Do you see what i see? A more realistic eyewitness sketch recognition

H Nejati, T Sim, Elisa MARTINEZ MARROQUIN

Research output: A Conference proceeding or a Chapter in BookConference contribution

4 Citations (Scopus)

Abstract

Face sketches have been used in eyewitness testimonies for about a century. However, 30 years of research shows that current eyewitness testimony methods are highly unreliable. Nonetheless, current face sketch recognition algorithms assume that eyewitness sketches are reliable and highly similar to their respective target faces. As proven by psychological findings and a recent work on face sketch recognition, these assumptions are unrealistic and therefore, current algorithms cannot handle real world cases of eyewitness sketch recognition. In this paper, we address the eyewitness sketch recog nition problem with a two-pronged approach. We propose a more reliable eyewitness testimony method, and an accompanying face sketch recognition method that accounts for realistic assumptions on sketch-photo similarities and individual eyewitness differences. In our eyewitness testimony method we first ask the eyewitness to directly draw a sketch of the target face, and provide some ancillary information about the target face. Then we build a drawing profile of the eyewitness by asking him/her to draw a set of face photos. This drawing profile implicitly contains the eyewitness' mental bias. In our face sketch recognition method we first correct the sketch for the eyewitness' bias using the drawing profile. Then we recognize the resulting sketch based on an optimized combination of the detected features and ancillary information. Experimental results show that our method is 12 times better than the leading competing method at Rank-1 accuracy, and 6 times better at Rank-10. Our method also maintains its superiority as gallery size increases
Original languageEnglish
Title of host publication2011 International Joint Conference on Biometrics (IJCB 2011)
Place of PublicationWashington, USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1-8
Number of pages8
Volume1
ISBN (Print)9781457713583
DOIs
Publication statusPublished - 2011
Event2011 International Joint Conference on Biometrics - Crystal City, Crystal City, United States
Duration: 11 Oct 201113 Oct 2011
http://www.cse.nd.edu/IJCB_11/ (Conference webpage)

Conference

Conference2011 International Joint Conference on Biometrics
Abbreviated titleIJCB 2011
CountryUnited States
CityCrystal City
Period11/10/1113/10/11
Internet address

Fingerprint

Face recognition

Cite this

Nejati, H., Sim, T., & MARTINEZ MARROQUIN, E. (2011). Do you see what i see? A more realistic eyewitness sketch recognition. In 2011 International Joint Conference on Biometrics (IJCB 2011) (Vol. 1, pp. 1-8). Washington, USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IJCB.2011.6117497
Nejati, H ; Sim, T ; MARTINEZ MARROQUIN, Elisa. / Do you see what i see? A more realistic eyewitness sketch recognition. 2011 International Joint Conference on Biometrics (IJCB 2011). Vol. 1 Washington, USA : IEEE, Institute of Electrical and Electronics Engineers, 2011. pp. 1-8
@inproceedings{b401fded8d104581a595cb3ce5753f7d,
title = "Do you see what i see? A more realistic eyewitness sketch recognition",
abstract = "Face sketches have been used in eyewitness testimonies for about a century. However, 30 years of research shows that current eyewitness testimony methods are highly unreliable. Nonetheless, current face sketch recognition algorithms assume that eyewitness sketches are reliable and highly similar to their respective target faces. As proven by psychological findings and a recent work on face sketch recognition, these assumptions are unrealistic and therefore, current algorithms cannot handle real world cases of eyewitness sketch recognition. In this paper, we address the eyewitness sketch recog nition problem with a two-pronged approach. We propose a more reliable eyewitness testimony method, and an accompanying face sketch recognition method that accounts for realistic assumptions on sketch-photo similarities and individual eyewitness differences. In our eyewitness testimony method we first ask the eyewitness to directly draw a sketch of the target face, and provide some ancillary information about the target face. Then we build a drawing profile of the eyewitness by asking him/her to draw a set of face photos. This drawing profile implicitly contains the eyewitness' mental bias. In our face sketch recognition method we first correct the sketch for the eyewitness' bias using the drawing profile. Then we recognize the resulting sketch based on an optimized combination of the detected features and ancillary information. Experimental results show that our method is 12 times better than the leading competing method at Rank-1 accuracy, and 6 times better at Rank-10. Our method also maintains its superiority as gallery size increases",
keywords = "Face-recognition, sketch-recognition, memory-retrieval",
author = "H Nejati and T Sim and {MARTINEZ MARROQUIN}, Elisa",
year = "2011",
doi = "10.1109/IJCB.2011.6117497",
language = "English",
isbn = "9781457713583",
volume = "1",
pages = "1--8",
booktitle = "2011 International Joint Conference on Biometrics (IJCB 2011)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Nejati, H, Sim, T & MARTINEZ MARROQUIN, E 2011, Do you see what i see? A more realistic eyewitness sketch recognition. in 2011 International Joint Conference on Biometrics (IJCB 2011). vol. 1, IEEE, Institute of Electrical and Electronics Engineers, Washington, USA, pp. 1-8, 2011 International Joint Conference on Biometrics, Crystal City, United States, 11/10/11. https://doi.org/10.1109/IJCB.2011.6117497

