Explore the vast range of titles available.

Fourier single-pixel imaging (FSI) employs Fourier basis patterns for encoding spatial information and is capable of reconstructing high-quality two-dimensional and three-dimensional images. Fourier-domain sparsity in natural scenes allows FSI to recover sharp images from undersampled data. The original FSI demonstration, however, requires grayscale Fourier basis patterns for illumination. This requirement imposes a limitation on the imaging speed as digital micro-mirror devices (DMDs) generate grayscale patterns at a low refreshing rate. In this paper, we report a new strategy to increase the speed of FSI by two orders of magnitude. In this strategy, we binarize the Fourier basis patterns based on upsampling and error diffusion dithering. We demonstrate a 20,000 Hz projection rate using a DMD and capture 256-by-256-pixel dynamic scenes at a speed of 10 frames per second. The reported technique substantially accelerates image acquisition speed of FSI. It may find broad imaging applications at wavebands that are not accessible using conventional two-dimensional image sensors.

It is difficult to identify the historical period in which some ancient murals were created because of damage due to artificial and/or natural factors; similarities in content, style, and color among murals; low image resolution; and other reasons. This study proposed a transfer learning-fused Inception-v3 model for dynasty-based classification. First, the model adopted Inception-v3 with frozen fully connected and softmax layers for pretraining over ImageNet. Second, the model fused Inception-v3 with transfer learning for parameter readjustment over small datasets. Third, the corresponding bottleneck files of the mural images were generated, and the deep-level features of the images were extracted. Fourth, the cross-entropy loss function was employed to calculate the loss value at each step of the training, and an algorithm for the adaptive learning rate on the stochastic gradient descent was applied to unify the learning rate. Finally, the updated softmax classifier was utilized for the dynasty-based classification of the images. On the constructed small datasets, the accuracy rate, recall rate, and F1 value of the proposed model were 88.4%, 88.36%, and 88.32%, respectively, which exhibited noticeable increases compared with those of typical deep learning models and modified convolutional neural networks. Comparisons of the classification outcomes for the mural dataset with those for other painting datasets and natural image datasets showed that the proposed model achieved stable classification outcomes with a powerful generalization capacity. The training time of the proposed model was only 0.7 s, and overfitting seldom occurred.

How to effectively protect ancient murals has become an urgent and important problem. Digital image processing developments have made it possible to repair damaged murals to a certain extent. This study proposes a consistency-enhanced generative adversarial network (GAN) model to repair missing mural areas. First, the convolutional layer from a fully convolutional network (FCN) is used to extract deep image features; then, through deconvolution, the features are mapped to the size of the original image and the repaired image is output, thereby completing the regenerative network. Next, global and local discriminant networks are applied to determine whether the repaired mural image is “authentic” in terms of both the modified and unmodified areas. In adversarial learning, the generative and discriminant network models are optimized to better complete the mural repair. The network introduces a dilated convolution that increases the convolution kernel’s receptive field. Each network convolutional layer joins in the batch standardization (BN) process to accelerate network convergence and increase the number of network layers and adopts a residual module to avoid the vanishing gradient problem and further optimizing the network. Compared with existing mural restoration algorithms, the proposed algorithm increases the peak signal-to-noise ratio (PSNR) by an average of 6–8 dB and increases the structural similarity (SSIM) index by 0.08–0.12. From a visual perspective, this algorithm successfully complements mural images with complex textures and large missing areas; thus, it may contribute to digital restorations of ancient murals.

In this study, a convolutional neural network with threshold optimization (CNN-THOP) is proposed to solve the issue of overlabeling or downlabeling arising during the multilabel image annotation process in the use of a ranking function for label annotation along with prediction probability. This model fuses the threshold optimization algorithm to the CNN structure. First, an optimal model trained by the CNN is used to predict the test set images, and batch normalization (BN) is added to the CNN structure to effectively accelerate the convergence speed and obtain a group of prediction probabilities. Second, threshold optimization is performed on the obtained prediction probability to derive an optimal threshold for each class of labels to form a group of optimal thresholds. When the prediction probability for this class of labels is greater than or equal to the corresponding optimal threshold, this class of labels is used as the annotation result for the image. During the annotation process, the multilabel annotation for the image to be annotated is realized by loading the optimal model and the optimal threshold. Verification experiments are performed on the MIML, COREL5K, and MSRC datasets. Compared with the MBRM, the CNN-THOP increases the average precision on MIML, COREL5K, and MSRC by 27%, 28% and 33%, respectively. Compared with the E2E-DCNN, the CNN-THOP increases the average recall rate by 3% on both COREL5K and MSRC. The most precise annotation effect for CNN-THOP is observed on the MIML dataset, with a complete matching degree reaching 64.8%.

