Fig 16 - uploaded by Fadhlan Hafizhelmi Kamaru Zaman
Content may be subject to copyright.
Example of images in FRGC 2.0 dataset. The dataset consist of controlled images (a–c), as well as uncontrolled images (d, e) and intensity of 3D images (f).
Source publication
Gabor Wavelets (GW) have been extensively used for facial feature representation due to its inherent multi-resolution and multi-orientation characteristics. In this work we extend the work on Local Gabor Feature Vector (LGFV) and propose a new face recognition method called LGFV//LN//SNP, which employs local normalization filter in pre-processing s...
Similar publications
We present in this paper a new palmprint recognition system based on the principal lines of the palm. An original algorithm is proposed in order to detect automatically principal lines and extract their corre-spondent geometrical features. Given the complexity of the palmprint recognition and in order to ameliorate performances, we propose a hybrid...
Citations
... In [27][28][29], it shown that employing logarithmic Gabor filters are extremely useful for image rendering. In the present study, the logarithmic filter functions are employed using a Gaussian transfer function, as suggested by [30]. Therefore, the response vector for each of the filter pairs is determined through Equation (3). ...
... The incidence of noise in the calculation of ( ) can be deduced under the following conditions: the image noise is additive; the noise power In [27][28][29], it shown that employing logarithmic Gabor filters are extremely useful for image rendering. In the present study, the logarithmic filter functions are employed using a Gaussian transfer function, as suggested by [30]. Therefore, the response vector for each of the filter pairs is determined through Equation (3). ...
The correct management of operations in thermoelectric plants is based on the continuous evaluation of the structural integrity of its components, among which there are elements made of stainless steel that perform water conduction functions at elevated temperatures. The working conditions generate progressive wear that must be monitored from the perspective of the microstructure of the material. When AISI 304 stainless steel is subjected to a temperature range between 450 and 850 °C, it is susceptible to intergranular corrosion. This phenomenon, known as sensitization, causes the material to lose strength and generates different patterns in its microstructure. This research analyzes three different patterns present in the microstructure of stainless steel, which manifest themselves through the following characteristics: the absence of intergranular corrosion, the presence of intergranular corrosion, and the precipitation of chromium carbides. This article shows the development of a methodology capable of recognizing the corrosion patterns generated in stainless steel with an accuracy of 98%, through the integration of a multilayer perceptron neural network and the following digital image processing methods: phase congruence and a gray-level co-occurrence matrix. In this way, an automatic procedure for the analysis of the intergranular corrosion present in AISI 304 stainless steel using artificial intelligence is proposed.
... Asimismo, los autores Kamaruzaman y Shafie [6] consideran que existen varios métodos para detectar y reconocer todo tipo de movimientos que realicen las personas, así también García, Mera, Santana y Uzmila [7] nos mencionan que existen estudios basados en algoritmos para identificar rostros, personas, señales de tránsito, tumores, aspectos de datos visuales y detección de imágenes. ...
This article presents the development of an artificial vision system for the recognition of postures focused on remote modality workers, being a suitable model to work with anyone, regardless of their age, race, sexual orientation or size as a target. of this work is to implement remote work to determine the challenges and possibilities of using this type of work and identify factors to consider before implementation. The work is justified because it is essential to determine if this modality is efficient to carry out the correct measurement of the worker's posture. Having as a result that the angle of 120 ° and 60 ° reveals possible causes of back pain and injuries caused by poor posture or incorrect postural hygiene; This means that when the user is sitting in the correct 90° degree posture, it avoids causing serious back injuries in the long term.
... One technique for extracting local features is the local binary patterns method [69][70][71]. In addition, the combination of global-and local-based approaches, which is termed the hybrid features extraction-based approach, aims to achieve the highest object recognition accuracy [72,73]. ...
Three-dimensional (3D) image and medical image processing, which are considered big data analysis, have attracted significant attention during the last few years. To this end, efficient 3D object recognition techniques could be beneficial to such image and medical image processing. However, to date, most of the proposed methods for 3D object recognition experience major challenges in terms of high computational complexity. This is attributed to the fact that the computational complexity and execution time are increased when the dimensions of the object are increased, which is the case in 3D object recognition. Therefore, finding an efficient method for obtaining high recognition accuracy with low computational complexity is essential. To this end, this paper presents an efficient method for 3D object recognition with low computational complexity. Specifically, the proposed method uses a fast overlapped technique, which deals with higher-order polynomials and high-dimensional objects. The fast overlapped block-processing algorithm reduces the computational complexity of feature extraction. This paper also exploits Charlier polynomials and their moments along with support vector machine (SVM). The evaluation of the presented method is carried out using a well-known dataset, the McGill benchmark dataset. Besides, comparisons are performed with existing 3D object recognition methods. The results show that the proposed 3D object recognition approach achieves high recognition rates under different noisy environments. Furthermore, the results show that the presented method has the potential to mitigate noise distortion and outperforms existing methods in terms of computation time under noise-free and different noisy environments.
