Skip to main content

Advertisement

SpringerLink
Log in

Facial composite systems: review

  • Published:
Artificial Intelligence Review Aims and scope Submit manuscript

Abstract

In criminal investigation, a facial composite refers to a portrait of a sought unknown individual created by a forensic technician based on the memory of the eye-witness. Despite the use of computerised techniques in order to construct a composite image, until recently, the recognition rate on the basis of the offender’s portrait was very low. Although different software solutions were proposed, the main principles of the construction process remained the same since manual sketching. The process still relied on the detailed description of offenders and their individual features with the purpose of merging the individual features together in order to create a final portrait. Extensive psychological research, and inclusion of its results into the facial composite procedure has led to the development of “holistic” systems which enable much more efficient identification of individuals utilising facial composites. This paper compares the techniques used for the construction of composites, summarises psychologically—criminological research on human perception, processing and recall of unknown faces, as well as a review of the new generation systems which automatically generate facial images in terms of facial representation and the applied optimisation method (GA).

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

References

  • Arandjelovic O, Hammoud R, Cipolla R (2006) On person authentication by fusing visual and thermal face biometrics. In: IEEE international conference on video and signal based surveillance, AVSS’06, pp 50–50

  • Arya S, Pratap N, Bhatia K (2015) Future of face recognition: a review. Proc Comput Sci 58:578–585

    Article  Google Scholar 

  • Brace N, Pike G, Kemp R, Turner J, Bennett P (2006) Does the presentation of multiple facial composites improve suspect identification? Appl Cognit Psychol 20(2):213–226

    Article  Google Scholar 

  • Bruce V, Ness H, Hancock PJ, Newman C, Rarity J (2002) Four heads are better than one: combining face composites yields improvements in face likeness. J Appl Psychol 87(5):894

    Article  Google Scholar 

  • Carlson CA, Gronlund SD, Weatherford DR, Carlson MA (2012) Processing differences between feature-based facial composites and photos of real faces. Appl Cognit Psychol 26(4):525–540

    Article  Google Scholar 

  • Chen X, Tian J, Yang X, Zhang Y (2006) An algorithm for distorted fingerprint matching based on local triangle feature set. IEEE Trans Inf Forens Secur 1(2):169–177

    Article  Google Scholar 

  • Choi H, Boaventura M, Boaventura IA, Jain AK (2012) Automatic segmentation of latent fingerprints. In: IEEE fifth international conference on biometrics: theory, applications and systems (BTAS), pp 303–310

  • Christie D, Davies GM, Shepherd JW, Ellis HD (1981) Evaluating a new computer-based system for face recall. Law Hum Behav 5(2–3):209–218

    Article  Google Scholar 

  • Cooper EE, Wojan TJ (2000) Differences in the coding of spatial relations in face identification and basic-level object recognition. J Exp Psychol Learn Mem Cognit 26(2):470

    Article  Google Scholar 

  • Cootes TF, Edwards GJ, Taylor CJ (1998) Active appearance models. In: Computer vision ECCV98. Springer, pp 484–498

  • Cootes TF, Edwards GJ, Taylor CJ (2001) Active appearance models. IEEE Trans Patt Anal Mach Intell 23(6):681–685

    Article  Google Scholar 

  • Craw I, Cameron P (1991) Parameterising images for recognition and reconstruction. In: BMVC91. Springer, pp 367–370

  • Craw I, Cameron P (1992) Face recognition by computer. In: BMVC92. Springer, pp 498–507

  • Cutler BL, Stocklein CJ, Penrod SD (1988) Empirical examination of a computerized facial composite production system. Forensic Rep 1(3):207–218

  • Cutler RG (1996) Face recognition using infrared images and eigenfaces. University of Maryland Institute for Advanced Computer Studies Report, University of Maryland, MD

  • Davies GM, Shepherd J, Shepherd J, Flin R, Ellis HD (1986) Training skills in police photofit operators. Policing 2(1):3546

