The security industry has entered the "digital era" from the "analog era", and has entered the "network era" from the "digital era". In 2011, the security industry officially entered the "smart" era. The intelligent application of the combination of face recognition access control systems and security technology has vigorously promoted the arrival of a new era.

Face recognition is a kind of biometric identification technology based on the facial feature information of people. Use a camera or camera to collect images or video streams containing human faces, and automatically detect and track human faces in the images, and then perform a series of face-related technologies on the detected human faces, usually also called face recognition and facial recognition.

The face is innate like other biological characteristics of the human body (fingerprints, iris, etc.). Its uniqueness and good characteristics that are not easy to be copied provide the necessary prerequisites for identity authentication. Compared with other types of biometrics, face recognition Has the following characteristics:

　　 Non-mandatory: The user does not need to specifically cooperate with the face acquisition equipment, and can obtain face images almost unconsciously. This sampling method is not "mandatory";

　　 Non-contact: The user can obtain facial images without direct contact with the device;

　　 Concurrency: in actual application scenarios, multiple faces can be sorted, judged, and recognized;

　　 In addition, it also conforms to the visual characteristics: the characteristics of "recognizing people by appearance", and the characteristics of simple operation, intuitive results, and good concealment.

　　 The face recognition system mainly includes four components, namely: face image acquisition and detection, face image preprocessing, face image feature extraction, and matching and recognition.

Face recognition system

The advantage of face recognition lies in its naturalness and the characteristic that it cannot be detected by the individual.

　　 The so-called naturalness means that the identification method is the same as the biological characteristics used by humans (or even other living beings) for individual identification. For example, in face recognition, humans can distinguish and confirm identities through observation and comparison. In addition, natural recognition includes iris recognition, voice recognition, body shape recognition, etc., while fingerprint recognition and iris recognition are not natural, because humans Or other creatures do not distinguish individuals by such biological characteristics.

　　The characteristic of being undetected is also very important for an identification method, which makes the identification method not objectionable, and because it is not easy to attract people's attention, it is not easy to be deceived. Face recognition has this feature. It completely uses visible light to obtain facial image information. Unlike fingerprint recognition or iris recognition, it needs to use an electronic pressure sensor to collect fingerprints or use infrared to collect iris images. These special collection methods are easy Being noticed by others makes it more likely to be disguised and deceived.

The face recognition system with security technology is mainly different from the traditional face recognition system in four aspects: First, most of the face recognition systems used in the security industry are dynamic recognition, which uses surveillance cameras to dynamically collect real-time images to communicate with the database. The pre-stored models are compared, and then the alarm plan is activated in real-time; while most traditional biometric recognition systems use static pictures to compare with the models in the database, showing similar results. Second, the system combined with security technology has inherent compatibility with the security monitoring system and can be seamlessly connected with traditional video monitoring systems and alarm systems to avoid repeated investment by customers. Third, the face recognition system combined with security technology inherits various security precautions and alarm plans originally possessed by the security industry. Fourth, the application environment of the security industry is complex, so the face recognition system used in the security industry must have good adaptability to natural light. Traditional face recognition using near-infrared technology is difficult to apply in the security field. Therefore, in order to get a better application in the security industry, professional optimization must be combined with the characteristics of the security industry.

So which areas of the security industry currently need face recognition systems? At present, the security industry’s most urgent need for face recognition systems is mainly in three aspects: 1. The pursuit of suspects, such as the key street bayonet in the "Safe City" project Portrait deployment, chase and escape of suspects at train stations and bus stations, etc. 2. Security identity verification in important places, such as high-level VIP clubs, important conference venues, prisons, smart high-end communities, etc. 3. Places that need to be able to obtain evidence and quickly locate afterward, such as bank counters, ATMs, etc., through the establishment of face index, to quickly, accurately, and clearly obtain the video, and obtain the physical characteristics of the main characters.

When a stranger enters your community, the security will immediately make necessary inquiries, and the resident security of your own community will let it go without interference; when a major case occurs in a city, as long as there is a photo of the person, the train station, and the bus station Cameras on important streets will become security guards for automatic patrols, just waiting for the arrest of the suspect; when you need to inquire about an important video, you no longer have to bury your head in shifts for days and keep staring at the massive data. It can be viewed in seconds, and the retrieval conditions indexed by the image of the person can quickly guide you to the specific location of the event. Face recognition has entered all aspects of security and will further push security into the "smart" era.

Author: Written by Mr.Andy Zhang from S4A INDUSTRIAL CO.,LIMITED