MYCOLab Ai Logo - gold and army green

A novel dataset of annotated oyster mushroom images with environmental context for machine learning applications

Summary

Researchers have created a large collection of carefully labeled photographs of oyster mushrooms along with environmental data from the farm where they were grown. The dataset includes about 16,000 images showing mushrooms at different stages of growth, captured both day and night, along with measurements of temperature, humidity, and air quality. This resource is designed to help scientists and farmers develop computer programs that can automatically identify mushrooms, determine if they’re ready to harvest, and predict growth patterns.

Background

Automated systems struggle with mushroom classification and growth analysis due to their varied sizes, shapes, and surface characteristics. Machine learning technologies show promise for addressing these challenges, but the field lacks comprehensive, well-labeled datasets of mushroom images across different growth stages and conditions.

Objective

To present a novel dataset of annotated oyster mushroom images captured with corresponding environmental parameters to enable development of machine learning models for intelligent mushroom cultivation, classification, and growth analysis.

Results

The dataset comprises 7,963 mushroom-labeled images, 8,282 maturity-labeled images (3,158 mature and 5,124 immature), annotation files in three popular formats (COCO, PASCAL VOC, YOLO), and sensor data from both cultivation cycles. Images were captured during day and night conditions, capturing diverse mushroom morphologies and growth stages with accompanying environmental parameters.

Conclusion

This comprehensive dataset provides a valuable resource for developing machine learning models for oyster mushroom classification, maturity detection, and growth analysis, while also offering potential applications in computer vision, agricultural robotics, precision agriculture, and fungal studies.
  • Published in:Data Brief,
  • Study Type:Dataset Creation and Annotation,
  • Source: 10.1016/j.dib.2024.111074, PMID: 39640405
Scroll to Top