**5. Experimental results**

All experiments are performed using Matlab 2018a on a standard i5–3320 2.60 GHz machine with 8.0 GB RAM. Here we prove the effectiveness of the LBP based IDW feature extraction method for which a comparison is established with other LBP based non-adaptive MRA methods. In the experiments, we randomly select a few face images for training and rest for testing to obtain the recognition results.

The face identification performance of the proposed method is performed on CASIA-WebFace [20] and LFW [21] face Database with extreme facial variations where all the images are considered under unrestrained environment. Since, LBPbased IDW histogram features are extracted, comparative face identification methods include descriptive methods such as LBP [7], WLD [8], and SRC-GSLBP [14]. Besides, a comparison with few non-adaptive MRA-based LBP feature extraction methods such as LGBPHS [9], SPT-LBP [10], Curvelet-LBP [11], Contourlet-LBP [12], and GTCLBPSRC [15] is also performed for competitive analysis.

### **5.1 Experiments on the CASIA-WebFace face database**

The CASIA-WebFace database [22] is a huge and complex face database. This database includes 494,414 face images of 10,575 subjects. Considering the subjects with only a few samples deters the recognition results. Thus 10,575 subjects are allocated in the decreasing order by the count of their images contained in the particular subject set. Here we consider only 9067 subjects which consist of at least 15 images. The remaining images of the rest of the 1508 subjects are discarded. Within this, we considered a subset of 600 subjects with 15 images per subject out of 9067 subjects. These subjects are specifically considered based upon their extreme facial variations. Face images are normalized and resized to128x128 pixels. illumination, expression, pose, occlusion, and age difference, this database imposes an immense challenge. **Figure 1** depicts the trend of the rank one recognition rates for different comparative methods along with the proposed method for Casia-

**5.2 Experiments on the labelled faces in the wild (LFW) face database**

**Method Number of training samples per subject**

*Rank-One Recognition Results of different methods on the LFW face database (%).*

LBP [7] 24.07 30.16 38.22 42.81 44.14 WLD [8] 25.12 31.42 40.10 43.60 46.12 LGBPHS [9] 33.76 35.15 42.05 45.34 49.06 SPT-LBP [10] 34.90 40.20 43.62 45.93 50.61 Curvlet-LBP [11] 33.11 39.48 43.55 44.60 50.08 Contourlet-LBP [12] 35.09 40.25 45.52 46.41 53.32 SRC-GSLBP [14] 38.30 41.40 47.22 55.00 57.69 GTCLBPSRC [15] 40.72 42.80 50.30 58.59 60.23 ADWTLBP [17] 41.60 44.50 52.28 59.44 62.74 DIWTLBP [18] 40.80 44.89 53.03 60.18 63.04 IDW-LBP (Proposed Method) 40.77 45.64 54.80 61.01 64.42

**45678**

*Rank-One Recognition Results of different methods for the CASIA-WebFace face database (%).*

*Face Identification Using LBP-Based Improved Directional Wavelet Transform*

*DOI: http://dx.doi.org/10.5772/intechopen.93445*

database. Each image is resized to 128 128 pixels.

The LFW [20] is a large database that contains face images of 5749 famous personalities captured in an unrestrained environment with an extreme variation of background, pose, illumination, expression, and accessories. This makes it a challenging database for face identification. Here, we used the LFW-a database [21] which is an aligned version of the LFW database. For our experimentation purpose, we created a subset with 15 dissimilar images of 150 subjects from the LFW-a

WebFace face database.

**Figure 1.**

**Table 2.**

**41**

A random subset is constructed with *T* (*T* = 4*,* 5*,* 6*,* 7*,* 8) images of each subject for training and in every case remaining images for testing. **Table 1** tabulates the Rank-one recognition results of various comparative methods. Since the images are collected from around the web with extremely unrestrained conditions, the results are less for all the methods. Due to extreme face variations which include


#### **Table 1.**

*Rank-One Recognition Results of different methods on the CASIA-WebFace face database (%).*

*Face Identification Using LBP-Based Improved Directional Wavelet Transform DOI: http://dx.doi.org/10.5772/intechopen.93445*

#### **Figure 1.**

**5. Experimental results**

*Biometric Systems*

results.

