ALBERT

Description: The range of light illumination in real scenes is very large, and ordinary cameras can only record a small part of this range, which is far lower than the range of human eyes’ perception of light. High-dynamic range (HDR) imaging technology that has appeared in recent years can record a wider range of illumination than the perceptual range of the human eye. However, the current mainstream HDR imaging technology is to capture multiple low-dynamic range (LDR) images of the same scene with different exposures and then merge them into one HDR image, which greatly increases the amount of data captured. The advent of single-pixel cameras (compressive imaging system) has proved the feasibility of obtaining and restoring image data based on compressive sensing. Therefore, this paper proposes a method for reduced-dimensional capture of high dynamic range images with compressive sensing, which includes algorithms for front end (capturing) and back end (processing). At the front end, the K-SVD dictionary is used to compressive sensing the input multiple-exposure image sequence, thereby reducing the amount of data transmitted to the back end. At the back end, the Orthogonal Matching Pursuit (OMP) algorithm is used to reconstruct the input multiple-exposure image sequence. A low-rank PatchMatch algorithm is proposed to merge the reconstructed image sequence to obtain an HDR image. Simulation results show that, under the premise of reducing the complexity of the front-end equipment and the amount of communication data between the front end and the back end, the overall system achieves a good balance between the amount of calculation and the quality of the HDR image obtained.

Description: Deep convolutional neural networks have been successfully applied to face detection recently. Despite making remarkable progress, most of the existing detection methods only localize each face using a bounding box, which cannot segment each face from the background image simultaneously. To overcome this drawback, we present a face detection and segmentation method based on improved Mask R-CNN, named G-Mask, which incorporates face detection and segmentation into one framework aiming to obtain more fine-grained information of face. Specifically, in this proposed method, ResNet-101 is utilized to extract features, RPN is used to generate RoIs, and RoIAlign faithfully preserves the exact spatial locations to generate binary mask through Fully Convolution Network (FCN). Furthermore, Generalized Intersection over Union (GIoU) is used as the bounding box loss function to improve the detection accuracy. Compared with Faster R-CNN, Mask R-CNN, and Multitask Cascade CNN, the proposed G-Mask method has achieved promising results on FDDB, AFW, and WIDER FACE benchmarks.

Description: In this paper, upper bound on the probability of maximum a posteriori (MAP) decoding error for systematic binary linear codes over additive white Gaussian noise (AWGN) channels is proposed. The proposed bound on the bit error probability is derived with the framework of Gallager’s first bounding technique (GFBT), where the Gallager region is defined to be an irregular high-dimensional geometry by using a list decoding algorithm. The proposed bound on the bit error probability requires only the knowledge of weight spectra, which is helpful when the input-output weight enumerating function (IOWEF) is not available. Numerical results show that the proposed bound on the bit error probability matches well with the maximum-likelihood (ML) decoding simulation approach especially in the high signal-to-noise ratio (SNR) region, which is better than the recently proposed Ma bound.