Garden Flower Cleome Identification Image Dataset

In modern garden flower management, quickly and accurately identifying plant species is an important aspect. However, traditional methods often rely on human expertise, which poses challenges in identifying plants like Cleome with rich color variations. Existing computer vision solutions provide a path for automatic identification, but still face accuracy issues with small samples and variable flower morphology. Therefore, constructing a dataset specifically for Cleome identification not only enhances recognition accuracy but also has significant implications for advancements in related technologies. The dataset ensures sample diversity and coverage by using high-resolution cameras to collect data in various garden environments. Quality control involves multiple rounds of annotation and consistency checks, with a professional team from the field of botany conducting reviews, resulting in the annotation of over 3,000 images. Image data is enhanced and normalized to improve model training effects and stores in scene-separated structures in JPG format. The dataset's annotation consistency exceeds 95%, ensuring highly efficient recognition.