scholarly journals REAL TIME FACE DETECTION AND RECOGNITION SYSTEM USING HAAR CASCADE CLASSIFIER AND NEURAL NETWORKS

2021 ◽  
Vol 9 (1) ◽  
pp. 224-231
Author(s):  
Anirban Chakraborty, Shilpa Sharma

Home protection and privacy have become one of the most critical aspects in today's world. As technology progresses at an exponential pace, the times are not far ahead for each house to be fitted with sophisticated security systems to deal with regular burglary and theft. But as one side of the tech progresses, so do its detrimental counterparts. DES encryption can be an indicator of how easily an encrypted piece of information can be deciphered. Not long after its release, DES encryption was referred to as 'unsafe' and with today's modern application, anything like DES might be an open invitation to hack. With many developments in the field, the technology has, in many respects, surpassed the use of biometrics (finger prints). Face recognition, nowadays, is present in almost every smart device that has some piece of information stored that holds importance to its users. With facial recognition gaining popularity, many tech companies have come with their own patent to make a technology related to Facial Recognition on the market. This paper suggests a somewhat related concept as to how home protection can be improved by using a face detection and recognition algorithm (Haar Cascade Classifier).

2016 ◽  
Vol 7 (3) ◽  
Author(s):  
Fadli Sirait ◽  
Yoserizal Yoserizal

Teknologi biometrik adalah teknologi untuk mengindetifikasi mahluk hidup. Tujuan perancangan  adalah  untuk  membangun  sistem  pendeteksi  wajah  dari  objek  citra  yang  didapat dari  gambar  frame  video  melalui  kamera.  Kemudian  dilakukan  pendeteksi  pola  wajah  yang dikenali  dan  mencari  kemiripan  terhadap  database  model  wajah  menggunakan  Raspberri  Pi berbasis  penggunaan  perangkat  lunak  Free  dan  Opensource.  Perancangan  ini  menggunakan metode  pengenalan  objek  citra  wajah  dengan  Haar  Cascade  Classifier  yang  diimplentasikan pada libarary OpenCV, sedangkan metode pengenalan pola wajah dengan menggunakan analisa PCA (Principal Component Analysist) dan LDA (Linear Discriminant Analysis) menggunakan pemograman  prerangkat  lunak  yang  dibuat  berbasis  Python.  Perangkat  lunak  yang dikembangkan  juga  dijalankan  pada  sistem  operasi  berbasis  Linux  Raspbian  (Jessie  dan Wheezy)  yang  diinstal  di  Raspberry  Pi.  Proses  input  citra  menggunakan  USB  kamera  yang dipasang  pada  Raspberry  Pi  2  Model  B  yang  dilengkapi  dengan  LCD  3,5  inchi.  Berdasarkan data pengujian terhadap 127 input didapat tingkat akurasi untuk pendeteksian satu objek wajah 84-97% sementara performa penggunaan CPU pada Raspberry Pi 41.87-46.25%.Kata kunci: face detection and recognition, Raspberry pi, pengolahan citra, embedded system.


2014 ◽  
Vol 9 (10) ◽  
Author(s):  
Peiyi Shen ◽  
Liang Zhang ◽  
Juan Song ◽  
Hu Xu ◽  
Lianjie Qin ◽  
...  

1997 ◽  
Author(s):  
Manesh B. Shah ◽  
Nageswara S. V. Rao ◽  
Victor Olman ◽  
Edward C. Uberbacher ◽  
Reinhold C. Mann

Author(s):  
MANUEL GÜNTHER ◽  
ROLF P. WÜRTZ

We present an integrated face recognition system that combines a Maximum Likelihood (ML) estimator with Gabor graphs for face detection under varying scale and in-plane rotation and matching as well as a Bayesian intrapersonal/extrapersonal classifier (BIC) on graph similarities for face recognition. We have tested a variety of similarity functions and achieved verification rates (at FAR 0.1%) of 90.5% on expression-variation and 95.8% on size-varying frontal images within the CAS-PEAL database. Performing Experiment 1 of FRGC ver2.0, the method achieved a verification rate of 72%.


Sign in / Sign up

Export Citation Format

Share Document