Search

One potential way to enhance the performance of facial expression recognition (FER) is to augment the training set by increasing the number of samples. By incorporating multiple FER datasets, deep learning models can extract more discriminative features. However, the inconsistent labeling criteria and subjective biases found in annotated FER datasets can significantly hinder the recognition accuracy of deep learning models when handling mixed datasets. Effectively perform joint training on multiple datasets remains a challenging task. In this study, we propose a joint training method for training an FER model using multiple FER datasets. Our method consists of four steps: (1) selecting a subset from the additional dataset, (2) generating pseudo-continuous labels for the target dataset, (3) refining the labels of different datasets using continuous label mapping and discrete label relabeling according to the labeling criteria of the target dataset, and (4) jointly training the model using multi-task learning. We conduct joint training experiments on two popular in-the-wild FER benchmark databases, RAF-DB and CAER-S, while utilizing the AffectNet dataset as an additional dataset. The experimental results demonstrate that our proposed method outperforms the direct merging of different FER datasets into a single training set and achieves state-of-the-art performance on RAF-DB and CAER-S with accuracies of 92.24% and 94.57%, respectively. [ABSTRACT FROM AUTHOR]

Facial expression recognition (FER) accuracy is often affected by an individual’s unique facial characteristics. Recognition performance can be improved if the influence from these physical characteristics is minimized. Using video instead of single image for FER provides better results but requires extracting temporal features and the spatial structure of facial expressions in an integrated manner. We propose a new network called Typical Facial Expression Network (TFEN) to address both challenges. TFEN uses two deep two-dimensional (2D) convolutional neural networks (CNNs) to extract facial and expression features from input video. A facial feature decoupler decouples facial features from expression features to minimize the influence from inter-subject face variations. These networks combine with a 3D CNN and form a spatial-temporal learning network to jointly explore the spatial-temporal features in a video. A facial recognition network works as an adversarial network to refine the facial feature decoupler and the network performance by minimizing the residual influence of facial features after decoupling. The whole network is trained with an adversarial algorithm to improve FER performance. TFEN was evaluated on four popular dynamic FER datasets. Experimental results show TFEN achieves or outperforms the recognition accuracy of state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

In the existing millimeter-wave (mmWave) wireless positioning systems, the method based on sparse Bayesian learning (SBL) uses the channel sparsity to estimate the parameters required for positioning, such as angle of arrival (AOA) and time delay, but most existing SBL solutions only consider the angle sparsity. In this paper, we consider the joint sparsity of the angle domain and time delay domain to propose an improved SBL algorithm by using a new two-dimensional adaptive grid refinement method in the SBL framework. This algorithm solves the grid mismatch problem caused by the fixed grid in the traditional SBL method, and reduces the algorithm complexity of the off-grid SBL (OGSBL) algorithm. We also obtain the Cramér-Rao bound (CRB) of AOA, time delay and position estimation based on the mmWave multipath signals to analyze the estimation errors. Simulation results show that the performance of the proposed algorithm is better than existing algorithms and can approach CRB. [ABSTRACT FROM AUTHOR]

This article focuses on automatic inspection for the commonly used component called spring-wire socket. An automatic inspection system is built that adopts an endoscope to improve the imaging quality. To detect the low contrast targets in complex background, we adopt the pipeline of Faster R-CNN but with several improvements. The improved network specifies the targets in the form of quadrangular bounding box as opposed to previous methods that specify them by rectangular bounding box. With the quadrangular representation, additional shape and pose information is provided and unexpected overlaps and background disturbance could be avoided. In the network, an eight-dimensional (8-D) vector is designed to represent the quadrangular bounding box followed by the improved anchor mechanism in the region proposal network. And also, a novel overlap score calculation method is proposed. On the basis of the detection result, rules arisen from expertise are provided to determine the quality of the component in which way automatic quality inspection could be accomplished. The superiority of our detection network over existing ones is sufficiently demonstrated with the detection result of irregular targets in images captured in the industrial scenario. Meanwhile, successful inspection result proves that the system meets the industrial requirements in terms of both accuracy and speed and thus is of practical significance to industrial applications. [ABSTRACT FROM AUTHOR]

In many measurement applications using multicameras, there is often a nonoverlapping field of view (nFOV) between multicameras. It benefits greatly from having all of the cameras unified in a single coordinate frame by means of common spatial constraints. However, it is very difficult to establish common spatial constraints for accurate and quick calibration of the extrinsic parameters between multicameras in the case of long working distance, asymmetric working angle, or limited working space. To overcome these issues, we propose a flexible calibration method using a camera rig, which can be easily modeled as a hand–eye calibration problem and solved by only several sets of calibration images. To further improve the calibration accuracy, the camera intrinsic parameters, lens distortion coefficients, and extrinsic parameters are optimized simultaneously, similar to binocular calibration. However, this causes calculation instability of multiparameters. We extend the epipolar constraint to two images with an nFOV and add it into the optimization objective function together with the reprojection error, which ensures the basic consistency of intrinsic parameters before and after optimization, and reduce the fluctuation caused by the number of images involved in calibration. Experiments and application have proved that the proposed new methods are feasible and effective. [ABSTRACT FROM AUTHOR]