Dense Stereo Correspondence with Contrast Context Histogram, Segmentation-Based Two-Pass Aggregation and Occlusion Handling

Face recognition has lot of challenges in biometrics. The challenges are addressed effectively by local pattern descriptors. The idea of local descriptors is to determine the feature vector and then compute the difference between test images with training images by using similarity measure. Based on the observation, local approaches attained better performance rate than other approaches in face recognition. Due to that, researchers made a significant attention on local descriptors for face recognition. For nonlinear subspace, the local descriptors will achieve better result than holistic approach. Local pattern descriptor follows simple procedure to extract the facial features. The steps are face alignment, face representation, and matching. Face alignment is the first step of local descriptor, which is used to divide the image into several blocks. Face representation is used to extract the meaningful information from each region. This local feature extraction method carries discriminant information of the region; it will improve the classification rate and matching rate. Local descriptors extract the discriminant information from the neighbors by setting a threshold value as center pixel value, and it is not capable of extracting the detailed information from microstructure. Finally, matching by classification techniques or distance measure is used to identify or verify the person. The local pattern descriptors are more robust against pose, lighting, and scale variations. This chapter describes the various local pattern descriptors and shows the effectiveness of the descriptor. The results of local pattern descriptors are experimented on standard benchmark databases such as FERET, Extended Yale-B, ORL, CAS-PEAL, LFW, JAFFE, and Cohn–Kannade.

A Fuzzy clustering based fusion location method is presented for acoustic source direction estimation in underwater wireless sensor network. This method based on acoustic signal energy measurements taken at the received acoustic signal of a stationary sensor. Using fuzzy K-Means clustering, we could get centers of clusters with different orders. According to the new centers with their coordinates calculated, three least-square methods of source localization based on energy decay model(LS, WLS and F-WLS) are used to estimate the direction of the source. Numerous simulation results show that weighted least-square (WLS) method of localization outperforms least-square (LS) localization for different SNR. The experimental results shown that this direction method could also perform well in lower SNR. The average error of F-WLS yield the approximately same direction accuracy, but outperforms WLS in lower SNR. And for a certain network, the optimal order of clusters could be found not the bigger the better.

A novel and practical combined weighted (COM-W) method for target localization based on time difference of arrival (TDOA) is proposed in this paper. For 2-D situations with more than three nodes, the main idea of the proposed method is to obtain multiple preliminary localization results corresponding to the different three-node combinations first, and then use the weighted averaging technique based on the Cramer–Rao lower bound (CRLB) to obtain the final estimation. Considering target localization with a set of fixed-positioning nodes employing TDOA measurements as an example, the performance of the proposed method is evaluated by both simulations and acoustic indoor positioning experiments. The experimental results show that the COM-W method is a closed-form and computationally efficient method. It has an excellent positioning performance under both narrow and square geometric arrangements, specifically in the central cross-shaped area and in the vicinity of the nodes. Compared to the three classic weighted linear least squares (WLS)-based positioning methods, the proposed COM-W method is less sensitive to the measurement noise and the NLOS environment. The proposed method has an important application value for the realization of a TDOA-based indoor target positioning system.

Rotation change is widespread in many computer vision applications. Robustness in the rotation is an important capability in evaluating local descriptors. We proposed a fast and rotation-robust local binary descriptor using polar location, called rotation-robust local difference binary descriptor (RLDB). The code of RLDB is generated by a binary test of average intensity, radial gradient, and tangent gradient of grid cells on multiple log-polar grids, which will save the presented local descriptors from spending extra time dealing with rotation changes. To speed up the computation, two tricks are proposed in the construction of the descriptor: one is using a lookup table mapping discrete polar coordinates with image pixel locations; the other is rebuilding the integral image in polar coordinates. Experimental results demonstrate that the presented descriptor is shown to be more robust in large rotation changes and viewpoint changes than some state-of-the-art local descriptors. At the same time, they also have comparable distinctive performance and construction speed.

Depth estimation has vital importance in various applications like Advance driver assistance systems, Robot navigation, 3D movies, etc. Depth information is represented using disparity maps which are generated from various stereo correspondence algorithms. This paper proposes an implementation of Semi global block matching algorithm on raspberry pi using python. The proposed algorithm generates a disparity map by block wise matching and smoothness constraint. The novel algorithm is compared with other algorithms on the standard dataset. It provides an efficient accuracy over local methods. The real time implementation of SGM algorithm on the system uses a block size of 21 × 21 for images having resolution 1280×720P. The system provides faster processing time for the proposed algorithm.

Discussions on phase-reconstructing algorithms for 3D digitizing structure-light profilometry

In low light condition, color (RGB) images captured by visible sensors suffer from severe noise causing loss of colors and textures. However, near infrared (NIR) images captured by NIR sensors are robust to noise even in low light condition without color. Since RGB and NIR images are complementary in low light condition, the multispectral fusion of RGB and NIR images provides a viable solution to low light imaging. In this paper, we propose multispectral fusion of RGB and NIR images using weighted least squares (WLS) and convolution neural networks (CNNs). We combine traditional WLS filtering for layer decomposition and denoising with latest deep learning for image enhancement and texture transfer into the multispectral fusion to take both advantages. We build two networks based on CNN: image enhancement network (IEN) for image enhancement and texture transfer network (TTN) for NIR texture transfer. First, we perform RGB image denoising based on WLS filtering and generate the base layer. We use both RGB and NIR images for WLS filtering as weights to filter out noise in low light RGB images. Second, we conduct IEN to enhance contrast of the base layer. Third, we perform TTN to deliver NIR details completely and naturally to the fusion result. The combination of WLS, TTN and IEN leads to noise reduction, contrast enhancement, and detail preservation in fusion. Experimental results show that the proposed method achieves good performance in both noise reduction and detail transfer as well as outperforms state-of-the-art methods in terms of visual quality and quantitative measurements.