... Different types of transforms have been used for this purpose. Gabor transform [52] has been used widely to extract the local features [53,54], alhough the extracted face features are particularly sensitive to noise. In addition, face recognition methods that use local feature are dependent on face localization and the registration model [39]. ...
Face recognition is required in various applications, and major progress has been witnessed in this area. Many face recognition algorithms have been proposed thus far; however, achieving high recognition accuracy and low execution time remains a challenge. In this work, a new scheme for face recognition is presented using hybrid orthogonal polynomials to extract features. The embedded image kernel technique is used to decrease the complexity of feature extraction, then a support vector machine is adopted to classify these features. Moreover, a fast-overlapping block processing algorithm for feature extraction is used to reduce the computation time. Extensive evaluation of the proposed method was carried out on two different face image datasets, ORL and FEI. Different state-of-the-art face recognition methods were compared with the proposed method in order to evaluate its accuracy. We demonstrate that the proposed method achieves the highest recognition rate in different considered scenarios. Based on the obtained results, it can be seen that the proposed method is robust against noise and significantly outperforms previous approaches in terms of speed.
... Hence, the four parameters of frequency (f), angle (θ) of the sine wave, standard deviation (σ), and the appearance rate (γ) of the Gaussian function play a fundamental role in its operation. Face recognition systems such as [6,12,21,28,35,36,50,52,61] use TGFB to extract features in which the σ and γ are fixed parameters, but f and θ have different values. The use of TGFB imposes high computational complexity on the face recognition system. ...
A biometric method for identifying people is face recognition. In the face recognition process, the key step is to extract the distinctive features of each person’s image. One of the most widely used tools for this purpose is the Gabor filter bank. A Gabor filter bank can extract powerful distinguishing features from a face image, but the disadvantage is that it imposes a high computational complexity on the face recognition system. The present paper introduces two new Gabor filter banks, i.e., the Optimal Gabor Filter Bank (OGFB) and the Personal Gabor Filter Bank (PGFB), which can reduce the computational complexity of a face recognition system by more than 7.5 and 30 times, respectively. It also introduces a new feature called Square Region of Face (SRoF) which is as easy to implement as global features, while taking into account the geometric position of facial features, including eyes, nose, and lips. This new feature is resistant to changes of hairstyle, eyebrows shape, and their color, as well as to the covered part of faces especially by different types of Islamic veils. Experiments on benchmark datasets of Caltech, Yale, Feret, and CsetM show that the proposed methods achieve better or competitive classification accuracy compared to several recent face recognition systems.
... Firstly, the input is reduced into smaller input image resolution from the original 227×277 to 64×64. Some previous works on face recognition showed that this image resolution is sufficient to achieve good results [29]. By changing the size of image input layer, the size of subsequent convolution layers need to be altered too. ...
Gender classification demonstrates high accuracy in many previous works. However, it does not generalize very well in unconstrained settings and environments. Furthermore, many proposed Convolutional Neural Network (CNN) based solutions vary significantly in their characteristics and architectures, which calls for optimal CNN architecture for this specific task. In this work, a hand-crafted, custom CNN architecture is proposed to distinguish between male and female facial images. This custom CNN requires smaller input image resolutions and significantly fewer trainable parameters than some popular state-of-the-arts such as GoogleNet and AlexNet. It also employs batch normalization layers which results in better computation efficiency. Based on experiments using publicly available datasets such as LFW, CelebA and IMDB-WIKI datasets, the proposed custom CNN delivered the fastest inference time in all tests, where it needs only 0.92ms to classify 1200 images on GPU, 1.79ms on CPU, and 2.51ms on VPU. The custom CNN also delivers performance on-par with state-of-the-arts and even surpassed these methods in CelebA gender classification where it delivered the best result at 96% accuracy. Moreover, in a more challenging cross-dataset inference, custom CNN trained using CelebA dataset gives the best gender classification accuracy for tests on IMDB and WIKI datasets at 97% and 96% accuracy respectively.
... In other words, the feature extraction process of this algorithm will not change when dealing with different kinds of data. The above methods, e.g., Gabor [1,2] , and LBP [3,4] are successful on certain image classification tasks but significant adap-ing samples. The learning procedure of those two kinds of networks is different. ...
... The first is the prior distribution of the latent variable and the second is the conditional distribution of the observable variable given the latent variable. The prior distribution of the latent variable z is given in (1) . It is a standard Gaussian distribution with mean 0 and unit covariance matrix. ...