**Table 1.**

**40**

All experiments are performed using Matlab 2018a on a standard i5–3320 2.60 GHz machine with 8.0 GB RAM. Here we prove the effectiveness of the LBP based IDW feature extraction method for which a comparison is established with other LBP based non-adaptive MRA methods. In the experiments, we randomly select a few face images for training and rest for testing to obtain the recognition

The face identification performance of the proposed method is performed on CASIA-WebFace [20] and LFW [21] face Database with extreme facial variations where all the images are considered under unrestrained environment. Since, LBPbased IDW histogram features are extracted, comparative face identification methods include descriptive methods such as LBP [7], WLD [8], and SRC-GSLBP [14]. Besides, a comparison with few non-adaptive MRA-based LBP feature extraction methods such as LGBPHS [9], SPT-LBP [10], Curvelet-LBP [11], Contourlet-LBP [12], and GTCLBPSRC [15] is also performed for competitive analysis.

The CASIA-WebFace database [22] is a huge and complex face database. This database includes 494,414 face images of 10,575 subjects. Considering the subjects with only a few samples deters the recognition results. Thus 10,575 subjects are allocated in the decreasing order by the count of their images contained in the particular subject set. Here we consider only 9067 subjects which consist of at least 15 images. The remaining images of the rest of the 1508 subjects are discarded. Within this, we considered a subset of 600 subjects with 15 images per subject out of 9067 subjects. These subjects are specifically considered based upon their extreme facial variations. Face images are normalized and resized to128x128 pixels. A random subset is constructed with *T* (*T* = 4*,* 5*,* 6*,* 7*,* 8) images of each subject for training and in every case remaining images for testing. **Table 1** tabulates the Rank-one recognition results of various comparative methods. Since the images are collected from around the web with extremely unrestrained conditions, the results

are less for all the methods. Due to extreme face variations which include

**Method Number of training samples per subject**

*Rank-One Recognition Results of different methods on the CASIA-WebFace face database (%).*

LBP [7] 14.07 16.06 18.24 21.81 24.14 WLD [8] 15.60 17.71 21.40 23.20 25.09 LGBPHS [9] 22.80 26.09 28.93 31.48 34.76 SPT-LBP [10] 25.22 30.10 32.20 34.52 36.12 Curvlet-LBP [11] 25.66 30.28 31.49 35.49 38.26 Contourlet-LBP [12] 27.22 31.33 32.49 36.55 40.60 SRC-GSLBP [14] 31.24 33.37 34.19 38.20 42.05 GTCLBPSRC [15] 31.25 32.55 34.42 38.63 42.30 ADWTLBP [17] 33.90 39.40 41.09 42.00 45.60 DIWTLBP [18] 34.65 40.36 41.78 42.17 45.81 IDW-LBP (Proposed Method) 35.89 41.39 42.20 43.31 46.12

**4567 8**

**5.1 Experiments on the CASIA-WebFace face database**

*Rank-One Recognition Results of different methods for the CASIA-WebFace face database (%).*

illumination, expression, pose, occlusion, and age difference, this database imposes an immense challenge. **Figure 1** depicts the trend of the rank one recognition rates for different comparative methods along with the proposed method for Casia-WebFace face database.

#### **5.2 Experiments on the labelled faces in the wild (LFW) face database**

The LFW [20] is a large database that contains face images of 5749 famous personalities captured in an unrestrained environment with an extreme variation of background, pose, illumination, expression, and accessories. This makes it a challenging database for face identification. Here, we used the LFW-a database [21] which is an aligned version of the LFW database. For our experimentation purpose, we created a subset with 15 dissimilar images of 150 subjects from the LFW-a database. Each image is resized to 128 128 pixels.


