Aquilegia Recognizing Image Dataset for Garden Flowers

Currently, plant identification in the agriculture and forestry sectors faces challenges due to the diversity of species and high similarity, making traditional manual identification inefficient and error-prone. Existing solutions mostly rely on a small amount of manually labeled data, lacking intelligent and efficient identification capabilities. This dataset focuses on the image recognition of Aquilegia, aiming to improve the accuracy and ease of use of intelligent identification systems by providing large-scale, high-quality Aquilegia image data. Data collection is conducted in various horticultural environments, under different lighting conditions and multi-angle shots, using high-resolution cameras for image acquisition. The data undergoes multiple rounds of manual labeling, expert consistency checks, and reviews to ensure precise and consistent labeling. The labeling team has backgrounds in botany and agriculture and forestry, including 10 experts. Data preprocessing includes image enhancement, normalization, and label calibration, with storage format as a well-organized JPG file directory structure for easy retrieval and training.