    Google Scholar 

  • Davies GM, Van der Willik P, Morrison LJ (2000) Facial composite production: a comparison of mechanical and computer-driven systems. J Appl Psychol 85(1):119

    Article  Google Scholar 

  • Davis JP, Simmons S, Sulley L, Solomon CJ, Gibson SJ (2015) An evaluation of post-production facial composite enhancement techniques. J Forensic Pract 17(4):307–318

    Article  Google Scholar 

  • Donohue K, Huang L, Burks T, Forsberg F, Piccoli C (2001) Tissue classification with generalized spectrum parameters. Ultrasound Med Biol 27(11):1505–1514

    Article  Google Scholar 

  • Elguebaly T, Bouguila N (2011) A bayesian method for infrared face recognition. In: Machine vision beyond visible spectrum. Springer, pp 123–138

  • Ellis HD (1986) Introduction to aspects of face processing: ten questions in need of answers. In: Aspects of face processing. Springer, pp 3–13

  • Ellis HD, Shepherd JW, Davies GM (1975) An investigation of the use of the photo-fit* technique for recalling faces. Br J Psychol 66(1):29–37

    Article  Google Scholar 

  • Ellis HD, Davies GM, Shepherd JW (1978) A critical examination of the photofit system for recalling faces. Ergonomics 21:297–307

    Article  Google Scholar 

  • Ellis HD, Shepherd JW, Davies GM (1979) Identification of familiar and unfamiliar faces from internal and external features: some implications for theories of face recognition. Perception 8(4):431–439

    Article  Google Scholar 

  • EvoFIT.co.uk (2015) Example EvoFIT screenshot. http://www.evofit.co.uk/how-it-works/. Accessed 01 May 2015

  • EvoFIT.co.uk (2016) Case studies. http://www.evofit.co.uk/case-studies/. Accessed 15 Oct 2016

  • Feng J (2008) Combining minutiae descriptors for fingerprint matching. Patt Recognit 41(1):342–352

    Article  MATH  Google Scholar 

  • Feng J, Yoon S, Jain AK (2009) Latent fingerprint matching: fusion of rolled and plain fingerprints. In: Advances in biometrics. Springer, pp 695–704

  • Fisher RP, Geiselman RE (1992) Memory-enhancing techniques for investigative interviewing: the cognitive interview. Charles C Thomas Publisher, Springfield

    Google Scholar 

  • Fodarella C, Kuivaniemi-Smith H, Gawrylowicz J, Frowd CD (2015) Forensic procedures for facial-composite construction. J Forensic Pract 17(4):259–270

    Article  Google Scholar 

  • Frowd CD (2001) EvoFIT: a holistic, evolutionary facial imaging system. PhD thesis, University of Stirling

  • Frowd CD (2015) Facial composites and techniques to improve image recognizability. In: Forensic facial identification: theory and practice of identification from eyewitnesses, composites and CCTV, pp 43–70

  • Frowd CD, Park J, McIntyre A, Bruce V, Pitchford M, Fields S, Kenirons M, Hancock PJ, (2008) Effecting an improvement to the fitness function. how to evolve a more identifiable face. In: IEEE ECSIS symposium on bio-inspired learning and intelligent systems for security, BLISS’08, pp 3–10

  • Frowd CD, Petkovic A, Nawaz K, Bashir Y (2009) Automating the processes involved in facial composite production and identification. In: IEEE 2009 symposium on bio-inspired learning and intelligent systems for security, pp 35–42

  • Frowd CD, Pitchford M, Skelton FC, Petkovic A, Prosser C, Coates B (2012b) Catching even more offenders with EvoFIT facial composites. In: IEEE 2012 third international conference on emerging security technologies (EST), pp 20–26

  • Frowd CD, Hancock PJ, Carson D (2004) EvoFIT: a holistic, evolutionary facial imaging technique for creating composites. ACM Trans Appl Percept 1(1):19–39

    Article  Google Scholar 

  • Frowd CD, Carson D, Ness H, McQuiston-Surrett D, Richardson J, Baldwin H, Hancock P (2005a) Contemporary composite techniques: the impact of a forensically-relevant target delay. Leg Criminol Psychol 10(1):63–81

