Face recognition using selected topographical features

International Journal of Electrical and Computer Engineering (IJECE)
Vol. 10, No. 5, October 2020, pp. 4695~4700
ISSN: 2088-8708, DOI: 10.11591/ijece.v10i5.pp4695-4700  4695
Journal homepage: http://ijece.iaescore.com/index.php/IJECE
Face recognition using selected topographical features
Maitham Ali Naji, Ghalib Ahmed Salman, Muthna Jasim Fadhil
College of Engineering and Electrical Technology, Middle Technical University (MTU), Iraq
Article Info ABSTRACT
Article history:
Received May 9, 2019
Revised Mar 16, 2020
Accepted Mar 28, 2020
This paper represents a new features selection method to improve an
existed feature type. Topographical (TGH) features provide large set of
features by assigning each image pixel to the related feature depending
on image gradient and Hessian matrix. Such type of features was
handled by a proposed features selection method. A face recognition
feature selector (FRFS) method is presented to inspect TGH features. FRFS
depends in its main concept on linear discriminant analysis (LDA) technique,
which is used in evaluating features efficiency. FRFS studies feature
behavior over a dataset of images to determine the level of its performance.
At the end, each feature is assigned to its related level of performance with
different levels of performance over the whole image. Depending on
a chosen threshold, the highest set of features is selected to be classified by
SVM classifier.
Keywords:
Face features
Face recognition
Feature selector
Features performance
topographical
Copyright © 2020 Institute of Advanced Engineering and Science.
All rights reserved.
Corresponding Author:
Ghalib Ahmed Salman,
College of Engineering and Electrical Technology,
Middle Technical University (MTU),
Al-Masafee Street, Al-Doora, Baghdad, Iraq.
Email: ghlbethawi@gmail.com
1. INTRODUCTION
Face recognition was deeply studied through the last decades [1]. Several types of features were
presented with different levels of recognition accuracy [2]. Each type of feature represent an amount of
information extracted from the image, and more represented information in chosen feature provides more
accuracy in recognition results [3]. Spatial filtering was adopted to extract points of interest, which are
grouped to form candidate features. A probability-based statistical model is built to select the most
powerful features for face recognition [4]. In another approach, the authors used RGB-D images based on
the extracting and the concatenating of the scale invariant feature transform (SIFT) descriptors from these
data sources for face recognition [5]. Jie Chen et al turned transformation feature by adopting specific version
of local binary patterns (LBP) as a face descriptor. Such features provided encouraging classification
accuracy, but with unacceptable error rate sometimes [6]. Face descriptor is also adopted for extracting face
feature in order to provide face recognition. The authors adopted enhanced local binary pattern (EnLBP) as
an adaption of LBP and they divided studied image into 3×3 blocks. For each block, the EnLBP features
provided mean values of each block instead of the ordinary number of LBP [7].
In this paper, since TGH provide more information than traditional edges [8], they are adopted by
combining them with the proposed feature selection method to choose the best set among them. The rest of
this of this paper contains brief explanation of TGH then the selection method; then face recognition results
and their analysis. Final section contains the conclusions extracted from this work.
2. TOPOGRAPHICAL FEATURES TGH
Although TGH were previously used in recognition researches [9, 10], their accuracy results were
relatively low regarding other types of features. One of the potential reasons of the lack in their usage is
the huge amount of produce features. Recently, it was used in object recognition researches but with the same

 ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 10, No. 5, October 2020 : 4695 - 4700
4696
problem of huge number of features [11]. Since TGH assigns each image pixel to the corresponding feature.
On the other side, TGH provides more information than traditional image edges and lines, see Figure 1(a).
Yet, and choosing only image lines and edges may ignore significant information.
Such problem can be solved by choosing efficient ones among produced features overall image, which
was a noticeable obstacle [12]. After manipulating the image with set of masks to find the orthogonal
polynomial of the image [13], image gradient and Hessian matrix of second derivatives are computed to extract
TGH (Peak, Pit, Saddle, Ridge, Ravine, Zero crossing, Flat, Increasing area and Decreasing area) [14],
see Figure 1(b). According to definitions, each literature defines some kinds of TGH to be image edges and
lines. As a result, dealing with TGH provides more information, and the next section explains the proposed
feature selection method to overcome high number of provided feature. Since TGH is an existed feature type,
this paper focuses on explaining feature selection, and aforementioned literatures discuss TGH in details.
(a) (b) (c)
Figure 1. Traditional image edges ignore significant information, while TGH study all available features:
(a) original image, (b) image edges, and (c) TGH fFeatures
3. FACE RECOGNITION FEATURE SELECTOR (FRFS)
This method seeks for features using similar rules used in LDA to evaluate feature significance [15].
According to non-parametric feature test in LDA, efficient features must yield high differences over
inter-class images against low differences over intra-class images [16]. This technique adopt testing single
feature in each round by measuring yielded differences over inter and intra-class to record its level of
efficiency. Then proposed technique moves to the second feature and so on till the last feature. Different
levels of efficiency are filtered by controlled threshold that determines selected set of features with highest
efficiency. Locations of selected features from learning dataset are allocated to choose recognition features
from test dataset in test stage.
To illustrate proposed FRFS, assume that learning dataset contains n×m images contain n persons
and m image for each of them. Each the image Imijis of h×k size, which is used to produce TGH features as:
𝑖𝑚𝑖𝑗 = [
𝑓11 𝑓12 𝑓13 … 𝑓1𝑘
𝑓21 𝑓22 𝑓23 … 𝑓2𝑘
𝑓ℎ1 𝑓ℎ2 𝑓ℎ3 … 𝑓ℎ𝑘
] (1)
The first feature from each image in learning dataset is transferred to the inspection matrix:
I11 = [
f1111 …
f11i1 …
f11n1 …
f111j … f111m
f11ij … f11im
f11nj … f11nm
] (2)
where I11: is the inspection matrix of the feature f11 over learning dataset
f11ij: the first feature f11 taken from the image in the row i and column j of the learning dataset
Statistical laws dispersion are used to measure the changes within values over inter-class and
intra-class, which are standard deviation SD and roughness coefficient rc [17]. Values dispersion is
measuring using SD by computing their deviation from the average, and it is usedin this paper to measure
two types of changes. Firstly, SD over each row is used to evaluate the changes over different images for
the same person, which represents interior differences (intra-changes). Secondly, SD over each column is
used to evaluate changes over different person in each line of images (inter-changes). The µ and SD of each
row are computed as:
µi =
∑ f11ij
m
j=1
m
(3)

Int J Elec & Comp Eng ISSN: 2088-8708 
Face recognition using selected topographical features (Maitham Ali Naji)
4697
SDri =
∑ (f11ij − µi)2m
j=1
m
(4)
Accordingly, µ and SD of each column are computed as:
µj =
∑ f11ij
n
i=1
n
(5)
SDcj =
∑ (f11ij − µj)2n
i=1
n
(6)
This produces the next matrix:
I11 =
[
f1111 …
f11i1 …
f11n1
SDc1
…
…
f111j … f111m SDr1
f11ij … f11im SDri
f11nj
SDcj
…
…
f11nm
SDcm
SDrn
]
(7)
SD for each row is called SDri to distinguish them from SD for each column (SDci). Several values
of SD are produced over intra-changes one for each person.To get one SD value over all intra-class, SDintra is
computed using next average rule:
SDintra =
∑ SDri
n
i=1
n
(8)
Accordingly, SDinter is computed as:
SDinter =
∑ SDcj
m
j=1
m
(9)
The final value of efficiencyEfinalfor the feature f11is computed by dividing SDinter over SDintra as:
Efinal =
SDinter
SDintra
(10)
The second measure of dispersion is roughness coefficient which divides the differences between
the successive values over their differences from the mean. Such measure reduces or eliminates the effect of
big differences between successive values [17].
rc =
∑ (xi − xi−1)2n
i=2
∑ (xi − μ)2n
i=2
(11)
In some cases, successive images yield significant differences due to different styles, face hair, face
expression or other factors, which can be handled using rc.Accordingly, the matrix in (7) will be:
I11 =
[
f1111 …
f11i1 …
f11n1
rcc1
…
…
f111j … f111m rcr1
f11ij … f11im rcri
f11nj
rccj
…
…
f11nm
rccm
rcrn
]
(12)
The best value of Efinal is the biggest one since it refers SDinter has highest level regarding SDintra.
Efinal is transferred to the corresponding location in a matrix for Efficiency of Features EFF, thus, Efinal for
the feature f11 is transferred to EFF (1,1). Equations (2) to (10) are re-applied on the next feature and so on
until covering all features in the image matrix imij. As result, EFF matrix will contain different values for
different levels of efficiency of features, and choosing features with highest efficiency provide best set of
candidate features. To control the number of chosen features, a threshold is proposed, and values of Efinal
lower than the threshold is ignored. Depending on chosen set of features, images are classified using
the standard support vector machine SVM [18, 19].