#### **Table 2.**

*Rank-One Recognition Results of different methods on the LFW face database (%).*

approximation sub-band and mid-frequency sub-bands coefficients for feature generation and does not consider the multi-region information. Thus LGBPHS, Curvelet-LBP, Contourlet-LBP, and SPT-LBP are both memory and time exhaustive to extract the multiresolution and multi-orientation features due to selection and

*Face Identification Using LBP-Based Improved Directional Wavelet Transform*

Moreover, these methods despite capturing the directional information lack the adaptation in selecting the directional details based on the image description and suffer from various issues such as the selection of sub-bands, high computational rate, and complex filter design. The GTCLBPSRC delivers close results to the proposed method for all the databases but at cost of additional computational time and due to the implementation of Gabor wavelet transform (GWT) which exhibits over-complete representation. We also examined comparable progress over SRC-GSLBP and GTCLBPSRC for all the databases which illustrate the effectiveness of sparse representation methods. The IDW method consists of benefits such as directional lifting and adaptation in the direction selection as per the characteristics of the images within a block of samples. Moreover, as a result of lifting based factorization, perfect reconstruction is also assured and the resultant multiresolution image is completely compatible with that of the conventional 2-D DWT

multiresolution image. These facts effectively consider various edge manifolds that

We also compared the proposed method with recently developed methods which also considers the facial descriptions in an adaptive MRA-based structure such as ADWT [17] and DIWT [18]. We applied a similar procedure to extract the LBP based features. The improvement in our method is visible owing to the adaptation of more directions as compared to DIWT [18] and application of sub-pixel

Thus, as per **Tables 1** and **2**, it is verified that the IDW method exhibit high discrimination capability and offers excellent recognition results for a very complex database such as CASIA-WebFace and LFW databases which consists of facial variations with mild to intense pose, expression, and illumination variations. Experiments performed for an identification process verify that the proposed

\* and Qazi Mateenuddin Hameeduddin<sup>2</sup>

1 Faculty of Electrical Engineering Department, Muffakham Jah College of

2 Faculty of Electronics and Communication, India Naval Academy, Ezhimala,

© 2020 The Author(s). Licensee IntechOpen. This chapter is distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/ by/3.0), which permits unrestricted use, distribution, and reproduction in any medium,

Engineering and Technology, Hyderabad, Telangana, India

\*Address all correspondence to: ab.muqeet2013@gmail.com

provided the original work is properly cited.

interpolation in IDW which is absent in the ADWT method.

method excels with all the comparative methods.

feature extraction from different sub-bands.

*DOI: http://dx.doi.org/10.5772/intechopen.93445*

represent different face variations.

**Author details**

Mohd. Abdul Muqeet<sup>1</sup>

Kannur, Kerala, India

**43**

#### **Figure 2.**

*Rank-One Recognition Results of different methods for the LFW face database (%).*

A subset with *T* (*T* = 4, 5, 6, 7, 8) images per subject is randomly selected to form a training set, and rest images per subject are selected to form the testing set. Rankone recognition results of different comparative methods are tabulated in **Table 2**. Since the images are selected in the unrestrained environment the Rank-one recognition results are also low in this database.

**Figure 2** depicts the trend of the rank one recognition rates for different comparative methods along with the proposed method for LFW face database.

#### **6. Conclusion**

This chapter discusses the recently developed implementation of interpolationbased ADWT with seven directions and an improved QTP scheme to extract directional MRA features from face images. LBP is applied to the selected top-level IDW sub-bands to extract the multi-region histogram-based local descriptive features. Experiments conducted on the complex face databases such as CASIA-WebFace and LFW database exhibit the efficacy of our proposed method. The identification results of our method are compared with various methods which include local descriptors such as LBP and WLD. Few LBP-based non-adaptive MRA methods are also utilized for a fair comparison as our method also falls into the category of MRA based methods.

LBP and WLD suffer from issues such as the large size of histogram features, extraction of only very local texture details, limited discriminative ability, and intolerance to noise.

It also is evident from **Tables 1** and **2** that LGBPHS, SPT-LBP, Curvelet-LBP, and Contour-LBP methods provide lesser results against our proposed method. We examine progress over SRC-GSLBP, GTCLBPSRC which illustrates some effectiveness of usage of sparse features at the cost of increased complexity in implementation.

SPT-LBP also exhibits comparable performance to the proposed method but the feature selection is threshold dependent and necessitates the selection of sub-bands for efficient feature extraction. Curvelet-LBP uses only the LBP coded image of the

#### *Face Identification Using LBP-Based Improved Directional Wavelet Transform DOI: http://dx.doi.org/10.5772/intechopen.93445*

approximation sub-band and mid-frequency sub-bands coefficients for feature generation and does not consider the multi-region information. Thus LGBPHS, Curvelet-LBP, Contourlet-LBP, and SPT-LBP are both memory and time exhaustive to extract the multiresolution and multi-orientation features due to selection and feature extraction from different sub-bands.

