For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
With the rapid development of the application of face recognition technology, the application of the combination of human and identification is becoming more and more extensive. In view of the fact that most of the current face recognition technologies are based on computers, the scope of use is limited, and the development cost is high. This article analyzes and studies the face detection and face recognition algorithms. In order to improve the detection speed and reduce the complexity of the algorithm, this article combines skin color segmentation and Adaboost algorithm Optimization: Pre-judge the position of the face based on the principle of skin color segmentation to determine the region of interest, avoid extracting the entire picture for face detection, and achieve the purpose of reducing the time for facial feature extraction. The experimental results show that the detection speed of the combination optimization algorithm based on skin color-Adaboost is faster than before Adaboost optimization. Finally, the face recognition is realized on the Android platform based on the PCA face recognition algorithm, and the recognition rate can reach 97.4%. The results show that the operation of the whole system of human identification and identification does not exceed 2s, which meets the real-time nature of terminal applications.
Inspec keywords: face recognition; image segmentation; principal component analysis; image colour analysis; learning (artificial intelligence); smart phones; feature extraction
Subjects: Principal component analysis; Image recognition; Mobile radio systems; Principal component analysis; Computer vision and image processing techniques; Neural nets