    Article  Google Scholar 

  • Frowd CD, Carson D, Ness H, Richardson J, Morrison L, Mclanaghan S, Hancock P (2005b) A forensically valid comparison of facial composite systems. Psychol Crime Law 11(1):33–52

    Article  Google Scholar 

  • Frowd CD, Bruce V, McIntyre AH, Ross D, Fields S, Plenderleith Y, Hancock PJ (2006) Implementing holistic dimensions for a facial composite system. J Multimed 1(3):42–51

    Article  Google Scholar 

  • Frowd CD, Bruce V, Ness H, Bowie L, Paterson J, Thomson-Bogner C, McIntyre A, Hancock PJ (2007a) Parallel approaches to composite production: interfaces that behave contrary to expectation. Ergonomics 50(4):562–585

    Article  Google Scholar 

  • Frowd CD, Bruce V, Ross D, McIntyre A, Hancock PJ (2007b) An application of caricature: how to improve the recognition of facial composites. Visual Cognit 15(8):954–984

    Article  Google Scholar 

  • Frowd CD, McQuiston-Surrett D, Anandaciva S, Ireland C, Hancock PJ (2007c) An evaluation of US systems for facial composite production. Ergonomics 50(12):1987–1998

    Article  Google Scholar 

  • Frowd CD, Hancock PJ, Bruce V, Skelton FC, Atherton CJ, Nelson L, McIntyre AH, Pitchford M, Atkins R, Webster D et al (2011a) Catching more offenders with EvoFIT facial composites: lab research and police field trials. Global J Hum Soc Sci 11:35–46

    Google Scholar 

  • Frowd CD, Pitchford M, Bruce V, Jackson S, Hepton G, Greenall M, McIntyre AH, Hancock PJ (2011b) The psychology of face construction: giving evolution a helping hand. Appl Cognit Psychol 25(2):195–203

    Article  Google Scholar 

  • Frowd CD, Nelson L, Skelton FC, Noyce R, Atkins R, Heard P, Morgan D, Fields S, Henry J, McIntyre A et al (2012a) Interviewing techniques for darwinian facial-composite systems. Appl Cognit Psychol 26(4):576–584

    Article  Google Scholar 

  • Frowd CD, Skelton FC, Atherton C, Pitchford M, Bruce V, Atkins R, Gannon C, Ross D, Young F, Nelson L et al (2012c) Understanding the multiframe caricature advantage for recognizing facial composites. Vis Cognit 20(10):1215–1241

    Article  Google Scholar 

  • Frowd CD, Skelton FC, Atherton C, Pitchford M, Hepton G, Holden L, McIntyre AH, Hancock PJ (2012d) Recovering faces from memory: the distracting influence of external facial features. J Exp Psychol Appl 18(2):224

    Article  Google Scholar 

  • Frowd CD, Skelton FC, Hepton G, Holden L, Minahil S, Pitchford M, McIntyre A, Brown C, Hancock PJ (2013) Whole-face procedures for recovering facial images from memory. Sci Justice 53(2):89–97

    Article  Google Scholar 

  • Frowd CD, Jones S, Fodarella C, Skelton FC, Fields S, Williams A, Marsh JE, Thorley R, Nelson L, Greenwood L et al (2014a) Configural and featural information in facial-composite images. Sci Justice 54(3):215–227

    Article  Google Scholar 

  • Frowd CD, White D, Kemp I, Jenkins R, Nawaz K, Herold K (2014b) Constructing faces from memory: the impact of image likeness and prototypical representations. J Forensic Pract 16(4):243–256

    Article  Google Scholar 

  • Frowd CD, Erickson WB, Lampinen JM, Skelton FC, McIntyre AH, Hancock PJ (2015) A decade of evolving composites: regression-and meta-analysis. J Forensic Pract 17(4):319–334

