Global service

Easy to integrate

Customer support

RecogX - A complete cross-industry solution


Events Management



Law Enforcement's



The RecogX robust face APIs allow you to easily integrate face recognition with a variety of third-party systems, creating complete face integrated identification and authenticating solutions.

Contact less Verification

Face recognition based access control systems can be helpful in providing contactless biometric verification for providing access to sensitive locations to authorized people. For example sensitive military installations, schools, government offices, airports, gated societies etc.

Attendance Management

Today’s dynamic business environment requires real-time access control solution with anytime,time-attendance and anywhere access. The existing biometric credentials used for authentication faces some challenges in identification due to various biometric changes and extreme weather condition effect on biometrics. Face recognition based attendance management can help registering attendance.

Find Missing Persons

Face recognition can be used to find missing children and victims of human trafficking. As long as missing individuals are added to a database, law enforcement can become alerted as soon as they are recognized by face recognition—be it an airport, retail store or other public space.

Catch Fake Identities

Immigration control can easily catch fake passport holders through face recognition. If passport control implements face recognition and verifies the face of the person with his photo on the passport, the face recognition system can match the photo on the passport with the person holding it and verify the person’s identity.

Instant Actionable Intelligence

Face recognition can become a great tool for the security forces as it can help identifying the movement of the criminals in public places in realtime and single them out in the crowd and provide actionable intelligence to security forces to help them take specific action.

Retail Store Analytics

By integrating store loyalty programs with face, the offline retail stores can create better shopping experience for their loyal customers by providing them customised retailing experience based on their specific buying choices and at the same time benefit from the in-store analytics for better product pricing and placement strategies.

System Process

Face detection

Detect faces within images, and get high-precision face location rectangles.


Face landmarks

Identify, match, and get full raw landmarks for any face.

Face comparing

Compute the similarity of two faces, and return a confidence score and thresholds to evaluate the similarity.

Face searching

Find similar faces to a new face from a given collection of faces, along with confidence scores and thresholds to evaluate the similarity.

Recogx System Features

Our biometric face recognition system performs fast and accurate detection of multiple faces in live video streams and still images. All faces on the current frame are detected in 0.07 sec. and then each face is processed in 0.13 sec.

A conventional face identification system can be easily cheated by placing a photo of another person in front of a camera. Our face recognition system is able to prevent this kind of security breach by determining whether a face in a video stream belongs to a real human or is a photo.

A quality threshold can be used during face enrolment to ensure that only the best quality face template will be stored into database.
Our face recognition system has certain tolerance to face posture that assures face enrolment convenience: rotation of a head can be up to 10 degrees from frontal in each direction (nodded up/down, rotated left/right, tilted left/right)
Biometric template record can contain multiple face samples belonging to the same person. These samples can be enrolled with different face postures and expressions, from different sources and in different time thus allowing to improve matching quality.
Our system functions can be used in 1-to-1 matching (verification), as well as 1-to-many mode (identification).