Do you see what i see? A more realistic eyewitness sketch recognition. / Nejati, H; Sim, T; MARTINEZ MARROQUIN, Elisa.

2011 International Joint Conference on Biometrics (IJCB 2011). Vol. 1 Washington, USA : IEEE, Institute of Electrical and Electronics Engineers, 2011. p. 1-8.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Do you see what i see? A more realistic eyewitness sketch recognition

AU - Nejati, H

AU - Sim, T

AU - MARTINEZ MARROQUIN, Elisa

PY - 2011

Y1 - 2011

N2 - Face sketches have been used in eyewitness testimonies for about a century. However, 30 years of research shows that current eyewitness testimony methods are highly unreliable. Nonetheless, current face sketch recognition algorithms assume that eyewitness sketches are reliable and highly similar to their respective target faces. As proven by psychological findings and a recent work on face sketch recognition, these assumptions are unrealistic and therefore, current algorithms cannot handle real world cases of eyewitness sketch recognition. In this paper, we address the eyewitness sketch recog nition problem with a two-pronged approach. We propose a more reliable eyewitness testimony method, and an accompanying face sketch recognition method that accounts for realistic assumptions on sketch-photo similarities and individual eyewitness differences. In our eyewitness testimony method we first ask the eyewitness to directly draw a sketch of the target face, and provide some ancillary information about the target face. Then we build a drawing profile of the eyewitness by asking him/her to draw a set of face photos. This drawing profile implicitly contains the eyewitness' mental bias. In our face sketch recognition method we first correct the sketch for the eyewitness' bias using the drawing profile. Then we recognize the resulting sketch based on an optimized combination of the detected features and ancillary information. Experimental results show that our method is 12 times better than the leading competing method at Rank-1 accuracy, and 6 times better at Rank-10. Our method also maintains its superiority as gallery size increases

AB - Face sketches have been used in eyewitness testimonies for about a century. However, 30 years of research shows that current eyewitness testimony methods are highly unreliable. Nonetheless, current face sketch recognition algorithms assume that eyewitness sketches are reliable and highly similar to their respective target faces. As proven by psychological findings and a recent work on face sketch recognition, these assumptions are unrealistic and therefore, current algorithms cannot handle real world cases of eyewitness sketch recognition. In this paper, we address the eyewitness sketch recog nition problem with a two-pronged approach. We propose a more reliable eyewitness testimony method, and an accompanying face sketch recognition method that accounts for realistic assumptions on sketch-photo similarities and individual eyewitness differences. In our eyewitness testimony method we first ask the eyewitness to directly draw a sketch of the target face, and provide some ancillary information about the target face. Then we build a drawing profile of the eyewitness by asking him/her to draw a set of face photos. This drawing profile implicitly contains the eyewitness' mental bias. In our face sketch recognition method we first correct the sketch for the eyewitness' bias using the drawing profile. Then we recognize the resulting sketch based on an optimized combination of the detected features and ancillary information. Experimental results show that our method is 12 times better than the leading competing method at Rank-1 accuracy, and 6 times better at Rank-10. Our method also maintains its superiority as gallery size increases

KW - Face-recognition

KW - sketch-recognition

KW - memory-retrieval

U2 - 10.1109/IJCB.2011.6117497

DO - 10.1109/IJCB.2011.6117497

M3 - Conference contribution

SN - 9781457713583

VL - 1

SP - 1

EP - 8

BT - 2011 International Joint Conference on Biometrics (IJCB 2011)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Washington, USA

ER -

Nejati H, Sim T, MARTINEZ MARROQUIN E. Do you see what i see? A more realistic eyewitness sketch recognition. In 2011 International Joint Conference on Biometrics (IJCB 2011). Vol. 1. Washington, USA: IEEE, Institute of Electrical and Electronics Engineers. 2011. p. 1-8 https://doi.org/10.1109/IJCB.2011.6117497