    Article  Google Scholar 

  • Gibson SJ, Solomon CJ, Bejarano AP (2003) Synthesis of photographic quality facial composites using evolutionary algorithms. In: BMVC, pp 1–10

  • Gibson SJ, Solomon CJ, Maylin MI, Clark C (2009) New methodology in facial composite construction: from theory to practice. Int J Electron Secur Digital Forensics 2(2):156–168

    Article  Google Scholar 

  • Gillenson ML, Chandrasekaran B (1975) The computerized police artist. Proc Carnahan Int Crime Count Meas 107:78

    Google Scholar 

  • Haig ND (1988) The effect of feature displacement on the perception of well-known faces. Perception 7:474

    Google Scholar 

  • Halim MFA, Al-Fiadh HH (2006) Facial composite system using genetic algorithm. In: IEEE 2006 international conference on computer graphics, imaging and visualisation, pp 262–266

  • Hancock PJ, Bruce V, Burton AM (2000) Recognition of unfamiliar faces. Trends Cognit Sci 4(9):330–337

    Article  Google Scholar 

  • Holland JH (1975) Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. U Michigan Press, Ann Arbor

    MATH  Google Scholar 

  • IDENTI-KIT Solutions (2016) Identi-kit 7. http://identikit.net/law-enforcement/. Accessed 04 May 2016

  • Jain AK, Feng J (2011) Latent fingerprint matching. IEEE Trans Patt Anal Mach Intell 33(1):88–100

    Article  Google Scholar 

  • Johnston VS (1994) Method and apparatus for generating composites of human faces. US Pat 5:375,195

    Google Scholar 

  • Kausalya R, Pandiarajan S (2013) Latent fingerprint matching techniques: a survey. Int J Eng Res Technol 2:3348–3355

  • Kawasaki M, Bouma BE, Bressner J, Houser SL, Nadkarni SK, MacNeill BD, Jang IK, Fujiwara H, Tearney GJ (2006) Diagnostic accuracy of optical coherence tomography and integrated backscatter intravascular ultrasound images for tissue characterization of human coronary plaques. J Am Coll Cardiol 48(1):81–88

    Article  Google Scholar 

  • Kim KI, Jung K, Kim HJ (2002) Face recognition using kernel principal component analysis. IEEE Signal Process Lett 9(2):40–42

    Article  MathSciNet  Google Scholar 

  • Klum S, Han H, Jain AK, Klare B (2013) Sketch based face recognition: forensic vs. composite sketches. In: IEEE 2013 international conference on biometrics (ICB), pp 1–8

  • Koehn CE, Fisher RP (1997) Constructing facial composites with the mac-a-mug pro system. Psychol Crime Law 3(3):209–218

    Article  Google Scholar 

  • Kovera MB, Penrod SD, Pappas C, Thill DL (1997) Identification of computer-generated facial composites. J Appl Psychol 82(2):235

    Article  Google Scholar 

  • Koziel T, Debinski Z (1994) Komputerowy portret obrazowy w systemie pol-sit. Probl Kryminal 206:94

    Google Scholar 

  • Kuivaniemi-Smith HJ, Nash RA, Brodie ER, Mahoney G, Rynn C (2014) Producing facial composite sketches in remote cognitive interviews: a preliminary investigation. Psychol Crime Law 20(4):389–406

    Article  Google Scholar 

  • Kurt B, Etaner-Uyar AS, Akbal T, Demir N, Kanlikilicer AE, Kus MC, Ulu FH (2006) Active appearance model-based facial composite generation with interactive nature-inspired heuristics. In: Multimedia content representation, classification and security. Springer, pp 183–190

  • Laughery KR, Fowler RH (1980) Sketch artist and identi-kit procedures for recalling faces. J Appl Psychol 65(3):307

    Article  Google Scholar 

  • Lin Z, Wenrui Z, Li S, Zhijun F (2011) Infrared face recognition based on compressive sensing and pca. In: 2011 IEEE international conference on computer science and automation engineering (CSAE), vol 2, pp 51–54

