Ethnicity detection is a process to determine a person’s ethnic background using various facial features. It has a tremendous usage in various fields of research like personalized services and marketing, improvement in health and medicine, computer vision, facial recognition systems, security, and much more. Despite these advantages, the field faces critical challenges including ethical and privacy concerns, data bias, collection of datasets, technical limitations in image quality, legal restrictions, risk of discrimination. In this paper, we have compiled research papers of different years from varied internet resources and studied the technologies, datasets, tools and technfiques they have used. The prominent technologies include facial feature analysis, face recognition algorithms, data augmentation, synthetic data generation and deep learning models like CNNs, ResNet, Transfer learning, R-Net, etc. BUPT, CAS-PEAL, FERET, UTKFACE, FairFace, custom dataset, etc., are the most commonly used datasets. Observations indicate that deep learning approaches achieved notable accuracy levels, ranging from 90 to 98%. The following sections provide an in-depth examination of ethnicity detection using images, highlighting areas for further improvement .