Initialization of deformable templates using weighted Gaussian approximations

Biometric features such as fingerprints, iris patterns, and face features help to identify people and restrict access to secure areas by performing advanced pattern analysis and matching. Face recognition is one of the most promising biometric methodologies for human identification in a non-cooperative security environment. However, the recognition results obtained by face recognition systems are a affected by several variations that may happen to the patterns in an unrestricted environment. As a result, several algorithms have been developed for extracting different facial features for face recognition. Due to the various possible challenges of data captured at different lighting conditions, viewing angles, facial expressions, and partial occlusions in natural environmental conditions, automatic facial recognition still remains as a difficult issue that needs to be resolved. In this paper, we propose a novel approach to tackling some of these issues by analyzing the local textural descriptions for facial feature representation. The textural information is extracted by an enhanced local binary pattern (ELBP) description of all the local regions of the face. The relationship of each pixel with respect to its neighborhood is extracted and employed to calculate the new representation. ELBP reconstructs a much better textural feature extraction vector from an original gray level image in different lighting conditions. The dimensionality of the texture image is reduced by principal component analysis performed on each local face region. Each low dimensional vector representing a local region is now weighted based on the significance of the sub-region. The weight of each sub-region is determined by employing the local variance estimate of the respective region, which represents the significance of the region. The final facial textural feature vector is obtained by concatenating the reduced dimensional weight sets of all the modules (sub-regions) of the face image. Experiments conducted on various popular face databases show promising performance of the proposed algorithm in varying lighting, expression, and partial occlusion conditions. Four databases were used for testing the performance of the proposed system: Yale Face database, Extended Yale Face database B, Japanese Female Facial Expression database, and CMU AMP Facial Expression database. The experimental results in all four databases show the effectiveness of the proposed system. Also, the computation cost is lower because of the simplified calculation steps. Research work is progressing to investigate the effectiveness of the proposed face recognition method on pose-varying conditions as well. It is envisaged that a multilane approach of trained frameworks at different pose bins and an appropriate voting strategy would lead to a good recognition rate in such situation.

Segmentation is the partitioning of an image into multiple regions (sets of pixels) according to a given criterion. The goal of segmentation is typically to locate objects of interest within the image. A wide variety of methods and algorithms are available to deal with the problem of the segmentation of images (Fu and Mui, 1981; Haralick and Shapiro, 1985; Pal and Pal, 1993). These methods can be broadly classified into four categories (Zhu and Yuille, 1996): • Edge-based techniques. • Region-based techniques. • Deformable models. • Global optimization approaches. The edge-based techniques are based on information about the boundaries of the image. Therefore, they try to locate the points in which abrupt changes occur in the levels of some property of the image, typically brightness (Canny, 1986; Rosenfeld and Kak, 1982). On the other hand, those methods that use spatial information of the image (e.g. color or texture) to produce the segmented image fit into the region-based techniques (Chen et al., 1992; Sahoo et al., 1988). These methods depend on the consistency of some relevant property in the different regions of the image. The deformable models are based on curves or surfaces defined within an image that moves due to the influence of certain forces. They can be classified into various groups, principally snakes, deformable templates and active contours (Blake and Isard, 1998; Kass et al., 1988). All of these techniques avoid the use of a global criterion when segmenting the image, which is contrary to the global optimization approaches (Geman and Geman, 1984; Kanungo et al., 1994). In this work a unified framework for image segmentation is proposed. The technique consists of two stages: a parallel seeded region growing algorithm (PSRG) and a region merging heuristic (RM). In Figure 1 the functional scheme of the proposed algorithm is shown. In the first step, different segmentations, performed in parallel, of the same input image are obtained. Each of these segmentations, which from now on will be called partial segmentations, are also generated in parallel using different number of processors. This way, the region growing algorithm uses a two level parallelism. Next, a region merging heuristic is applied to the oversegmented image created as result of combining the different initial

Image warping concerns about transforming an image from one spatial coordinate to another. It is widely used for the vidual effect of deforming and morphing images in the film industry. A number of warping techniques have been introduced, which are mainly based on the corresponding pair mapping of feature points, feature vectors or feature patches (mostly triangular or quadrilateral). However, very often warping of an image object with an arbitrary shape is required. This requires a warping technique which is based on boundary contour instead of feature points or feature line-vectors. In addition, when feature point or feature vector based techniques are used, approximation of the object boundary by using point or vectors is required. In this case, the matching process of the corresponding pairs will be very time consuming if a fine approximation is required. In this paper, we propose a contour-based warping technique for warping image objects with arbitrary shapes. The novel idea of the new method is the introduction of mathematical morphology to allow a more flexible control of image warping. Two morphological operators are used as contour determinators. The erosion operator is used to warp image contents which are inside a user specified contour while the dilation operation is used to warp image contents which are outside of the contour. This new method is proposed to assist further development of a semi-automatic motion morphing system when accompanied with robust feature extractors such as deformable template or active contour model.

