Calla Lily Recognition Image Dataset for Garden Flowers

In the modern agriculture and forestry industry, the recognition and management of garden flowers is a challenging task. Traditional manual management methods are time-consuming, labor-intensive, and prone to errors, while existing automated recognition systems are often limited by insufficient data volume or inaccurate labeling. This dataset aims to improve the accuracy of calla lily recognition to support intelligent garden management business needs. The dataset is collected on-site using professional photographic equipment in diverse garden environments, ensuring coverage of different growth stages and lighting conditions of calla lilies. Quality control is carried out using a combination of multi-round labeling and expert review, with the labeling team composed of professionals with backgrounds in agricultural and forestry botany, ensuring labeling accuracy and consistency. Data preprocessing includes image denoising, color correction, and resolution unification, ultimately stored in JPG format and organized by category and stage of the calla lilies. The core advantage of this dataset lies in its excellent data quality, with labeling accuracy exceeding 98%; it employs an innovative semi-automatic labeling method that significantly improves labeling efficiency; in practical applications, this dataset can increase plant recognition accuracy by up to 15%, effectively reducing management costs. Compared to other datasets, it provides more comprehensive growth stage images and higher labeling consistency. In addition, the dataset has good scalability and can be widely applied to other flower identification or related agricultural fields.