“…The wavelet coefficients of low and high frequency in the third layer were used to form the feature vector. The feature fusion and classification methods in [27] were used.…”
Section: Experimental Results Using Normal Facesmentioning
confidence: 99%
“…There were 66 moment features, each of which included imaginary and real parts, and modulus values. The raw image was divided into 12 blocks according to [27]. The DB3 wavelet was then used to perform a three-layer non-sampling discrete wavelet transform.…”
Section: Discussionmentioning
confidence: 99%
“…In this section, we will test NIRFaceNet, LBP + PCA [23], LBP Histogram [47], ZMUDWT [27], ZMHK [28], and GoogLeNet on the CASIA NIR database [23]. Facial expression, head pose variation, salt-and-pepper and Gaussian noise, motion and Gaussian blur are added to the dataset to compare the robustness of the algorithms.…”
Section: Experiments and Analysismentioning
confidence: 99%
“…Using the same CASIA NIR database, Sajad et al [26] later tested global feature extraction methods (ZM, independent component analysis, radon transform plus discrete cosine transform, radon transform plus discrete wavelet transform) and local feature extraction methods (LBP, Gabor wavelets, discrete wavelet transform, undecimated discrete wavelet transform), and found ZM and undecimated discrete wavelet transform (UDWT) can achieve the highest recognition rate among global and local feature extraction methods, respectively. To obtain better recognition performance, Sajad et al [27,28] moved on to fuse global and local features and proposed Zernike moment undecimated discrete wavelet transform (ZMUDWT) method and the Zernike moments plus hermite kernels (ZMHK) method as the feature extraction methods for NIR face recognition.…”
Near-infrared (NIR) face recognition has attracted increasing attention because of its advantage of illumination invariance. However, traditional face recognition methods based on NIR are designed for and tested in cooperative-user applications. In this paper, we present a convolutional neural network (CNN) for NIR face recognition (specifically face identification) in non-cooperative-user applications. The proposed NIRFaceNet is modified from GoogLeNet, but has a more compact structure designed specifically for the Chinese Academy of Sciences Institute of Automation (CASIA) NIR database and can achieve higher identification rates with less training time and less processing time. The experimental results demonstrate that NIRFaceNet has an overall advantage compared to other methods in the NIR face recognition domain when image blur and noise are present. The performance suggests that the proposed NIRFaceNet method may be more suitable for non-cooperative-user applications.
“…The wavelet coefficients of low and high frequency in the third layer were used to form the feature vector. The feature fusion and classification methods in [27] were used.…”
Section: Experimental Results Using Normal Facesmentioning
confidence: 99%
“…There were 66 moment features, each of which included imaginary and real parts, and modulus values. The raw image was divided into 12 blocks according to [27]. The DB3 wavelet was then used to perform a three-layer non-sampling discrete wavelet transform.…”
Section: Discussionmentioning
confidence: 99%
“…In this section, we will test NIRFaceNet, LBP + PCA [23], LBP Histogram [47], ZMUDWT [27], ZMHK [28], and GoogLeNet on the CASIA NIR database [23]. Facial expression, head pose variation, salt-and-pepper and Gaussian noise, motion and Gaussian blur are added to the dataset to compare the robustness of the algorithms.…”
Section: Experiments and Analysismentioning
confidence: 99%
“…Using the same CASIA NIR database, Sajad et al [26] later tested global feature extraction methods (ZM, independent component analysis, radon transform plus discrete cosine transform, radon transform plus discrete wavelet transform) and local feature extraction methods (LBP, Gabor wavelets, discrete wavelet transform, undecimated discrete wavelet transform), and found ZM and undecimated discrete wavelet transform (UDWT) can achieve the highest recognition rate among global and local feature extraction methods, respectively. To obtain better recognition performance, Sajad et al [27,28] moved on to fuse global and local features and proposed Zernike moment undecimated discrete wavelet transform (ZMUDWT) method and the Zernike moments plus hermite kernels (ZMHK) method as the feature extraction methods for NIR face recognition.…”
Near-infrared (NIR) face recognition has attracted increasing attention because of its advantage of illumination invariance. However, traditional face recognition methods based on NIR are designed for and tested in cooperative-user applications. In this paper, we present a convolutional neural network (CNN) for NIR face recognition (specifically face identification) in non-cooperative-user applications. The proposed NIRFaceNet is modified from GoogLeNet, but has a more compact structure designed specifically for the Chinese Academy of Sciences Institute of Automation (CASIA) NIR database and can achieve higher identification rates with less training time and less processing time. The experimental results demonstrate that NIRFaceNet has an overall advantage compared to other methods in the NIR face recognition domain when image blur and noise are present. The performance suggests that the proposed NIRFaceNet method may be more suitable for non-cooperative-user applications.
“…Other important properties include robustness against transformational noise and excellent reconstruction capabilities. Owing to these properties, the ZMs were applied in the fields of character recognition [3], watermarking [4,5], image retrieval [6], texture retrieval [7], face recognition [8] and image reconstruction [9]. Pseudo-Zernike moments (PZMs) were given by Bhatia and Wolf [10].…”
Moments can be viewed as powerful image descriptors that capture global characteristics of an image. The magnitude of the moment coefficients is said to be invariant under geometrical transformations like rotation which makes them suitable for most of the recognition applications. But in practice, the invariance of moment coefficients is compromised due to the errors in computation. This paper presents an empirical study of some popularly used moment functions to find out the robust coefficients under rotation. The selected robust coefficients are used in face recognition under in-plane rotation. Experimental results demonstrate that the performance of the proposed method comes at par with the performance of the traditional method by using lesser number of moment coefficients and thus results in significant saving in the feature extraction time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.