TY - JOUR
T1 - Recognition of face images under angular constraints using DWT-PCA/SVD algorithm
AU - Asiedu, Louis
AU - Mettle, Felix O.
AU - Nortey, Ezekiel N.N.
AU - Yeboah, Enoch S.
N1 - Publisher Copyright:
© 2017 Pushpa Publishing House, Allahabad, India.
PY - 2017/12
Y1 - 2017/12
N2 - The intricacy of a face’s features originates from continuous changes in the facial features that take place over time. Regardless of these changes, we are able to recognize a person very easily. In human interactions, the articulation and perception of constraints; like head-poses, facial expressions form a communication channel that is additional to voice and that carries crucial information about mental, emotional and even physical states of a conversation. Automatic face recognition is worthwhile, since an efficient and resilient recognition system is useful in many application areas. This paper presents an evaluation of the performance of principal component analysis with singular value decomposition using discrete wavelet transform (DWT-PCA/SVD) for preprocessing under angular constraints (4°, 8°, 12°, 16°, 20°, 24°, 28° and 32°). Ten individuals from Massachusetts Institute of Technology (MIT) database (2003-2005) captured under the specified angular constraints were considered for recognition runs. Friedman’s rank sum test was used to ascertain whether significant differences exist between the median recognition distances of the various constraints from their straight-pose (0°). Recognition rate and runtime were adopted as the numerical evaluation methods to assess the performance of the study algorithm. All numerical and statistical computations were done using Matlab. The results of the Friedman’s rank sum test show that the higher the degrees of head-pose, the larger the recognition distances and that at 20° and above, the recognition distances become profoundly larger compared to the 4° head-pose. The numerical evaluations show that DWT-PCA/SVD face recognition algorithm has an appreciable average recognition rate (87.5%) when used to recognize face images under angular constraints. Also, the recognition rate decreases for head-poses greater than 20°. Discrete wavelet transform is recommended as a viable noise removal mechanism that should be adopted during image preprocessing.
AB - The intricacy of a face’s features originates from continuous changes in the facial features that take place over time. Regardless of these changes, we are able to recognize a person very easily. In human interactions, the articulation and perception of constraints; like head-poses, facial expressions form a communication channel that is additional to voice and that carries crucial information about mental, emotional and even physical states of a conversation. Automatic face recognition is worthwhile, since an efficient and resilient recognition system is useful in many application areas. This paper presents an evaluation of the performance of principal component analysis with singular value decomposition using discrete wavelet transform (DWT-PCA/SVD) for preprocessing under angular constraints (4°, 8°, 12°, 16°, 20°, 24°, 28° and 32°). Ten individuals from Massachusetts Institute of Technology (MIT) database (2003-2005) captured under the specified angular constraints were considered for recognition runs. Friedman’s rank sum test was used to ascertain whether significant differences exist between the median recognition distances of the various constraints from their straight-pose (0°). Recognition rate and runtime were adopted as the numerical evaluation methods to assess the performance of the study algorithm. All numerical and statistical computations were done using Matlab. The results of the Friedman’s rank sum test show that the higher the degrees of head-pose, the larger the recognition distances and that at 20° and above, the recognition distances become profoundly larger compared to the 4° head-pose. The numerical evaluations show that DWT-PCA/SVD face recognition algorithm has an appreciable average recognition rate (87.5%) when used to recognize face images under angular constraints. Also, the recognition rate decreases for head-poses greater than 20°. Discrete wavelet transform is recommended as a viable noise removal mechanism that should be adopted during image preprocessing.
KW - Discrete wavelet transform
KW - Friedman’s rank sum test
KW - Principal component analysis
KW - Singular value decomposition
UR - http://www.scopus.com/inward/record.url?scp=85038121539&partnerID=8YFLogxK
U2 - 10.17654/MS102112809
DO - 10.17654/MS102112809
M3 - Article
AN - SCOPUS:85038121539
SN - 0972-0871
VL - 102
SP - 2809
EP - 2830
JO - Far East Journal of Mathematical Sciences
JF - Far East Journal of Mathematical Sciences
IS - 11
ER -