Face recognition in biometrics is a difficult process because of factors including individual differences in facial emotions, illumination, resolution, facial rotation, and facial structure similarities. "A Combination of Cross Domain Features for Face Recognition" is what we suggest here. The benchmarked face images are considered, downsized to consistent 128x128 dimensions, and converted to grayscale. Face photos are compressed, and their quality is improved by using the Discrete Wavelet Transform (DWT). Initial characteristics that are unaffected by changes in an image's lighting are extracted using the Histogram of Oriented Gradients (HOG) on a compressed LL band of DWT. By connecting the LL band's output to the HOG's input, the DWT and HOG's LL bands are connected in a cascade. HOG's input and output are combined to create new, strong final features. The system's results when comparing test and database features are calculated using the Euclidean Distance (ED). It has been noted that the suggested system outperforms the current ones in terms of results.

LocalFace: Learning significant local features for deep face recognition

In this paper, singular value decomposition (SVD) and its stability, proportion invariance, and rotation invariance of image matrix are discussed in detail. Optimal approximation of the rank reduction matrix is studied. As for the Olivetti Research Laboratory (ORL) face database, experimental results demonstrate that it is effective and feasible that singular values of the face image matrix are used as recognition features in face recognition, and that singular value features take on separability, stability and independence, and are valid in feature extraction of face image.

Authentication of a user's identity is becoming a tough task for a system in today's era in which digital authentication becoming mandatory to satisfy the security of a system. Recognition failure of user's identity is one of the big concerns. This paper introduces an efficient mechanism to carry out the recognition of facial features in order to satisfy the authentication of a system. Earlier researches in this field have common constraints such as false acceptance and false rejection rate. The proposed method implements over video data on which deep reinforcement learning and K-nearest neighbors (KNN) have been applied to perform detection and recognize facial data accurately. The challenging task of this work is to correctly recognize the facial data under various disturbance and unprecedented noisy circumstances including bad illumination, blurring, inappropriate poses, angle, etc. The main objective of the model is to achieve a high recognition rate of facial data under different unwanted noise and attacks. Reinforcement learning is used to count the number of people in the proposed system. This concept of the KNN algorithm is used for classification based on Euclidean distance to achieve better recognition results. The average rate of accuracy for recognition is found to be 96.40%. The proposed model can be applied to an investigation into digital forensics.

As people's requirements for applications are getting higher and higher, the recognition of facial features has been paid more and more attention. The current facial feature recognition algorithm not only takes a long time, but also has problems such as large system resource consumption and long running time in practical applications. Based on this, the research proposes a multi-task face recognition algorithm by combining multi-task deep learning on the basis of convolutional neural network, and analyzes its performance in four dimensions of face identity, age, gender, and fatigue state. The experimental results show that the multi-task face recognition algorithm model obtained through layer-by-layer progression takes less time than other models and can complete more tasks in the same training time. At the same time, comparing the best model M44 with other algorithms in four dimensions, it is found that the Mean Absolute Error lowest is 3.53, and the highest Accuracy value is 98.3%. On the whole, the multi-task face recognition algorithm proposed in the study can recognize facial features efficiently and quickly. At the same time, its training time is short, the calculation speed is fast, and the recognition accuracy is much higher than other algorithms. It is applied to intelligent driving behavior. Analysis, intelligent clothing navigation and other aspects have strong practical significance.

