Pengecaman muka telah menjadi tumpuan kajian selama dua dekad kerana potensi aplikasi yang luas dan penting untuk memenuhi keperluan keselamatan dunia sekarang. Projek ini mencadangkan satu sistem pengecaman muka yang menggunakan stereo pasif visi untuk menangkap maklumat tiga dimensi (3D) wajah dan pencocokan 3D menggunakan cara Sum of Squared Difference (SSD). Setakat ini, teknik pengecaman muka 3D yang dilaporkan menganggap penggunaan pengukuran aktif 3D untuk menangkap muka 3D. Namun, kaedah aktif menggunakan penerangan berstruktur (struktur unjuran, pertukaran fasa, demodulasi kod kelabu, dll) atau laser scanning, yang tidak disukai dalam banyak aplikasi pengecaman manusia. Kelebihan kaedah pasif adalah kosnya yang lebih rendah daripada kaedah aktif. Sistem ini menggunakan kamera stereo untuk mencari, menelusuri, dan mengecami muka seseorang. Teknik ini meningkatkan cara 2D objek pengecaman dengan mempertimbangkan permukaan wajah 3D, yang relatif stabil bawah pelbagai keadaan pencahayaan. Pertama, muka-muka dikesan dan permukaan mereka dibina daripada gambar stereo. Selepas itu, satu muka 3D dibina dengan menggabungkan data gambar 2D dan data kedalaman yang sesuai. Wajah 3D kemudian didekomposisi menjadi komponen-komponen utamanya. Komponen utama digunakan untuk pengecaman muka 3D dengan membandingkan corak muka sekarang ini dengan muka yang disimpan di dalam tabung data. Hasilnya menunjukkan cara pengecaman muka ini cekap dan tepat.
_____________________________________________________________________________________
Face recognition has been a focus in research for the last couple of decades because of its wide potential applications and its importance to meet the security needs of today’s world. This project proposes a face recognition system that uses passive stereo vision to capture three-dimensional (3D) facial information and 3D matching using a simple Sum of Squared Difference (SSD) algorithm. So far, the reported 3D face recognition techniques assume the use of active 3D measurement for 3D facial capture. However, active methods employ structured illumination (structure projection, phase shift, gray-code demodulation, etc.) or laser scanning, which is not desirable in many human recognition applications. An advantage of passive method is that it costs lower than active method. This system uses a stereo camera to locate, track, and recognize a person’s face. This algorithm improves state-of-the-art monocular 2D object recognition techniques by additionally considering the facial 3D surface, which is relatively stable under different lighting conditions. First, faces are detected and their surfaces are reconstructed from the stereo images. Afterwards, a 3D face is composed by joining 2D image data and appropriate depth data. The 3D face is then decomposed into its principal components. The principal components are used to recognize a 3D face by comparing characteristics of the current face to those of known individuals in a database. The result is an efficient and accurate face recognition algorithm.
face recognition system that uses passive stereo vision to capture three-dimensional (3D) facial information and 3D matching using a simple Sum of Squared Difference (SSD) algorithm; algorithm improves state-of-the-art monocular 2D object recognition techniques by additionally considering the facial 3D surface, which is relatively stable under different lighting conditions; active methods employ structured illumination (structure projection, phase shift, gray-code demodulation, etc.) or laser scanning,
3d facial verification using stereo vision_Tai Shu Worn_E3_2010_875003587_00003084279_NI