Infrared and visible image fusion based on visual saliency map and weighted least square optimization

Combined non-contact coordinate measurement system and calibration method

This study introduces an information granular-based fuzzy radial basis function neural networks (FRBFNN) based on multiobjective optimization and weighted least square (WLS). An improved multiobjective space search algorithm (IMSSA) is proposed to optimize the FRBFNN. In the design of FRBFNN, the premise part of the rules is constructed with the aid of Fuzzy C-Means (FCM) clustering while the consequent part of the fuzzy rules is developed by using four types of polynomials, namely constant, linear, quadratic, and modified quadratic. Information granulation realized with C-Means clustering helps determine the initial values of the apex parameters of the membership function of the fuzzy neural network. To enhance the flexibility of neural network, we use the WLS learning to estimate the coefficients of the polynomials. In comparison with ordinary least square commonly used in the design of fuzzy radial basis function neural networks, WLS could come with a different type of the local model in each rule when dealing with the FRBFNN. Since the performance of the FRBFNN model is directly affected by some parameters such as e.g., the fuzzification coefficient used in the FCM, the number of rules and the orders of the polynomials present in the consequent parts of the rules, we carry out both structural as well as parametric optimization of the network. The proposed IMSSA that aims at the simultaneous minimization of complexity and the maximization of accuracy is exploited here to optimize the parameters of the model. Experimental results illustrate that the proposed neural network leads to better performance in comparison with some existing neurofuzzy models encountered in the literature.

Utilizing the optical characteristics of the target for detection and localization does not require actively emitting signals and has the advantage of strong concealment. Once the optoelectronic platform mounted on the unmanned aerial vehicle (UAV) detects the target, the vector pointing to the target in the camera coordinate system can estimate the angle of arrival (AOA) of the target relative to the UAV in the Earth-centered Earth-fixed (ECEF) coordinate system through a series of rotation transformations. By employing two UAVs and the corresponding AOA measurements, passive localization of an unknown target is possible. To achieve high-precision target localization, this paper investigates the following three aspects. Firstly, two error transfer models are established to estimate the noise distributions of the AOA and the UAV position in the ECEF coordinate system. Next, to reduce estimation errors, a weighted least squares (WLS) estimator is designed. Theoretical analysis proves that the mean squared error (MSE) of the target position estimation can reach the Cramér–Rao lower bound (CRLB) under the condition of small noise. Finally, we study the optimal placement problem of two coplanar UAVs relative to the target based on the D-optimality criterion and provide explicit conclusions. Simulation experiments validate the effectiveness of the localization method.

This paper proposes a generalized locally weighted group method of data handling (G-LWGMDH) based on evolutionary algorithm (EA) for short-term load forecasting. The locally weighted group method of data handling (LWGMDH) can be derived by combining GMDH with the local regression method and weighted least squares (WLS) regression. The connectivity configuration in the G-LWGMDH is not limited to adjacent layers, unlike the conventional GMDH. Moreover, each node in the G-LWGMDH network has a different number of inputs and a different polynomial order. The performance of the G-LWGMDH depends on choosing these factors before the network is constructed. Therefore, EA is used in this paper to optimally select these factors. In the proposed method, a new encoding scheme is presented, where each chromosome represents the structure of the whole network. The weighting functions bandwidth, the polynomial order for each node, the number of inputs for each node, and the input variables chosen to each node are encoded as a chromosome. The performance of the proposed method (EA-based G-LWGMDH) is evaluated using two real-world datasets. The results show that the proposed method provides a much better prediction performance in comparison with other methods employing the same data.

This paper investigates local descriptor methods utilizing color images instead of grayscale images to improve the uniqueness of the local descriptors. A color model was utilized in order to be invariant to illumination condition changes. Two local descriptor methods, namely color local descriptor and hybrid local descriptor methods, were developed. Results from the experiments conducted show that these methods are more robust against a variety of image transformation and illumination condition changes compared to existing methods.

Fingerprint liveness detection is an effective way to ensure the security and reliability of fingerprint recognition algorithms against spoof fingerprint attacks. Local descriptors are one of the most widely studied fingerprint liveness detection algorithms. However, the performance of simplex local descriptors or simple voting models among multiple descriptors still can-not achieve satisfactory accuracy, robustness, and applicability. This paper proposes a 2-layer parallel Support Vector Machine (SVM) network to improve the classification performance of local descriptors and achieve 95.32% accuracy on the LivDet datasets (2009, 2011, 2013, and 2015). The experimental results and theoretical analysis indicate that the proposed 2-layer parallel SVM network based on aggregated local descriptors shows better detection accuracy and model robustness against adversarial attacks compared with simplex descriptors and state-of-the-art neural network structures. Besides, the 2-layer parallel SVM network can save training time through parallel computing, and achieve extremely high accuracy and reliability through ultra-high-dimensional descriptor classification.

Local descriptor matching is the most overlooked stage of the three stages of the local descriptor process, and this paper proposes a new method for matching local descriptors based on support vector machines. Results from experiments show that the developed method is more robust for matching local descriptors for all image transformations considered. The method is able to be integrated with different local descriptor methods, and with different machine learning algorithms and this shows that the approach is sufficiently robust and versatile.