Face Identification Systems

Question 1

Types of Face Identification Systems

Problem?

Answer 1

Identikit, Photofit, sketching, computer systems (e.g. Identikit 2000, FACES 3.0, E-Fit, Evo-Fit).

Problem: usually poor at producing recognisable likenesses.

Question 2

Ellis, Shepherd and Davies (1975): First and Second Experiment

Answer 2

First experiment:
Subjects saw two Photofit faces.
Reconstructed them using Photofit - very difficult, even when the target Photofit face was present.

Second experiment:
Subjects saw 6 faces: produced Photofits of them from memory, immediately afterwards.
A second group tried to use these Photofits to identify the 6 original faces from a set of 36 faces.
Chance matching performance = 3% (1 in 36).
Actual success rate was 12.5% - better than chance, but very poor.

Question 3

Ellis, Shepherd and Davies (1978): Compared Photofit to Free hand sketching

Answer 3

Sketches were better than Photofits if the target face was physically present.
Photofit was better when the target was reconstructed from memory.

Sketches were “child-like in their simplicity and bore only a vague approximation to the original target faces” - Photofits rated little better!

Question 4

Frowd et al (2005, 2007): forensically-relevant evaluations:

Answer 4

2005: compared Photofit, E-Fit, Pro-Fit, Evo-Fit.
Witness makes composite of a famous face that is unknown to them.
Police procedures followed, plus realistic delay between seeing face and making composite.
Different participant tries to identify the famous face (known to them).
Various measures - spontaneous naming most relevant.
E-Fit and Pro-Fit best, but only 20% of composites were recognised.

2007: compared E-Fit, Identikit 2000, FACES 3.0. Only two out of 480 composites could be spontaneously identified.

Question 5

Why is FRS performance so poor?

Answer 5

1. Limitations in eyewitnesses themselves.
2. Equipment limitations (restricted feature-sets).
3. Interference effects from Photofit features.
4. Problems in method of construction (verbal mediation issues).
5. Inappropriate “feature-based” theoretical basis (Penry 1971), at odds with the “configural-based” processing actually used for face recognition.

Question 6

Cheque cards with photographs: (Kemp, Towell and Pike 1999).

ID cards: (Bindemann and Sandford (2011):

Answer 6

1) Cashiers poor at detecting mismatches between user and photo on card.
Falsely accepted over 50% of fraudulent cards.
Falsely rejected over 10% of legitimate ones.

2) For each ID card, participants tried to pick target face from 30 photos.
67% correctly matched ID1, 46% ID2, 58% ID3.
Only 38% correctly matched target to all three IDs - i.e. most participants thought the ID cards showed three different people.
When told the 3 ID cards showed the same person, 85% correctly identified the target face.

Question 7

Recognition in surveillance videos: (Burton, Wilson, Cowan and Bruce 1999).

Answer 7

Subjects judged whether faces seen in high-quality photos had been seen before in video clips.
Subjects personally familiar with the targets performed well; subjects unfamiliar with them performed poorly.

Question 8

Problems with the method of construction: Hall and Christie and Ellis

Answer 8

Verbal description and Photofit construction are sequential, feature-by-feature processes, unlike face representations.

Hall (1976):
Making verbal descriptions of a face to a sketch artist impaired subsequent recognition of the described face.

Christie and Ellis (1981):
No correlation between rated quality of a subject’s Photofit constructions and the quality of their verbal descriptions.

Question 9

Verbal overshadowing:

Answer 9

1) Verbally describing a face may impair subsequent recognition of that face - and others (Schooler and Engstler-Schooler 1990; Meissner and Brigham 2001).
2) Elaborative description produces more overshadowing (Meissner and Brigham 2001).
3) Effects cross semantic categories: e.g. describing a face impairs car recognition (but not vice versa) (Brown and Lloyd-Jones 2003).
4) Verbal description encourages inappropriate processing strategies, which hinder retrieval of face-appropriate information.

Question 10

The Thatcher illusion

Answer 10

Inversion reduces sensitivity to configural information…

Recognition survives loss of featural information (due to blurring or pixellation)

Question 11

The composite face effect: (Young, Hellawell and Hay 1987).

Answer 11

Upright faces are processed in an integrated “holistic” way, that prevents easy access to their constituent features.
Inversion abolishes this effect.

Question 12

“Whole over part” advantage:

Answer 12

Features are recognised better if they are presented within a whole face than if presented in isolation or within a scrambled face (Tanaka and Farah 1993).

Question 13

The Bruce and Young (1986) model of face processing:

Answer 13

Structural encoding:
Based on features, and their configuration (spatial relationship)
Face Recognition Unit:
Activated by a match to a stored face representationPerson Identity Node:
Contains semantic information about the person
Name Generation

Question 14

Familiar and unfamiliar face recognition are qualitatively different:

Answer 14

But - familiar faces recognised better from internal features, unfamiliar faces from external features.
(Ellis, Shepherd and Davies 1979; Young, Hay, McWeeny, Flude and Ellis 1985).

Question 15

Ways to improve the recognisability of composites:

Answer 15

1. Using multiple composites to aid recognition
2. Improved composite systems
3. Using multiple techniques can improve recognition