets
This data separation generating code isn't included in the dataset archive, it is in our open source code. Please see our open source code repository for the detailed information.
If you have any questions, you can contact the author through email.
The email address is a QR code in the archive.

Pea Plant Disease Detection Dataset Overview This dataset was designed to support research and model development for the automated detection of diseases affecting pea plants. It includes labeled images of pea plant leaves, allowing users to differentiate between healthy and diseased samples effectively.

Dataset Structure The dataset contains 4 main directories, each representing a different class:

Classes: FRESH_LEAF (Healthy samples) - 411 images DOWNY_MILDEW_LEAF - 366 images LEAFMINER_LEAF - 348 images POWDER_MILDEW_LEAF - 307 images Image Format: JPEG/PNG

Image Resolution: The images in this dataset vary in resolution, reflecting the diversity of conditions under which they were captured.

Usage Ideal for machine learning and deep learning projects, this dataset is suitable for image classification tasks aimed at plant health monitoring, agricultural diagnostics, and precision agriculture applications.

Data Collection Method This dataset was created in 2023 as part of a collaborative project by a team of three members tasked with collecting data specifically on pea plants. Images were collected from a small field located in Urmar Payan, near Peshawar in Khyber Pakhtunkhwa, Pakistan. The team captured images under varied lighting and angle conditions to enhance the robustness of the dataset, ensuring that models trained on it could generalize well in diverse real-world scenarios.

License Apache 2.0 – free for research and commercial applications with proper attribution.

Acknowledgments Please reference this dataset as: "Pea Plant Disease Detection Dataset, curated by Abdullah Zunorain(2023)."

This unique and huge data set contains plant information for the Himalaya Uplands; it consists of 164,360 records. This database is implemented in MS ACCESS following ABCD 1.2. It describes Asian plant species related to the Tibetan Plateau, Central Asia. Data have been collected for over 50 years, and in over 11 countries (e.g. Afghanistan, Pakistan, Bhutan, China,India, Kazakhstan, Kyrgyztan, Myanmar, Nepal, Russia, Tajikistan, Turkmenistan, Uzbekistan), covering over 220 national regions. Taxonomic information for this region is diverse and not well studied. However, the database follows ICBN taxonomy matched with ITIS and consists of over 5,562 unique species entries. From these, ITIS has 996 species listed. Over 2,200 collectors from all over the world contributed to this dataset, which mostly was compiled and maintained by the author for over 20 years. This database covers 21,869 localities. virtually all sites are georeferenced with latitude and longitude (2 decimals; geographic datum of WGS84), and 6,668 of such unique locations are found in the HUP database. This dataset has altitude information provided by the fieldworker.