This paper discusses the body segment recognition based on human electromagnetic radiation frequency. Twenty-three points of human electromagnetic radiation are studied experimentally from thirty-three healthy human subjects. Three human body segments are considered, namely Left, Right and Chakra. For the purpose of recognition, k-Nearest Neighbor (KNN) algorithm is used to classify the segments of the human body. Then, the performances of classification are determined based on the accuracy and Receiving Operating Characteristic (ROC) analysis. It is found that the proposed technique accurately classifies the body segments with 100% accuracy, thus suggest that the proposed technique is significant to classify human body segments.