With the rapid development of the Internet and the increasing popularity of mobile devices, the availability of digital image resources is increasing exponentially. How to rapidly and effectively retrieve and organize image information has been a hot issue that urgently must be solved. In the field of image retrieval, image auto-annotation remains a basic and challenging task. Targeting the drawbacks of the low accuracy rate and high memory resource consumption of current multilabel annotation methods, this study proposed a CM-supplement network model. This model combines the merits of cavity convolutions, Inception modules and a supplement network. The replacement of common convolutions with cavity convolutions enlarged the receptive field without increasing the number of parameters. The incorporation of Inception modules enables the model to extract image features at different scales with less memory consumption than before. The adoption of the supplement network enables the model to obtain the negative features of images. After 100 training iterations on the PASCAL VOC 2012 dataset, the proposed model achieved an overall annotation accuracy rate of 94.5%, which increased by 10.0 and 1.1 percentage points compared with the traditional convolution neural network (CNN) and double-channel CNN (DCCNN). After stabilization, this model achieved an accuracy of up to 96.4%. Moreover, the number of parameters in the DCCNN was more than 1.5 times that of the CM-supplement network. Without increasing the amount of memory resources consumed, the proposed CM-supplement network can achieve comparable or even better annotation effects than a DCCNN.

Single-pixel imaging techniques enable to capture a scene without a direct line of sight to the object, but high-quality imaging has been proven challenging especially in the presence of noisy environmental illumination. Here we present a single-pixel imaging technique that can achieve high-quality images by acquiring their Fourier spectrum. We use phase-shifting sinusoid structured illumination for the spectrum acquisition. Applying inverse Fourier transform to the obtained spectrum yields the desired image. The proposed technique is capable of capturing a scene without a direct view of it. Thus, it enables a feasible placement of detectors, only if the detectors can collect the light signals from the scene. The technique is also a compressive sampling like approach, so it can reconstruct an image from sub-Nyquist measurements. We experimentally obtain clear images by utilizing a detector not placed in direct view of the imaged scene even with noise introduced by environmental illuminations. Single-pixel imaging can capture a scene without a direct line of sight to the object but high-quality imaging has proven challenging. Here, by acquiring their Fourier spectrum, Zhang et al . demonstrate indirect, high-quality single-pixel imaging in the presence of noisy environmental illumination.

Fourier single-pixel imaging (FSI) is a branch of single-pixel imaging techniques. It allows any image to be reconstructed by acquiring its Fourier spectrum by using a single-pixel detector. FSI uses Fourier basis patterns for structured illumination or structured detection to acquire the Fourier spectrum of image. However, the spatial resolution of the reconstructed image mainly depends on the number of Fourier coefficients sampled. The reconstruction of a high-resolution image typically requires a number of Fourier coefficients to be sampled. Consequently, a large number of single-pixel measurements lead to a long data acquisition time, resulting in imaging of a dynamic scene challenging. Here we propose a new sampling strategy for FSI. It allows FSI to reconstruct a clear and sharp image with a reduced number of measurements. The key to the proposed sampling strategy is to perform a density-varying sampling in the Fourier space and, more importantly, the density with respect to the importance of Fourier coefficients is subject to a one-dimensional Gaussian function. The final image is reconstructed from the undersampled Fourier spectrum through compressive sensing. We experimentally demonstrate the proposed method is able to reconstruct a sharp and clear image of 256 × 256 pixels with a sampling ratio of 10%. The proposed method enables fast single-pixel imaging and provides a new approach for efficient spatial information acquisition.

In digital holography, reconstructed image quality can be primarily limited due to the inability of a single small aperture sensor to cover the entire field of a hologram. The use of multi-sensor arrays in synthetic aperture digital holographic imaging technology contributes to overcoming the limitations of sensor coverage by expanding the area for detection. However, imaging accuracy is affected by the gap size between sensors and the resolution of sensors, especially when dealing with a limited number of sensors. An image reconstruction method is proposed that combines physical constraint characteristics of the imaging object with a score-based diffusion model, aiming to enhance the imaging accuracy of digital holography technology with extremely sparse sensor arrays. Prior information of the sample is learned by the neural network in the diffusion model to obtain a score function, which alternately constrains the iterative reconstruction process with the underlying physical model. The results demonstrate that the structural similarity and peak signal-to-noise ratio of the reconstructed images using this method are higher than the traditional method, along with a strong generalization ability.

The rapid classification of ancient murals is a pressing issue confronting scholars due to the rich content and information contained in images. Convolutional neural networks (CNNs) have been extensively applied in the field of computer vision because of their excellent classification performance. However, the network architecture of CNNs tends to be complex, which can lead to overfitting. To address the overfitting problem for CNNs, a classification model for ancient murals was developed in this study on the basis of a pretrained VGGNet model that integrates a depth migration model and simple low-level vision. First, we utilized a data enhancement algorithm to augment the original mural dataset. Then, transfer learning was applied to adapt a pretrained VGGNet model to the dataset, and this model was subsequently used to extract high-level visual features after readjustment. These extracted features were fused with the low-level features of the murals, such as color and texture, to form feature descriptors. Last, these descriptors were input into classifiers to obtain the final classification outcomes. The precision rate, recall rate and F1-score of the proposed model were found to be 80.64%, 78.06% and 78.63%, respectively, over the constructed mural dataset. Comparisons with AlexNet and a traditional backpropagation (BP) network illustrated the effectiveness of the proposed method for mural image classification. The generalization ability of the proposed method was proven through its application to different datasets. The algorithm proposed in this study comprehensively considers both the high- and low-level visual characteristics of murals, consistent with human vision.