Can we ID from CCTV? Image quality in digital CCTV and face identification performance

@inproceedings{Keval2008CanWI,
  title={Can we ID from CCTV? Image quality in digital CCTV and face identification performance},
  author={Hina Uttam Keval and M. Angela Sasse},
  booktitle={SPIE Defense + Commercial Sensing},
  year={2008}
}
  • H. KevalM. Sasse
  • Published in
    SPIE Defense + Commercial…
    3 April 2008
  • Computer Science
CCTV is used for an increasing number of purposes, and the new generation of digital systems can be tailored to serve a wide range of security requirements. [] Key Method Participants compared face images taken from a high quality photographs and low quality CCTV stills, which were recorded at 4 different video quality bit rates (32, 52, 72 and 92 Kbps). We found that the number of correct identifications decreased by 12 (~18%) as MPEG-4 quality decreased from 92 to 32 Kbps, and by 4 (~6%) as Wavelet video…

Enhancing CCTV: Averages improve face identification from poor-quality images

Low‐quality images are problematic for face identification, for example, when the police identify faces from CCTV images. Here, we test whether face averages, comprising multiple poor‐quality

Video compression technique impact on efficiency of person identification in CCTV systems

Results of the paper show applicability of HEVC compression standard in the security CCTV camera systems especially in comparison with earlier widely used standards as H.264.

Face search in CCTV surveillance

Across four studies it is found that providing multiple photos of the search target consistently improves performance, and the multiple-image advantage in relation to a growing understanding of the importance of within-person variability in face recognition.

A practical end-to-end test of image quality applied to digital CCTV systems with unknown compression engines

The object was to create a technology agnostic test regime that would identify whether or not a system was above a ‘threshold resolution’ that would produce images fit for purpose.

Effective design, configuration, and use of digital CCTV

Whether CCTV is effective, and if not, how it could be made more effective is determined and a framework using a typical CCTV deployment scenario is presented, which has been validated through an expert review.

The Effect of Image Quality and Forensic Expertise in Facial Image Comparisons

The untrained participants had more false negatives and false positives than experts, which in the latter case could lead to a higher risk of an innocent person being convicted for an untrained witness.

Are facial image analysis experts any better than the general public at identifying individuals from CCTV images?

The extent to which garments affect the assessment of body shapes of males from faceless CCTV images.

Type of the wear had little effect in the description of individuals from CCTV images using the body shapes; ectomorphic component of individuals wearing black shirts and padded jackets was overestimated and underestimated, respectively.

Facial Comparison from CCTV footage: The competence and confidence of the jury.

  • H. WalkerA. Tough
  • Law
    Science & justice : journal of the Forensic Science Society
  • 2015

References

SHOWING 1-10 OF 28 REFERENCES

Face Recognition in Poor-Quality Video: Evidence From Security Surveillance

Security surveillance systems often produce poor-quality video, and this may be problematic in gathering forensic evidence. We examined the ability of subjects to identify target people captured by a

Matching the faces of robbers captured on video

Recent research has shown that unfamiliar face matching from both high- and low-quality closed circuit television video images to photographs is highly prone to error, even when viewpoint and

Can small be beautiful?: assessing image resolution requirements for mobile TV

The results show that acceptability is significantly lower for images smaller than 168x126, regardless of content type, and participants are more likely to rate image quality as unacceptable when the audio quality is high.

To be Taken at Face Value? Computerised Identification

Scientific evidence such as fingerprints and blood, hair and DNA samples are often presented during legal proceedings. Without such evidence, a description provided by the victim or any eyewitnesses

Methodology for the subjective assessment of the quality of television pictures

The ITU Radiocommunication Assembly, considering that there exists a considerable measure of agreement between the different laboratories about a number of aspects of the tests, recommends that the general methods of test, the grading scales and the viewing conditions for the assessment of picture quality, described in the following Annexes should be used for laboratory experiments and whenever possible for operational assessments.

Critical video quality for distributed automated video surveillance

There exists a sweet spot, which is term critical video quality that can be used to reduce video bit rate without significantly affecting the accuracy of the surveillance tasks, and a formal rate-accuracy optimization framework is proposed.

Identification of spatially quantised tachistoscopic images of faces: How many pixels does it take to carry identity?

Abstract Six images of human faces were quantised into isoluminant square-shaped pixels (16 grey levels) at eight different spatial levels of quantisation. The subjects had to identify the faces that

Matching identities of familiar and unfamiliar faces caught on CCTV images.

The results show that video evidence can be used effectively as a probe to identity when the faces shown are highly familiar to observers, but caution should be used where images of unfamiliar people are being compared.

Multimedia surveillance systems

A short overview of the hot topics in multimedia surveillance systems is given and some research activities currently engaged in the world are introduced at VSSN05, co-located at ACM Multimedia Conference.

Video surveillance using low bandwidth, high compression systems

The paper describes specific features in the Bath Scaleable Video codec (BSV) and the results of employing this codec in a security application are shown and the principal benefits are summarised.