Image analysis – Applications – Personnel identification
Reexamination Certificate
2002-12-03
2004-04-06
Patel, Jayanti K. (Department: 2625)
Image analysis
Applications
Personnel identification
C348S164000, C348S169000
Reexamination Certificate
active
06718049
ABSTRACT:
BACKGROUND OF THE INVENTION
The present invention pertains to detection systems and methods. More particularly, the present invention pertains to detection systems and methods using the near-infrared spectrum for the detection of, for example, disguised persons.
In certain situations, disguise detection is of paramount importance. For example, in high-end security applications, e.g., surveillance of an embassy perimeter where there is a need to know if disguised terrorists are staking out a facility, disguise detection is required. Sophisticated systems for early detection and identification of individuals at a distance need to be developed and implemented for future security systems.
Sophisticated terrorists use both natural (e.g., darkness, weather, blending into the background) and man-made (e.g., heavy make-up, artificial face parts, add-on hair, etc.) deception and disguise techniques to avoid identification. Currently, systems that can determine whether an individual is wearing a facial disguise are lacking. Therefore, face identification processes and systems that have the capability to identify a particular human face cannot even be initiated, or even if such processes are initiated, the processes do not know of the possible disguise being used by the individual. Therefore, the face identification processes are easily rendered ineffective. As such, the mere detection of a disguised individual on the perimeter is highly valuable to security forces.
One article entitled “Disguise detection and identification using infrared imagery,” by F. J. Prokoski,
Proceedings of SPIE, Optics, and Images in Law Enforcement II
, A. S. Hecht, Ed., Arlington, pp. 27-31, Virginia, May 1982, describes a disguise detection system that uses facial thermograms in the thermal infrared spectrum for the detection of disguises and in positive identification of known individuals. However, thermal infrared radiation does not transmit effectively through glass, e.g., so as to allow for detection of disguises within vehicles.
Other portions of the spectrum are also ineffective for use in disguise detection. For example, even though the visible spectrum has been used in imaging and detecting individuals, such visible spectrum systems or methods are not effective for disguise detection. Disguises cannot be detected in the visible band because by definition such disguises are meant to cheat the human eye and the other sensors that operate in the same wavelength. In other words, in the visible spectrum, artificial materials disguising an individual are not detectable.
Further, for example, the lower portion of the electromagnetic spectrum consists of gamma rays, x-rays, and radiation in the ultra-violet range. Radiation of such wavelengths is harmful. Thus, such radiation that is typically useful in a controlled manner, e.g., for medical applications, cannot generally be used for disguise detection.
At the far end of the electromagnetic spectrum, there is microwave and radio radiation. This range of the spectrum has recently started to be exploited for imaging purposes. Sensors operate in an active or in passive mode. The major advantage of such longer wavelengths is that they can penetrate clouds, fog, and rain for producing weather independent imaging results. However, the technology for such wavelengths is new and prohibitively expensive. Also, the sensors available for detection in this range of radiation are extremely large and have very low resolution.
Related efforts by others, for example, in the field of detecting occupants in vehicles, such as for gathering statistics in high occupancy vehicle lanes which can be used for road construction planning, have involved the use of a near-infrared camera (i.e., in the range of 0.55 to 0.90 micron) and a near-infrared illumination source in the same range of wavelengths. One reason for using near-infrared sensing is the ability to use non-distracting illumination at night. Illumination at nighttime enhances the quality of the image. However, it appears that this choice of range of wavelengths is not appropriate because of its close proximity to the visible spectrum. Experiments have shown that the human eye has some sensitivity to this range of near-infrared wavelengths, however small. Another reason for this approach, was to bypass problems caused by solar illumination during daytime, such as glare from glass of vehicles. Nevertheless, particularly in this range of the spectrum (i.e., 0.55 to 0.9 micron) solar illumination is still substantial and the associated glare can be reduced only through the use of polarizing filters.
Further, in more general terms, related art projects that involve imaging usually adopt the use of visible spectrum cameras which as described above, are ineffective in disguise detection. One strong point of the visible spectrum is that the relevant imaging sensors are very advanced and at the same time very economical. Visible spectrum cameras have a particular advantage in terms of speed, which is an important consideration, for example, in detecting occupants in vehicles, where vehicles are moving at rates of speed of 65 mph. These cameras can also have very high resolution, resulting in very clear images under various conditions. However, unfortunately, in addition to not detecting disguised individuals, there are other serious problems with the visible spectrum approach. For instance, some vehicles have heavily tinted window glass to reduce glare from solar illumination. This glass is nearly opaque to visible spectrum cameras. Also, visible spectrum cameras do not have operational capability during nighttime.
Visible spectrum or very near infrared detection of people in vehicles has not been very successful under most conditions. The glare and other problems caused by solar illumination, such as through vehicle windows, has prevented effective detection of vehicle occupants. Also, environmental conditions like weather obscure detection. People appear to have darker or lighter faces, depending on the characteristics of the people being detected, and on the incident angle and intensity of deliberate or incidental illumination.
SUMMARY OF THE INVENTION
Various embodiments of the present invention provide solutions to one or more problems existing with respect to detection systems and methods, and in particular disguise detection systems and methods. Such embodiments may provide one or more of the following advantages. For example, disguised faces may be detected within vehicles through window glass thereof. Further, the present invention provides a simple thresholding system that can deliver excellent disguise detection results. In addition, the existence of specific materials used for disguise purposes may be identified.
The present invention capitalizes on the unique and universal properties of the natural human skin and/or natural human hair in the upper band of the near-infrared spectrum. Some embodiments of the methods according to the present invention include one or more of the following: detecting reflection from at least one portion of a head of a human body in at least a portion of an upper band of the near-infrared spectrum (e.g., at least a portion within the range of 1.4 &mgr;m and greater in the upper band of the near-infrared spectrum); determining the presence of an artificial material associated with the head of the human body based on the detected reflection; detecting reflection from at least a skin portion of the head of the human body; detecting reflection from at least a hair portion of the head of the human body; determining the presence of an artificial material associated with the head of the human body by displaying to a user a representation of the detected reflection; determining the presence of an artificial material associated with the head by generating data representative of the detected reflection and comparing the data to at least one threshold reference reflection level; identifying one or more artificial materials associated with the head; basing the threshold reference reflection level(s) o
Fritz Bernard S.
Pavlidis Ioannis
Symosek Peter F.
Fredrick Kris T.
Honeywell International , Inc.
Patel Jayanti K.
Tabatabai Abolfazl
LandOfFree
Near-infrared disguise detection does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Near-infrared disguise detection, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Near-infrared disguise detection will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3213896