Software for Biometric Facial Image Autocapture with Quality Analysis and Compliance Assurance

Facial biometric matching is used to verify the identity of individuals attempting access for various border management and access control applications. Facial matching algorithms make use of digital photographs of the face stored in a database or on an ID card. These digital images are captured upon registration into the system, and then compared to a live photo of the individual upon an access attempt in a process called “matching”. The performance of the matching algorithm can be improved—that is, the occurrence of false matches and false accepts can be reduced—if the quality of the facial images can be maximized. For this reason, new standards for biometric facial images specify normative requirements for facial image quality, and also provide best practices for biometric facial image capture.

In environments where automated facial matching is not yet in use, it can still be useful to aid human visual matching and automate the process of facial photo capture. It is also useful to locate facial features such as eye locations and store them with the image for future use or for use by recipients of the data. 

Aware’s PreFace software development kit (SDK) performs several functions to analyze biometric facial images and then either notify an operator of non-compliant features of the image or automatically correct the image where possible.   PreFace is intended for integration into enrollment and ID personalization applications to:

• ensure compliance of facial images with ANSI/INCITS 385-2004 and ISO/IEC 19794-5 biometric data interchange format standards
• maximize the visual quality of biometric facial images improve performance of the facial image in matching applications by screening non-compliant images upon capture
• help automate photo capture and improve operational efficiency of the process

PreFace functionality includes:

• Eyes, nose and mouth

• eye contrast
• facial brightness
• facial dynamic range
• background uniformity
• background gray %
• inter-eye resolution
• eye axis
• image size
• head size
• blurriness
• eye glasses
• pose angle
• smile/teeth
• eye-obstruction (dark glasses)
  

• Image dimensions
• Resolution adjustment
• Horizontal eye positioning
• Head orientation and size in frame
• Background color selection

Compression

• JPEG
           
• JPEG2000
           
• JPEG2000 with region of interest (ROI)