Application of Multiscale Facial Feature Manifold Learning Based on VGG‐16

Abstract

Purpose. In order to solve the problems of small face image samples, high size, low structure, no label, and difficulty in tracking and recapture in security videos, we propose a popular multiscale facial feature manifold (MSFFM) algorithm based on VGG16. Method. We first build the VGG16 architecture to obtain face features at different scales and construct a multiscale face feature manifold with face features at different scales as dimensions. At the same time, the recognition rate, accuracy rate, and running time are used to evaluate the performance of VGG16, LeNet-5, and DenseNet on the same database. Results. From the results of comparative experiments, it can be seen that the recognition rate and accuracy of VGG16 are the highest among the three networks. The recognition rate of VGG16 is 97.588%, and the accuracy is 95.889%. And the running time is only 3.5 seconds, which is 72.727% faster than LeNet-5 and 66.666% faster than DenseNet. Conclusion. The model proposed in this paper breaks through the key problem in the face detection and tracking problem in the public security field, predicts the position of the face target image in the time dimension manifold space, and improves the efficiency of face detection.

Klasifikasi Kinship Keluarga Hollywood Dengan Metode Visual Geometry Group-Support Vector Machine

“…VGG-16 dapat menggunakan banyak data untuk diproses seperti model VGG-16 [7] [8]. VGG-16 juga dapat digunakan untuk mendeteksi, mendeteksi, dan mengekstrak fitur wajah manusia dengan akurasi 96% hingga 95,89% [9] [10].…”

“…Dari seluruh penelitian seputar CNN, dapat disimpulkan bahwa metode VGG-16 dapat mendeteksi fitur wajah dan membedakannya dari berbagai kondisi seperti jenis kelamin, ras, dll. VGG-16 juga memiliki waktu komputasi yang cepat dibandingkan dengan arsitektur lain, yaitu 3,5 detik [10] Support Vector Machine (SVM) adalah metode klasifikasi data yang menentukan data mana yang diproses menjadi kelas tertentu [13]. Perbandingan metode klasifikasi tersedia dalam penelitian [9] menggunakan metode SVM, Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Decision Tree (DT) dan Logistic Regression (LR).…”