 ISSN: 2088-8708
4698
4. RESULTS AND DISCUSSION
Experiments of this work used fairly distorted and good images of standard FG-NET which contains
(912 of 1002) face-images, which are captured for males and females in different occasions. Highly distorted
images are excluded from the study due to their affection on yielded results. All studied images are
manipulated to be gray-scale and with size of (512×512). Comparison used in this paper is mean absolute
error (MAE).
Although building 2D polynomial for the image uses set of enhancing masks, image quality affects
recognition rate (RR). Low image quality may cause blurry or add lines and undesirable details to the image,
which may cause non-real details. Where TGH depends on differences between values [20], undesirable
effects may create non-real features as shown in Figure 2.
(a) (b) (c)
Figure 2. Image quality affects the classification accuracy and causes error rate in recognition results:
(a) fairly distorted MAE=92.78, (b) acceptable MAE=93.93, and (c) high quality MAE=94.12
As face recognition feature selector (FRFS) measures the performance of each feature and chooses
the highest set of them using a threshold, controlling the threshold value affects RR value. Increasing
the threshold value provides features with highest level of performance, yet it may ignore significant set of
features, and big number of chosen features requires longer processing time. On the other side, decreasing
threshold value ensures choosing all significant features, but they be combined by low level-performance
features, which affects recognitions accuracy. Experiments yielded best results when threshold value chooses
the highest 27% of the features performance. Only low percentage of features is chosen, though such percentage
provides significant number of features due to the huge number of produced features. See Figure 3.
Figure 3. Recognition rate due to the value of chosen threshold
FG-Net face dataset is collected from number of ordinary images, which are not prepared for
scientific purposes [21]. Faces in such images may contain glasses, hair style and face hair as shown in
Figure 4. Such undesirable conditions affects recognition accuracy, yet experiments yielded encouraging
results as shown in Table 1. Faces in some of images are rotated in two directions, first one is the rotation
around the vertical axis when some persons are leaning his head to the left or right, while some others turns
their faces to left or right direction around the horizontal axis as shown in Figure 5.

Int J Elec & Comp Eng ISSN: 2088-8708 
Face recognition using selected topographical features (Maitham Ali Naji)
4699
Figure 4. Glasses, hair style and face hair affect the recognition by hiding some features or creating new ones
Table 1. Recognition rate under the effects of glasses, hair style and face hair
Condition RR
Hair Style 93.41
Face Hair 93.03
Glasses 92.81
Figure 5. Some faces are rotated around the horizontal or vertical axis
Experimental results showed that TGH features have more robustness against rotation around
the vertical axis, which is justified by two points. As TGH features are produced using differences between
values rather than the values themselves, they have lower level of effects against rotation and illumination [9].
Secondly, this type of rotation changes features positions only, while the second type of rotation hides or
creates features due to the illumination and the view angle. Rotation around the horizontal axis yielded lower
rate in recognition accuracy.
For benchmarking with state of art, proposed collection between TGH features and FRFS method
yielded encouraging results. Comparing with highest yielded RR, proposed technique yielded noticeable
improvement considering all types of tested images by reaching (93.95%) for recognition accuracy, while
best results are yielded by applying proposed technique on images with best condition when TGH and FRFS
reach (94.12) for recognition accuracy as shown in Table 2.
Table 2. Comparing proposed technique with state of art
Techniques RR
Affine transformation due to viewing angle and distance variations. Therefore, affine invariant feature extraction [22] 92.50
Local and Holistic features with Neural Networks [23] 93.46
Signal Reconstruction with Neural Networks[24] 93.89
HAAR-like features and eigenfaces [25] 93.91
Proposed Technique (Average) 93.95
Proposed Technique (Best) 94.12
5. CONCLUSION
In this paper, a collection of topographical features which are extracted from face images after
finding the 2D polynomial of the image. They are extracted by computing image gradient and Hessian matrix
of second order derivatives of image. Due the huge number of produced features, the proposed technique of
face recognition feature selection FRFS is applied to choose the best set of produced features. Selected
features recorded robustness against rotation with insignificant level of effects for glasses, hair style and face
hair. The entire performance of the proposed technique recorded encouraging results against state of art.
For future works, we propose studying the effects of facial expression on TGH features extracted by FRFS.

