GOURD LEAVES

The dataset comprises over 500 images of gourd leaves from the Cucurbitaceae family, classified into two categories: "good" and "bad." These images were captured using a Poco M2 Pro mobile camera against a black background under daylight conditions, ensuring consistent lighting across the dataset.

For each image, various attributes and characteristics of the gourd leaves were captured, including:

1. **Leaf Size and Shape**: Measurements of length, width, and shape descriptors such as aspect ratio or circularity, providing insights into the physical morphology of the leaves.

2. **Color**: RGB values or color histograms representing the color distribution across the leaf surface. This information can help identify patterns related to health or disease.

3. **Texture**: Descriptors of leaf texture, such as smoothness, roughness, or presence of any patterns or abnormalities.

4. **Vein Structure**: Analysis of the vein network within the leaves, including parameters like vein density, arrangement, and branching patterns.

5. **Symptoms and Defects**: Identification of any visible symptoms or defects indicating the health condition of the leaves. This could include signs of pests, diseases, nutrient deficiencies, or physical damage.

6. **Contextual Information**: Metadata such as location, date, and time of image capture, which can provide additional context for understanding environmental conditions and potential factors influencing leaf health.

Furthermore, the dataset may include annotations or labels provided by domain experts indicating whether each leaf is classified as "good" or "bad" based on predefined criteria. These labels serve as ground truth for training and evaluating classification algorithms.

The dataset aims to facilitate research and development in the field of agricultural science, specifically in the domain of gourd leaf health assessment and disease diagnosis. By leveraging machine learning techniques, researchers can develop models capable of accurately classifying gourd leaves and detecting potential health issues, ultimately aiding farmers in early intervention and crop management strategies.