  • McDonald H (1960) The identi-kit manual. Townsend Company (Identi-Kit Division), Santa-Ana

    Google Scholar 

  • McQuiston-Surrett D, Topp LD, Malpass RS (2006) Use of facial composite systems in US law enforcement agencies. Psychol Crime Law 12(5):505–517

    Article  Google Scholar 

  • Moon S, Kong S, Yoo JH, Chung K (2006) Face recognition with multiscale data fusion of visible and thermal images. In: Proceedings of the 2006 IEEE international conference on computational intelligence for homeland security and personal safety, pp 24–27

  • Moon H, Phillips PJ (2001) Computational and performance aspects of pca-based face-recognition algorithms. Percept Lond 30(3):303–322

    Article  Google Scholar 

  • National Research Council (2014) Identifying the culprit: assessing eyewitness identification. The National Academies Press, Washington

  • Ness H, Hancock PJ, Bowie L, Bruce V, Pike G (2015) Are two views better than one? Investigating three-quarter view facial composites. J Forensic Pract 17(4):291–306

    Article  Google Scholar 

  • Paulino A, Feng J, Jain AK et al (2013) Latent fingerprint matching using descriptor-based hough transform. IEEE Trans Inf Forensics Secur 8(1):31–45

    Article  Google Scholar 

  • Penry J (1971) Photofit kit. John Waddington of Kirkstall Ltd, Leeds

    Google Scholar 

  • Penry J, Ryan I (1971) Looking at faces and remembering them: a guide to facial identification. Elek Books, London

  • Pignoli P, Tremoli E, Poli A, Oreste P, Paoletti R (1986) Intimal plus medial thickness of the arterial wall: a direct measurement with ultrasound imaging. Circulation 74(6):1399–1406

    Article  Google Scholar 

  • Prokoski F, Riedel R, Coffin J (1992) Identification of individuals by means of facial thermography. In: Proceedings institute of electrical and electronics engineers, 1992 international Carnahan conference on security technology: crime Countermeasures, pp 120–125

  • Schooler JW, Engstler-Schooler TY (1990) Verbal overshadowing of visual memories: some things are better left unsaid. Cognit Psychol 22(1):36–71

    Article  Google Scholar 

  • Schreiber P, Kovac M, Moravcik O (2012) Using genetic algorithms for identikit creation. In: Proceedings of the world congress on engineering and computer science, vol 1

  • Shi P, Tian J, Su Q, Yang X (2007) A novel fingerprint matching algorithm based on minutiae and global statistical features. In: First IEEE international conference on biometrics: theory, applications, and systems, BTAS 2007, pp 1–6

  • Sinha P, Balas B, Ostrovsky Y, Russell R (2006) Face recognition by humans: nineteen results all computer vision researchers should know about. Proc IEEE 94(11):1948–1962

    Article  Google Scholar 

  • Skelton FC, Frowd CD, Andrews S (2011) Witness interviews: Does recall of relational information improve identifiability of a facial composite? Int J Secur Appl 5(4):3748

    Google Scholar 

  • Skelton FC, Frowd CD, Speers KE (2015) The benefit of context for facial-composite construction. J Forensic Pract 17(4):281–290

    Article  Google Scholar 

  • Socolinsky D, Selinger A (2004) Thermal face recognition over time. In: Proceedings of the 17th international conference on pattern recognition, ICPR 2004, vol 4, pp 187–190

  • Solomon CJ, Gibson SJ, Pallares-Bejarano A (2005) Eigenfit–the generation of photographic quality facial composites. J Forensic Sci

  • Solomon CJ, Gibson SJ, Mist JJ (2013) Interactive evolutionary generation of facial composites for locating suspects in criminal investigations. Appl Soft Comput 13(7):3298–3306

    Article  Google Scholar 

  • Straus J (2008) Kriminalisticka taktika. Vydavatelstvi a nakladatelstvi Aleš Čeněk

  • Straus J, Vavera F (2010) Slovnik kriminalistickych pojmu a osobnosti. Vydavatelstvi a nakladatelstvi Ales Cenek