 ISSN: 2088-8708
4700
REFERENCES
[1] M. M. Kasar, D. Bhattacharyya, and T. H. Kim, “Face recognition using neural network: a review,” International
Journal of Security and Its Applications, vol. 10, no. 3, pp. 81-100, 2016.
[2] R. Rouhi, et al, “A Review on Feature Extraction Techniques in Face Recognition,” Signal & Image Processing:
An International Journal (SIPIJ), vol. 3, no. 6, 2012.
[3] I. Guyon, et al, “Feature Extraction, Foundations and Applications,” Springer, 2006.
[4] K. C. Yow and R. Cipolla, “Feature-based Human Face Detection,” Journal of Image and Vision Computing,
vol. 15, no. 9, pp. 713-735, 1997.
[5] H. Ouanan, M. Ouanan, and B. Aksasse, “Gabor-HOG features based face recognition scheme,” TELKOMNIKA
Indonesian Journal of Electrical Engineering, vol. 15, no. 2, pp. 331-335, 2015.
[6] J. Chen et al, “Robust local features for remote face recognition,” Journal of Image and Vision Computing, vol. 64,
pp. 34–46, 2017.
[7] H. H. Abbas, A. A. Altameemi, and H. R. Farhan, “Biological landmark vs quasi-landmarks for 3D face
recognition and gender classification,” International Journal of Electrical and Computer Engineering (IJECE),
vol. 9, no. 5, pp. 4069-4076, 2019.
[8] M. E. Wibowo, et al., “Improved Face Recognition across Poses using Fusion of Probabilistic Latent Variable
Models,” TELKOMNIKA Telecommunication Computing Electronics and Control, vol. 15, no. 4, pp. 1971-1981,
2017.
[9] L. Wang and T. Pavlidis, “Direct Gray-Scale Extraction of Features for Character recognition,” IEEE Transactions
on Pattern Analysis and Machine Intelligence, vol. 15, no. 10, pp. 1053-1067, 1993.
[10] S.-W. Lee and Y. J. Kim, “Direct Extraction of Topographic Features for Gray Scale Character Recognition,” IEEE
Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 7, pp. 724-728, 1995.
[11] N. S. Rani, S. K. Verma, and A. Joseph, “A Zone Based Approach for Classification and Recognition of Telugu
Handwritten Characters,” International Journal of Electrical and Computer Engineering (IJECE), vol. 6, no. 4,
pp. 1647-1653, 2016.
[12] P. VenkateswarLal, G. R. Nitta, and A. Prasad, “Ensemble of texture and shape descriptors using support
vector machine classification for face recognition” Journal of Ambient Intelligence and Humanized Computing,
pp. 1-8, 2019.
[13] E. B. Moody, “Discrete Orthogonal Polynomial Restoration of Images Degraded by Spatially Varying Point Spread
Functions,” Proceedings of 1st International Conference on Image Processing, pp. 680-684, 1994.
[14] R. M. Haralick, “Digital Step Edges from Zero Crossing of Second Directional Derivatives,” IEEE Transactions on
Pattern Analysis and Machine Intelligence, vol. 1, pp. 58-68, 1984.
[15] W. Chen, M. J. Er, and S. Wu, “PCA and LDA in DCT Domain,” Pattern Recognition Letters, vol. 26, no. 15,
pp. 2474-2482, 2005.
[16] I. G. P. S. Wijaya, A. Y. Husodo, and I. W. A. Arimbawa, “Real Time Face Recognition Based on Face Descriptor
and Its Application,” TELKOMNIKA Telecommunication Computing Electronics and Control, vol. 16, no. 2,
pp. 739-746, 2018.
[17] R. V. Hogg, J. McKean, and A. T. Craig, “Introduction to mathematical statistics,” Pearson Education, 2005.
[18] J. A. Suykens and J. Vandewalle, “Least squares support vector machine classifiers,” Neural processing letters,
vol. 9, no. 3, pp. 293-300, 1999.
[19] F. E. Gunawan, J. Harefa, and N. Sekishita, “Face Recognition on Linear Motion-blurred Image,” TELKOMNIKA
(Telecommunication Computing Electronics and Control), vol. 16, no. 3, pp. 1249-1255, 2018.
[20] S. Mizugaki, et al., “Fingerprinting suspended sediment sources in the Nukabira River, northern Japan,”
International Journal of Erosion Control Engineering, vol. 5, no. 1, pp. 60-69, 2012.
[21] R. P. Persada, et al., “Automatic face and VLP'S recognition for smart parking system,” TELKOMNIKA
(Telecommunication Computing Electronics and Control), vol. 17, no. 4, pp. 1698-1705, 2019.
[22] L. Yu, et al., “Affine invariant fusion feature extraction based on geometry descriptor and BIT for object
recognition,” IET Image Processing, vol. 13, no. 1, pp. 57-72, 2018.
[23] S. Xie and H. Hu, “Facial Expression Recognition Using Hierarchical Features With Deep Comprehensive
Multipatches Aggregation Convolutional Neural Networks,” IEEE Transactions on Multimedia, vol. 21, no. 1,
pp. 211-220, 2019.
[24] B. Xu, Q. Liu, and T. Huang, “A discrete-time projection neural network for sparse signal reconstruction with
application to face recognition,” IEEE transactions on neural networks and learning systems, vol. 30, no. 1,
pp. 151-162, 2018.
[25] G. I. Hapsari, G. A. Mutiara, and H. Tarigan, “Face recognition smart cane using HAAR-like features
and eigenfaces,” TELKOMNIKA Telecommunication Computing Electronics and Control, vol. 17, no. 2,
pp. 973-980, 2019.

Face recognition using selected topographical features

More Related Content

What's hot (19)

Similar to Face recognition using selected topographical features (20)

More from IJECEIAES (20)

Recently uploaded (20)

Face recognition using selected topographical features