Real-Time Face Recognition from Surveillance Video

Davis, Michael; Popov, Stefan; Surlea, Cristina

doi:10.1007/978-3-642-17554-1_8

Cited by 9 publications

(5 citation statements)

References 26 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The low quality video coupled with the large variations in the subjects face orientations in the acquired video decreases the recognition accuracy. Various techniques have been proposed for face recognition for surveillance application [3,4,5], which can be classified into two groups: software and hardware based techniques. One of the problems with face recognition for surveillance is that data often acquired from different video sources and in different configurations.…”

Section: Introductionmentioning

confidence: 99%

The Effect of Training Data Selection on Face Recognition in Surveillance Application

Dargham

Chekima

Moung

et al. 2015

Distributed Computing and Artificial Intelligence, 12th International Conference

View full text Add to dashboard Cite

Abstract.Face recognition is an important biometric method because of its potential applications in many fields, such as access control and surveillance. In surveillance applications, the distance between the subject and the camera is changing. Thus, in this paper, the effect of the distance between the subject and the camera, distance class, the effect of the number of images per class, and also the effect of database used for training have been investigated. The images in the database were equally divided into three classes: CLOSE, MEDIUM, and FAR, according to the distance of the subject from the camera.

show abstract

Section: Introductionmentioning

confidence: 99%

The Effect of Training Data Selection on Face Recognition in Surveillance Application

Dargham

Chekima

Moung

et al. 2015

Distributed Computing and Artificial Intelligence, 12th International Conference

View full text Add to dashboard Cite

show abstract

“…Issues related to the face recognition in real-time monitoring systems can be found in paper [8]. The authors of this paper conclude that most of the techniques of the identification systems capture a full-frontal image of the face.…”

Section: Related Workmentioning

confidence: 90%

“…Face recognition from a video stream is a more difficult task, because the system has to be resistant to changes in illumination, scale (size) of pictures, and face position. A solution proposed in article [8] is the use of the OpenCV Face Detector, which implements the technique proposed by Viola-Jones. The detection process can also be realized by the detection of the skin color.…”

Section: Related Workmentioning

confidence: 99%

Influence of low resolution of images on reliability of face detection and recognition

Marciniak

Chmielewska

Weychan

et al. 2013

Multimed Tools Appl

View full text Add to dashboard Cite

In this paper we analyze reliability of the real-time system for face detection and recognition from low-resolution images, e.g., from video monitoring images. First, we briefly describe main features of the standards for biometric face images. Available scientific databases have been checked for compliance with these biometric standards. During the research we have considered both the correctness of extraction (location) of the face from the image as well as the correctness of the identification (based on the eigenfaces approach). To the tests we have used the face databases that allow to study tolerance to illumination and face positions. We have compared various face detection techniques and analyzed minimum requirements for the resolution of facial images. Finally, an influence of the resolution reduction on the FAR/FRR of the recognition is presented.

show abstract

“…• Surveillance: most face recognition applications are aimed to reinforce the security, mainly due to its versatility [23,35]. The most common applications are advanced video surveillance or CCTV systems in public cluttered places where suspect people have to be localized, detected and tracked; other surveillance applications cover the issue of avoiding potential robberies (i.e.…”

Section: Face Recognition: Definition and Applicationsmentioning

confidence: 99%

“…In this normalized face, the left and right eye-candidates are located in fixed positions, r(x, y) = (25,35) and l(x, y) = (100, 35), respectively, establishing an interocular distance of iod = 75 pixels.…”

Section: Generation and Normalization Of Face-candidatesmentioning

confidence: 99%

Contributions on Automatic Recognition of Faces using Local Texture Features

Ferrer¹

View full text Add to dashboard Cite

A mi familia, por su apoyo incondicional Siempre fuiste mi espejo; para verme sólo tenía que mirarte.Julio Cortázar AcknowledgmentsThis work is not only the result of all my efforts but a consequence of the many supports and useful advices that I received.To my parents and my brothers. The pillar of my education and unconditional support.To my friends. They patiently released me from the hardest moments and continuously encouraged me to go on.To all the people of the old and new Clementine. We shared the most time of this Thesis between hours of work and laughs.To the people of Visual. In their eyes, they always saw me as a doctor.To Alberto, Antonio and Jorge. They offered me the opportunity of developing this work and pushed me into the field of Computer Vision. ResumenUno de los temas más destacados del área de visión artificial se deriva del análisis facial automático. En particular, la detección precisa de caras humanas y el análisis biométrico de las mismas son problemas que han generado especial interés debido a la gran cantidad de aplicaciones que actualmente hacen uso de estos mecanismos.En esta Tesis Doctoral se analizan por separado los problemas relacionados con detección precisa de caras basada en la localización de los ojos y el reconocimiento facial a partir de la extracción de características locales de textura. Los algoritmos desarrollados abordan el problema de la extracción de la identidad a partir de una imagen de cara (en vista frontal o semi-frontal), para escenarios parcialmente controlados. El objetivo es desarrollar algoritmos robustos y que puedan incorporarse fácilmente a aplicaciones reales, tales como seguridad avanzada en banca o la definición de estrategias comerciales aplicadas al sector de retail.Respecto a la extracción de texturas locales, se ha realizado un análisis exhaustivo de los descriptores más extendidos; se ha puesto especial énfasis en el estudio de los Histogramas de Gradientes Orientados (HOG features). En representaciones normalizadas de la cara, estos descriptores ofrecen información discriminativa de los elementos faciales (ojos, boca, etc.), siendo robustas a variaciones en la iluminación y pequeños desplazamientos.Se han elegido diferentes algoritmos de clasificación para realizar la detección y el reconocimiento de caras, todos basados en una estrategia de sistemas supervisados. En particular, para la localización de ojos se ha utilizado clasificadores boosting y Máquinas de Soporte Vectorial (SVM) sobre descriptores HOG. En el caso de reconocimiento de caras, se ha desarrollado un nuevo algoritmo, HOG-EBGM (HOG sobre Elastic Bunch Graph Matching). Dada la imagen de una cara, el esquema seguido por este algoritmo se puede resumir en pocos pasos: en una primera etapa se extrae un grafo facial ubicando automáti-camente los puntos más significativos de la cara; de cada uno de estos puntos, se extrae un descriptor local HOG y se concatenan. Finalmente, el vector de características biométricas pasa por una etapa de reducción de dimensionalidad. Al vector resultante...

show abstract

Real-Time Face Recognition from Surveillance Video

Cited by 9 publications

References 26 publications

The Effect of Training Data Selection on Face Recognition in Surveillance Application

The Effect of Training Data Selection on Face Recognition in Surveillance Application

Influence of low resolution of images on reliability of face detection and recognition

Contributions on Automatic Recognition of Faces using Local Texture Features

Contact Info

Product

Resources

About