Gender and race classification using geodesic distance measurement

<span lang="EN-US">Gender and ethnicity classifications are a long-standing challenge in the face recognition’s field. They key-demographic traits of individuals applied real-world applications such as biometric demographic research, human-computer interaction (HCI), law enforcement online advertisements. Thus, many methods have been proposed to address gender or/and race achieved various accuracies. This research improves classification by employing geodesic path algorithm extract discriminative features both ethnicity. PCA is also utilized for dimensionality reduction Gender-feature race-feature matrices. KNN SVM used classify extracted feature. was tested on recognition technology (FERET) dataset, with results demonstrating high-level performance (100%) distinguishing ethnicity.</span>