Aug 5, 2008 - Quantitative Measurement of FD Algorithm Performance .... Speed. FERET. 735. 90.63%. 9.27%. 0.0%. 0.28 det
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Quantitative Measurement of Face Detection Algorithm Performance Setiawan Hadi Mathematics Department Universitas Padjadjaran (UNPAD) Bandung - INDONESIA
The 4th International Conference on Information & Communication Technology (ICTS) 2008
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Outline
1
Background and Motivation Background Problem Definition Motivation
2
Proposed Method Description Development Strategy Implementation Scenario Experimental Result
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Background Problem Definition Motivation
Outline
1
Background and Motivation Background Problem Definition Motivation
2
Proposed Method Description Development Strategy Implementation Scenario Experimental Result
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Background Problem Definition Motivation
Why Human Face ? Background
+ Given an arbitrary image, the goal of face detection is to determine whether or not there are any faces in the image and, if present ... return the image location and extent of each face. Yang (2004) The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Background Problem Definition Motivation
Why Human Face ? Background
+ Given an arbitrary image, the goal of face detection is to determine whether or not there are any faces in the image and, if present ... return the image location and extent of each face. Yang (2004) The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Background Problem Definition Motivation
Sample Results of Face Detection Algorithms Background
(a)
(b)
(c)
Successful face detection from (a) Rowley et al. (b) Hsi et al. (c) Hadi et al.
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Background Problem Definition Motivation
Outline
1
Background and Motivation Background Problem Definition Motivation
2
Proposed Method Description Development Strategy Implementation Scenario Experimental Result
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Background Problem Definition Motivation
Problem Definition
+ Most face detection algorithms do not clearly define a successful face detection process.
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Background Problem Definition Motivation
What constitutes successful face detection? Problem Definition
(a)
(b)
(a) Test Image (b) Possible Face Detection Results Classified as Face or Non-face
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Background Problem Definition Motivation
Outline
1
Background and Motivation Background Problem Definition Motivation
2
Proposed Method Description Development Strategy Implementation Scenario Experimental Result
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Background Problem Definition Motivation
Motivation
+ A uniform criterion should be adopted to define or to measure a successful detection.
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Development Strategy Implementation Scenario Experimental Result
Outline
1
Background and Motivation Background Problem Definition Motivation
2
Proposed Method Description Development Strategy Implementation Scenario Experimental Result
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Development Strategy Implementation Scenario Experimental Result
Measuring Accuracy Technique Development Strategy
+ Using bounding box determination (GTBB and DBB calculation)
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Development Strategy Implementation Scenario Experimental Result
Measuring Accuracy Technique Development Strategy
+ GTBB : Ground Truth Bounding Box + DBB : Detected Bounding Box
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Development Strategy Implementation Scenario Experimental Result
Measuring Accuracy Technique Development Strategy
+ GTBB : Ground Truth Bounding Box + DBB : Detected Bounding Box
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Development Strategy Implementation Scenario Experimental Result
Measuring Accuracy Technique Development Strategy
D=
1 (dTL + dTR + dBL + dBR ) 4
(1)
dTL , dTR , dBL and dBR are Euclidean distances of GTBB and DBB. dTL =
(GTBBTLx − DBBTLx )2 + (GTBBTLy − DBBTLy )2
q (GTBB q = (GTBB q
dTR = dBL
q
dBR =
(2)
TRx
− DBBTRx )2 + (GTBBTRy − DBBTRy )2
(3)
BLx
− DBBBLx )2 + (GTBBBLy − DBBBLy )2
(4)
(GTBBBRx − DBBBRx )2 + (GTBBBRy − DBBBRy )2
The 4th International Conference on ICTS - 5th August 2008
(5)
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Development Strategy Implementation Scenario Experimental Result
Outline
1
Background and Motivation Background Problem Definition Motivation
2
Proposed Method Description Development Strategy Implementation Scenario Experimental Result
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Development Strategy Implementation Scenario Experimental Result
Characteristics Implementation Scenario
+ Using DeWa, a framework for multiple human face detection in complex background digital image that utilized multiaspect approach + Algorithm for measuring single face and multiple faces + Using single human face image databases and multiple human face image databases
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Development Strategy Implementation Scenario Experimental Result
DeWa Framework Implementation Scenario
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Development Strategy Implementation Scenario Experimental Result
Human Face Databases Implementation Scenario
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Development Strategy Implementation Scenario Experimental Result
Mechanism Implementation Scenario
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Development Strategy Implementation Scenario Experimental Result
Outline
1
Background and Motivation Background Problem Definition Motivation
2
Proposed Method Description Development Strategy Implementation Scenario Experimental Result
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Development Strategy Implementation Scenario Experimental Result
Experimental Result
Using Single Face Image Databases Image
DR
TN
FP
Speed
FERET
Database
735
90.63%
9.27%
0.0%
0.28 detik
DWI
347
89.78%
10.22%
0.0%
0.28 detik
Using Complex Face Image Databases Database
Face
DR
TN
FP
Speed
mDWI
488
92.21%
7.79%
7.96%
0.19 s/f
VALID
298
91.28%
8.72%
7.67%
0.15 s/f
DR=Detection Rate | TN = True Negative | FP = False Positive
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Conclusion + A technique for quantitatively measuring face detection algorithm performance has been proposed + A face detection algorithm called DeWa is used for implementing the technique + It has been tested successfully using two single face image database and two multiple face image database
Future Works + Using different bounding objects such as ellips and facial edge boundary + Using more sophisticated techniques for distance calculation
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
Selected References
1
Hadi, S, Ahmad, A.S, Suwardi, I.S., Wazdi, F., DeWa : A multiaspect approach for multiple face detection in complex scene digital image, ITB Journal of Information and Communication Technology, Vol. 1C No. 1, 2007
2
Hsu, R.L., Abdel-Mottaleb, M., Jain, A.K.,Face Detection in Color Images, IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 24 No.5 Pp. 696-706, 2002
3
Rowley, H. A., Baluja, S. dan Kanade, T., Neural Network-based Face Detection, IEEE Trans. on Pattern Analysis and Machine Intelligence , Vol. 20 No. 1 Pp. 23-28, 1998
4
Yang, M.-H., Kriegman, D. J. and Ahuja, N., Detecting Faces in Images: A Survey, IEEE Transactions on Patterns Analysis and Machine Intelligence (PAMI), Vol. 24 No. 1 Pp. 34-58, 2002
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
Background and Motivation Proposed Method Description Conclusion and Future Works Selected References
The 4th International Conference on ICTS - 5th August 2008
Quantitative Measurement of FD Algorithm Performance
