Quantitative Measurement of Face Detection Algorithm Performance

  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

  1

  2

  1

  2

  ☞ 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)

  ☞ 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)

  (a) (b) (c) Successful face detection from (a) Rowley et al. (b) Hsi et al. (c) Hadi et al.

  1

  2

  

☞ Most face detection algorithms do not clearly define a

successful face detection process.

  (a) (b) (a) Test Image (b) Possible Face Detection Results Classified as Face or Non-face

  1

  2

  ☞ A uniform criterion should be adopted to define or to measure a successful detection.

  1

  2

  ☞ Using bounding box determination (GTBB and DBB calculation)

  ☞ GTBB : Ground Truth Bounding Box ☞ DBB : Detected Bounding Box

  ☞ GTBB : Ground Truth Bounding Box ☞ DBB : Detected Bounding Box

  D =

  1

  4 (d _TL + d _TR + d _BL + d _BR ) (1) d _TL ^, d _TR ^, d _BL and d _BR are Euclidean distances of GTBB and DBB. d _TL

  = q (GTBB _{TL x − DBB TL x} ) ² + (GTBB _{TL y − DBB TL y} ) ²

  (2) d _TR = q (GTBB _{TR x − DBB TR x} ) ² + (GTBB _{TR y − DBB TR y} ) ² (3) d _BL = q

  (GTBB _{BL x − DBB BL x} ) ² + (GTBB _{BL y − DBB BL y} ) ² (4) d _BR = q (GTBB _{BR x} ^{− DBB} _{BR x} ) ² + (GTBB _{BR y} ^{− DBB} _{BR y} ) ² (5)

  1

  2

  DeWa , a framework for multiple human face ☞ Using 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

  1

  2 Using Single Face Image Databases

  Database Image DR TN FP Speed FERET 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 _{DR=Detection Rate | TN = True Negative | FP = False Positive}

  VALID 298 91.28% 8.72% 7.67% 0.15 s/f 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

  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 ₂ Information and Communication Technology, Vol. 1C No. 1, 2007

  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. ₃ 696-706, 2002 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. ₄ 23-28, 1998

  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