Four Biometric Parameters

Solution Preview

I have explained the various types of biometric parameters used in identifying individuals, their limitations and applications in criminal investigation. **Attachment- MS Word version.

FACIAL RECOGNITION

Spatial geometry of distinguishing features of the face are recorded in an automated method by facial recognition biometric. A computer application verifies a person from a digital image or a video frame from a video source. Facial databases exists which are used to compare facial features captured from a CCTV or video to identify a suspect. Facial recognition has been used in projects designed to identify card counters in casinos, shoplifters in stores, criminals in targeted urban areas, and terrorists overseas.

Advantages
- No contact required
- Commonly available sensors (cameras)
- Large amounts of existing data to allow background and/or watchlist checks
- Easy for humans to verify results

Disadvantages
- Face can be obstructed by hair, glasses, hats, scarves, etc.
- Sensitive to changes in lighting, expression, and pose
- Faces change over time
- Propensity for users to provide poor-quality video images yet to expect accurate results

Limitations:
There is lot of variability in the face recognition process that's why face recognition is considered relatively inaccurate. This is due to changes that occur to people over time, like ageing, or simply related to external environmental conditions (poses, facial expressions, illumination, textured background). Recording conditions varies the methods performance a lot. A leading biometrics expert Dr. James L Wayman believes facial recognition is still in its infancy and needs lot of improvement but the technology hold immense potential to emerge as a very useful biometric technique. Dr. Wayman has noted that subjects should ideally be photographed under tightly controlled conditions. For example, each subject should look directly into the camera and fill the area of the photo for an automated system to reliably identify the individual or even detect his face in the photograph. Thus, while the technology for facial recognition systems shows promise, it is not yet considered fully mature.

Criminal Investigation purposes:

- Facial recognition is providing good investigative leads, and will only get better as the technology improves.
- Although crime-based TV shows sophisticated facial recognition softwares but the reality is not so perfect. The facial softwares at best are 80% accurate as evidenced from the wide range search launched by FBI in the year 2014 which involved face recognition of suspects from ~15 million mug shots.
- But the ...