OrnAsia: A dataset of asian ornaments for image classification and cultural identification.

This article presents a curated dataset comprising 1088 high-resolution original images of six traditional Asian ornaments: Bangles, Rings, Earrings, Tikka, Necklaces, and Payel. The dataset was developed to support the classification and identification of culturally significant jewellery using computer vision and artificial intelligence techniques. All images were captured in real-world settings, including local markets and remote areas of Mirpur, Dhaka, Bangladesh, using smartphone cameras under natural lighting conditions. The collection process ensured variation in lighting angles, perspectives, and ornament positioning to enhance the dataset's robustness and realism. The data was organized into six distinct categories, with both training and testing subsets clearly defined to facilitate machine learning model development. Each class reflects unique visual features commonly found in ethnic accessories worn across South Asia. The dataset emphasizes diversity in design and background context, making it valuable for research in fine-grained image classification, object detection, and cultural artifact recognition. The dataset serves multiple purposes within the AI field: training deep learning models for ornament recognition, evaluating performance across different neural network architectures, and enabling the development of real-time identification systems. Its availability on a public platform (Mendeley Data) supports open research, reproducibility, and global collaboration. The structured image set can be directly reused for benchmarking classification algorithms, developing lightweight AI models suitable for mobile applications, and enriching visual datasets in cultural heritage research. It also fills a noticeable gap in ornament-related datasets, which are typically limited in scope, cultural context, and image diversity. By offering a balanced mix of traditional ornament types, verified labelling, and application-ready formats, this dataset contributes meaningfully to the advancement of AI applications in fashion technology, cultural preservation, and intelligent retail systems.