TY - JOUR
T1 - A novel local pattern descriptor - Local vector pattern in high-order derivative space for face recognition
AU - Fan, Kuo Chin
AU - Hung, Tsung Yung
PY - 2014/7
Y1 - 2014/7
N2 - In this paper, a novel local pattern descriptor generated by the proposed local vector pattern (LVP) in high-order derivative space is presented for use in face recognition. Based on the vector of each pixel constructed by computing the values between the referenced pixel and the adjacent pixels with diverse distances from different directions, the vector representation of the referenced pixel is generated to provide the 1D structure of micropatterns. With the devise of pairwise direction of vector for each pixel, the LVP reduces the feature length via comparative space transform to encode various spatial surrounding relationships between the referenced pixel and its neighborhood pixels. Besides, the concatenation of LVPs is compacted to produce more distinctive features. To effectively extract more detailed discriminative information in a given subregion, the vector of LVP is refined by varying local derivative directions from the (n th-order LVP in (n-1) th-order derivative space, which is a much more resilient structure of micropatterns than standard local pattern descriptors. The proposed LVP is compared with the existing local pattern descriptors including local binary pattern (LBP), local derivative pattern (LDP), and local tetra pattern (LTrP) to evaluate the performances from input grayscale face images. In addition, extensive experiments conducting on benchmark face image databases, FERET, CAS-PEAL, CMU-PIE, Extended Yale B, and LFW, demonstrate that the proposed LVP in high-order derivative space indeed performs much better than LBP, LDP, and LTrP in face recognition.
AB - In this paper, a novel local pattern descriptor generated by the proposed local vector pattern (LVP) in high-order derivative space is presented for use in face recognition. Based on the vector of each pixel constructed by computing the values between the referenced pixel and the adjacent pixels with diverse distances from different directions, the vector representation of the referenced pixel is generated to provide the 1D structure of micropatterns. With the devise of pairwise direction of vector for each pixel, the LVP reduces the feature length via comparative space transform to encode various spatial surrounding relationships between the referenced pixel and its neighborhood pixels. Besides, the concatenation of LVPs is compacted to produce more distinctive features. To effectively extract more detailed discriminative information in a given subregion, the vector of LVP is refined by varying local derivative directions from the (n th-order LVP in (n-1) th-order derivative space, which is a much more resilient structure of micropatterns than standard local pattern descriptors. The proposed LVP is compared with the existing local pattern descriptors including local binary pattern (LBP), local derivative pattern (LDP), and local tetra pattern (LTrP) to evaluate the performances from input grayscale face images. In addition, extensive experiments conducting on benchmark face image databases, FERET, CAS-PEAL, CMU-PIE, Extended Yale B, and LFW, demonstrate that the proposed LVP in high-order derivative space indeed performs much better than LBP, LDP, and LTrP in face recognition.
KW - Local pattern descriptors
KW - comparative space transform (CST)
KW - face recognition
KW - local binary pattern (LBP)
KW - local derivative pattern (LDP)
KW - local tetra pattern (LTrP)
KW - local vector pattern (LVP)
UR - http://www.scopus.com/inward/record.url?scp=84901992300&partnerID=8YFLogxK
U2 - 10.1109/TIP.2014.2321495
DO - 10.1109/TIP.2014.2321495
M3 - 期刊論文
AN - SCOPUS:84901992300
SN - 1057-7149
VL - 23
SP - 2877
EP - 2891
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
IS - 7
M1 - 6809981
ER -