... The conditional distribution of the observable variable x given the latent variable z is given in (2) . From (1) and (2) , we can derive the unconditional distribution of the observable variable x as ...
The main learning strategy of the PCANet is using Principal Component Analysis (PCA) for learning the convolutional filters from the data. The assumption that all the image patches are sampled from a single Gaussian component is implicitly taken, which is too strong. In this paper, the image patches are modeled using mixtures of probabilistic principal component analysis (MPPCA) and the corresponding MPPCANet (PCANet constructed using mixtures of probabilistic principal component analysis) is proposed. The proposed model is applied to the few-shot learning scenario. In the proposed framework, the image patches are assumed to come from several suppositions of Gaussian components. In the process of estimating the parameters of the MPPCA model, the clustering of the training image patches and the principal components of each cluster are simultaneously obtained. The number of mixture components is automatically determined during the optimization procedure. The theoretical insights of the proposed MPPCANet is elaborated by comparing with our prior work, CPCANet (PCANet with clustering-based filters). The proposed MPPCANet is evaluated on several benchmarking visual data sets in the experiment. It is compared with the original PCANet, CPCANet and several state-of-the-art methods. The experimental results show that the proposed MPPCANet has improved significantly the recognition capability of the original PCANet under the few-shot learning scenario. The performance of the MPPCANet is also better than the CPCANet in most cases.
... The authors in [16], [17], [18], manifest that there are several studies on base at the recognition of an image using algorithms. ...
... Traditionally, existing methods generally address the face recognition problem in two subsequent steps namely (1) feature extraction and (2) recognition. In the feature extraction stage, a variation of handcrafted features has been successfully used [11][12][13][14]. Although these works include learning-based feature extraction approaches, each feature are extracted individually and separated from each other, thus some important correlations between the two compared images have been lost at the feature extraction stage. ...
span>Face verification focuses on the task of determining whether two face images belong to the same identity or not. For unrestricted faces in the wild, this is a very challenging task. Besides significant degradation due to images that have large variations in pose, illumination, expression, aging, and occlusions, it also suffers from large-scale ever-expanding data needed to perform one-to-many recognition task. In this paper, we propose a face verification method by learning face similarities using a Convolutional Neural Networks (ConvNet). Instead of extracting features from each face image separately, our ConvNet model jointly extracts relational visual features from two face images in comparison. We train four hybrid ConvNet models to learn how to distinguish similarities between the face pair of four different face portions and join them at top-layer classifier level. We use binary-class classifier at top-layer level to identify the similarity of face pairs which includes a conventional Multi-Layer Perceptron (MLP), Support Vector Machines (SVM), Native Bayes, and another ConvNet. There are 3 face pairing configurations discussed in this paper. Results from experiments using Labeled face in the Wild (LFW) and CelebA datasets indicate that our hybrid ConvNet increases the face verification accuracy by as much as 27% when compared to individual ConvNet approach. We also found that Lateral face pair configuration yields the best LFW test accuracy on a very strict test protocol without any face alignment using MLP as top-layer classifier at 87.89%, which on-par with the state-of-the-arts. We showed that our approach is more flexible in terms of inferencing the learned models on out-of-sample data by testing LFW and CelebA on either model.</span
... Higher number of D would signify higher dissimilarity, thus higher chance for the face images to actually belong to different person. Prior to the computation of D, the local Gabor features of both faces are extracted following approach outlined [20]. The dissimilarity index (D) can be denoted as the total Cosine distance between m local patches (LP) of images, which given in Equation (1) ...
As normally practiced, the information of visitor is recorded manually by either the visitor or the guard when the visitor arrives at the guard house. This manual process takes large amount of time and involves tedious works. Furthermore, it is prone to fraudulent information provided by visitors and occasionally interferes with guard's actual job in securing the area. This paper aims to provide an automated solution to these aforementioned problems. We address these problems by replacing the existing manual way of recording visitor information by an automated and fully computerized system. The solution proposed uses Radio-Frequency Identification (RFID), smart card information retrieval as well as computer vision and image processing to record and manage visitors' data. To evaluate the similarity between face images from camera and National Registration Identification Card (NRIC), we propose a method to find dissimilarity index between the faces. We found that the system minimizes the need for human interventions, improves the time required during recording of visitors' information as well as efficiently manages and analyses visitors' records. Additionally, our proposed method for finding face similarity yields a promising result of TPR = 0.914 and FPR = 0.140 when tested using publicly available face dataset called AR Dataset. The system is able to minimize the need for guard and visitor interventions, improves the time required during recording of visitors' information especially for recurring visits and also capable of securely and efficiently manages and analyses visitors' records.