Moreover, these methods despite capturing the directional information lack the adaptation in selecting the directional details based on the image description and suffer from various issues such as the selection of sub-bands, high computational rate, and complex filter design. The GTCLBPSRC delivers close results to the proposed method for all the databases but at cost of additional computational time and due to the implementation of Gabor wavelet transform (GWT) which exhibits over-complete representation. We also examined comparable progress over SRC-GSLBP and GTCLBPSRC for all the databases which illustrate the effectiveness of sparse representation methods. The IDW method consists of benefits such as directional lifting and adaptation in the direction selection as per the characteristics of the images within a block of samples. Moreover, as a result of lifting based factorization, perfect reconstruction is also assured and the resultant multiresolution image is completely compatible with that of the conventional 2-D DWT multiresolution image. These facts effectively consider various edge manifolds that represent different face variations.

We also compared the proposed method with recently developed methods which also considers the facial descriptions in an adaptive MRA-based structure such as ADWT [17] and DIWT [18]. We applied a similar procedure to extract the LBP based features. The improvement in our method is visible owing to the adaptation of more directions as compared to DIWT [18] and application of sub-pixel interpolation in IDW which is absent in the ADWT method.

Thus, as per **Tables 1** and **2**, it is verified that the IDW method exhibit high discrimination capability and offers excellent recognition results for a very complex database such as CASIA-WebFace and LFW databases which consists of facial variations with mild to intense pose, expression, and illumination variations. Experiments performed for an identification process verify that the proposed method excels with all the comparative methods.

## **Author details**

A subset with *T* (*T* = 4, 5, 6, 7, 8) images per subject is randomly selected to form a training set, and rest images per subject are selected to form the testing set. Rankone recognition results of different comparative methods are tabulated in **Table 2**. Since the images are selected in the unrestrained environment the Rank-one recog-

**Figure 2** depicts the trend of the rank one recognition rates for different com-

This chapter discusses the recently developed implementation of interpolationbased ADWT with seven directions and an improved QTP scheme to extract directional MRA features from face images. LBP is applied to the selected top-level IDW sub-bands to extract the multi-region histogram-based local descriptive features. Experiments conducted on the complex face databases such as CASIA-WebFace and LFW database exhibit the efficacy of our proposed method. The identification results of our method are compared with various methods which include local descriptors such as LBP and WLD. Few LBP-based non-adaptive MRA methods are also utilized for a fair comparison as our method also falls into the category of MRA

LBP and WLD suffer from issues such as the large size of histogram features, extraction of only very local texture details, limited discriminative ability, and

It also is evident from **Tables 1** and **2** that LGBPHS, SPT-LBP, Curvelet-LBP, and Contour-LBP methods provide lesser results against our proposed method. We examine progress over SRC-GSLBP, GTCLBPSRC which illustrates some effectiveness of usage of sparse features at the cost of increased complexity in

SPT-LBP also exhibits comparable performance to the proposed method but the feature selection is threshold dependent and necessitates the selection of sub-bands for efficient feature extraction. Curvelet-LBP uses only the LBP coded image of the

parative methods along with the proposed method for LFW face database.

*Rank-One Recognition Results of different methods for the LFW face database (%).*

nition results are also low in this database.

**6. Conclusion**

**Figure 2.**

*Biometric Systems*

based methods.

intolerance to noise.

implementation.

**42**

Mohd. Abdul Muqeet<sup>1</sup> \* and Qazi Mateenuddin Hameeduddin<sup>2</sup>

1 Faculty of Electrical Engineering Department, Muffakham Jah College of Engineering and Technology, Hyderabad, Telangana, India

2 Faculty of Electronics and Communication, India Naval Academy, Ezhimala, Kannur, Kerala, India

\*Address all correspondence to: ab.muqeet2013@gmail.com

© 2020 The Author(s). Licensee IntechOpen. This chapter is distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/ by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