Manifold learning aims to map the original data from a high-dimensional space into a low-dimensional feature space with possible better discriminative structure. In this paper, we propose a supervised manifold learning approach called SubManifold Individuality LEarning (SMILE). In SMILE, the linear subspace derived from the principal component analysis based on data with the same label is named as "the individual subspace", while the linear subspace learned from all data is defined as "the global subspace". For each data sample, the aim of SMILE is to enlarge the diversity between its reconstructed data from individual subspace and global subspace, respectively, so that the intrinsic character of each class can be stimulated in the feature space. SMILE also utilizes the Laplacian matrix to restrict the local structure of data in the low-dimensional feature space in order to preserve the locality of the high-dimensional data. The proposed method is validated in appearance-based face recognition problem on some typical facial image databases via extracting discriminative features. Experimental results show that the proposed approach can obtain the discriminative structure of facial manifold and extract better features for face recognition than other counterparts approaches.

Due to the current manual recording of students' classroom attendance by teachers, it is not conducive to later data statistics and analysis. In response to the attendance issue of such students in class, this article proposes a facial recognition algorithm based on FaceNet, which detects targets using multi-scale convolutional feature layers and is suitable for fast object detection; FaceNet maps faces to Euclidean space through deep learning and uses the distance between feature vectors to determine face similarity. Subsequently, a student classroom attendance management system was designed, integrating information collection, facial recognition, random roll call, and data management modules. FaceNet algorithm was used for facial feature extraction and recognition. The experimental results show that the system can effectively achieve classroom attendance management, but attention should be paid to the impact of camera resolution and face size on recognition accuracy. This method ultimately achieved the goal of recording students' classroom attendance, thus achieving the purpose of student classroom management.

Recently, automatic face recognition method has become one of the key issues in the field of pattern recognition and artificial intelligence. Typically, the face recognition process can be divided into three parts: the detection and recognition of human face, facial feature extraction and face recognition, and among which the facial feature extraction is the key to face recognition technology. In this paper, an extraction algorithm of face recognition feature, which is based on face recognition feature, is proposed. The experimental results based on the ORL face database demonstrate that this algorithm works well.

Data augmentation has been utilized to improve the accuracy and robustness of face recognition algorithms. However, most of the previous studies focused on using the augmentation techniques to enlarge the feature set, while the diversity produced by the virtual samples lacked sufficient attention. In sparse dictionary learning-based face recognition, $$l_1$$ -based sparse representation (SR) and SVD-based dictionary learning (DL) both have shown promising performance. How to utilize both of them in an enhanced training process by data augmentation is still unclear. This paper proposes a novel method that utilizes the sample diversity generated by data augmentation and integrates sparse representation with dictionary learning, to learn dual sparse features for robust face recognition. An additional feature set is created by applying sample augmentation via simply horizontal flipping of face images. The two sparse models, $$l_1$$ -based SR and SVD-based DL, are integrated together using our new proposed objective function. Under two-level fusion of both data and classifiers, the diversity between two training sets is well learned and utilized, in three implementations, to obtain a robust face recognition. After conducting extensive experiments on some popular facial datasets, we demonstrate the proposed method can produce a higher classification accuracy than many state-of-the-art algorithms, and it can be considered as a promising option for image-based face recognition. Our code is released at GitHub.

Humans are natural face recognition experts, far out-performing current automated face recognition algorithms, especially in naturalistic, “in the wild” settings. However, a striking feature of human face recognition is that we are dramatically better at recognizing highly familiar faces, presumably because we can leverage large amounts of past experience with the appearance of an individual to aid future recognition. Meanwhile, the analogous situation in automated face recognition, where a large number of training examples of an individual are available, has been largely underexplored, in spite of the increasing relevance of this setting in the age of social media. Inspired by these observations, we propose to explicitly learn enhanced face representations on a per-individual basis, and we present two methods enabling this approach. By learning and operating within person-specific representations, we are able to significantly outperform the previous state-of-the-art on PubFig83, a challenging benchmark for familiar face recognition in the wild, using a novel method for learning representations in deep visual hierarchies. We suggest that such person-specific representations aid recognition by introducing an intermediate form of regularization to the problem.

Selective generation of Gabor features for fast face recognition on mobile devices

Applications of summation invariant features to multi-region face recognition are explored in this work. Earlier, we have demonstrated the potential benefits of this approach. In this paper, we provide a systematic, thorough comparison of all the summation invariant features derived to-date, and propose a new multi-feature fusion approach to further improve the overall performance. We also identify summation invariant features that yield superior performance for face recognition applications. Special attention is given to the implementation of 3D summation invariants. Extensive experimental results with the FRGC (Face Recognition Grand Challenge) 2.0 data set confirms the advantage of summation invariant features for 3D face recognition.