<![CDATA[The facial recognition process is normally used to verify and identify individuals, especially during the process of analyzing facial biometrics. The face detection algorithm automatically determines the presence or absence of a face. It is, however, theoretically difficult to analyze the face of a system with limited resources due to the complex pattern of a face. This implies an embedded platform scheme which is a combination of several learning methods supporting each other is required. Therefore, this research proposed the combination of the Haar Cascade method for the face detection process and the WNNs method for the learning process. The WNNs face recognition Algorithm (WNNs-FRA) uses facial data at the binary level and for binary recognition. Moreover, the sample face data in the binary were compared with the primary face data obtained from a particular camera or image. The parameters tested in this research include detection distance, detection coordinates, detection degree, memory requirement analysis, and the learning process. It is also important to note that the RAM node has 300 addresses divided into three face positions while the RAM discriminator has three addresses with codes (00), (10), and (10). Meanwhile, the largest amount of facial ROI data was found to be 900 pixels while the lowest is 400 pixels. The total RAM requirements were in the range of 32,768 bytes and 128 bytes and the execution time for each face position was predicted to be 33.3% which is an optimization because it is 66.67% faster than the entire learning process]]>
Copyrights © 2022