  • Sudarshan V, Acharya UR, Ng EYK, Meng CS, San Tan R, Ghista DN (2015) Automated identification of infarcted myocardium tissue characterization using ultrasound images: a review. IEEE Rev Biomed Eng 8:86–97

  • Tanaka JW, Farah MJ (2003) The holistic representation of faces. Percept Faces Objects Scenes Anal Holist Process 53–74

  • Tredoux C (2002) A direct measure of facial similarity and its relation to human similarity perceptions. J Exp Psychol Appl 8(3):180

    Article  Google Scholar 

  • Tredoux C, Nunez D, Oxtoby O, Prag B (2006) An evaluation of id: an eigenface based construction system—reviewed article. S Afr Comput J 37:90–97

    Google Scholar 

  • Troje NF, Vetter T (1996) Representation of human faces. Tech. rep., Max-Planck-Institut Tubingen

  • Turk M, Pentland A (1991) Eigenfaces for recognition. J Cognit Neurosci 3(1):71–86

    Article  Google Scholar 

  • Valentine T (1991) A unified account of the effects of distinctiveness, inversion, and race in face recognition. Q J Exp Psychol 43(2):161–204

    Article  Google Scholar 

  • Valentine T, Davis JP, Thorner K, Solomon CJ, Gibson SJ (2010) Evolving and combining facial composites: between-witness and within-witness morphs compared. J Exp Psychol Appl 16(1):72

    Article  Google Scholar 

  • VisionMetric (2015) Facial composite imaging. http://www.visionmetric.com/. Accessed 01 May 2015

  • VisionMetric (2016) How e-fit works. http://www.visionmetric.com/products/about-e-fit/how-e-fit-works. Accessed 04 May 2016

  • Wells GL (1993) What do we know about eyewitness identification? Am Psychol 48(5):553

    Article  Google Scholar 

  • Wells GL, Charman SD, Olson EA (2005) Building face composites can harm lineup identification performance. J Exp Psychol Appl 11(3):147

    Article  Google Scholar 

  • Wogalter MS, Bradley Warwitz D (1991) Face composite construction: in-view and from-memory quality and improvement with practice. Ergonomics 34(4):459–468

    Article  Google Scholar 

  • Yoon S, Feng J, Jain AK (2012) Altered fingerprints: analysis and detection. IEEE Trans Patt Anal Mach Intell 34(3):451–464

    Article  Google Scholar 

  • Yoon S, Feng J, Jain AK (2010) On latent fingerprint enhancement. In: SPIE defense, security, and sensing, international society for optics and photonics, pp 766,707–766,707

  • Zhang Y, McCullough C, Sullins JR, Ross CR (2008) Human and computer evaluations of face sketches with implications for forensic investigations. In: 2nd IEEE international conference on biometrics: theory, applications and Systems 2008, BTAS 2008, pp 1–7

Download references

Acknowledgments

This work was funded by a Grant from the VEGA, No. 1/0673/15: “Knowledge discovery for hierarchical control of technological and production processes”. This publication is a result of implementation of the project: “UNIVERSITY SCIENTIFIC PARK: CAMPUS MTF STU-CAMBO” (ITMS: 26220220179) supported by the Research & Development Operational Program funded by the EFRR.

Author information

Authors and Affiliations

  1. Institute of Applied Informatics, Automation and Mechatronics, Faculty of Materials Science and Technology in Trnava, Slovak University of Technology in Bratislava, Paulinska 16, Trnava, Slovakia

    Barbora Zahradnikova, Sona Duchovicova & Peter Schreiber

Authors
  1. Barbora Zahradnikova
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sona Duchovicova
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Peter Schreiber
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Barbora Zahradnikova.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zahradnikova, B., Duchovicova, S. & Schreiber, P. Facial composite systems: review. Artif Intell Rev 49, 131–152 (2018). https://doi.org/10.1007/s10462-016-9519-1

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10462-016-9519-1

Keywords

Search

Navigation