An Efficient Super-Resolution Single Image Network using Sharpness Loss Metrics for Iris

Investigating single image super-resolution algorithm with deep learning using convolutional neural network for chest digital tomosynthesis

In recent years, deep neural networks (DNNs) have achieved great successes in many areas, such as cognitive computation, pattern recognition, and computer vision. Although many hand-crafted deep networks have been proposed in the literature, designing a well-behaved neural network for a specific application requires high-level expertise yet. Hence, the automatic architecture design of DNNs has become a challenging and important problem. In this paper, we propose a new reinforcement learning method, whose action policy is to select neural blocks and construct deep networks. We define the action search space with three types of neural blocks, i.e., dense block, residual block, and inception-like block. Additionally, we have also designed several variants for the residual and inception-like blocks. The optimal network is automatically learned by a Q-learning agent, which is iteratively trained to generate well-performed deep networks. To evaluate the proposed method, we have conducted experiments on three datasets, MNIST, SVHN, and CIFAR-10, for image classification applications. Compared with existing hand-crafted and auto-generated neural networks, our auto-designed neural network delivers promising results. Moreover, the proposed reinforcement learning algorithm for deep networks design only runs on one GPU, demonstrating much higher efficiency than most of the previous deep network search approaches.

There has been a remarkable growth in computer vision due to the introduction of deep convolutional neural network. In most electronic imaging applications, images with high resolution are desired and cannot be ignored in many crucial applications. Super-resolution is a technique that enhances the resolution of images from the low-resolution input. Even thought, the performance of pattern recognition in computer vision will be improved if high resolution image is provided. The current super-resolution models based convolutional neural network has shown great performance, and also could outpace the other models. Depth in of CNN models is crucial importance for image super-resolution. However, the deeper networks based SR techniques are more difficult to train. To address these problems we propose a very deep residual network which comprises residual in residual structure to form a very deep network. In particular, the proposed model consists of several residual units with long skip connection. The proposed model allows low-frequency information to be bypassed through multiple skip connections, and the high-frequency information will be centralized in the main network. Extensive experiments show that our proposed model achieves better performance against state-of-the-art methods.

Predictive analysis on cellular traffic is important for the control and monitoring of wireless networks. Cellular traffic prediction is a challenging problem due to the non- stationarity and dynamic spatial-temporal correlation of the traffic. In this paper, we address the problem of accurate traffic prediction in a base station by proposing a deep neural network called RAConv. Its structure includes residual network, attention mechanism, and deep convolutional network. In the proposed architecture, a deep 3D residual convolutional network (ResConv3D) with three residual blocks are employed to learn the local spatial-temporal features. An attention-aided convolutional long short-term memory network (AConvLSTM) is then used to capture the long-term spatial-temporal dependencies. The use of the attention modules enable the network to focus on the most important spatial-temporal information. We evaluate the performance of the proposed RAConv network using a dataset provided by a Canadian wireless service provider. We consider the traffic prediction on two time scales (i.e., hourly and daily), which exhibit different spatial-temporal dependency patterns. Experimental results show that the proposed RAConv network can achieve accurate prediction under both time scales. Results also show that our proposed network provides a lower root-mean-square error (RMSE) than the conventional ConvLSTM baseline scheme.

Seeing through disguise: Getting to know you with a deep convolutional neural network

Higher performance is the eternal purpose for super-resolution (SR) methods to pursue. Since the deep convolution neural network is introduced into this issue successfully, many SR methods have achieved impressive results. To further improve the accuracy that current SR methods have achieved, we propose a high-accuracy deep convolution network (HDCN). In this article, deeper network structure is deployed for reconstructing images with a fixed upscaling factor and the magnification becomes alternative by cascading HDCN. \(L_2\) loss function is substituted by a more robust one for reducing the blurry prediction. In addition, gradual learning is adopted for accelerating the rate of convergence and compacting the training process. Extensive experiment results prove the effectiveness of these ingenious strategies and demonstrate the higher-accuracy of proposed model among state-of-the-art SR methods.

Existing single image super-resolution (SR) algorithms based on convolution neural networks (CNNs) have achieved usable visual results.However, they often encounter artifacts and blurring, particularly at large scaling factors (e.g., 4, 8), due to significant loss of high-frequency information.To address these challenges, we propose a novel high-low frequency differentiation dynamic Laplacian pyramid network (HFDDLap).Our approach introduces a learnable high-low frequency differentiation convolution (HLC) within high-low frequency differentiation residual channel attention blocks (HL-RCAB) to effectively capture and differentiate high-and low-frequency components, enhancing detail preservation.Additionally, we employ a dynamic deconvolution (DDC) that adaptively generates upsampling kernels based on input features, improving reconstruction accuracy by reducing feature distortion.Extensive experiments on 4 and 8 SR demonstrate that our proposed method effectively reconstructs edge details, produces satisfactory SR results and outperforms some state-of-the-art (SOTA) methods in terms of evaluation metrics.

Rectified linear units (ReLU) are known to be effective in many deep learning methods. Inspired by linear-mapping technique used in other super-resolution (SR) methods, we reinterpret ReLU into point-wise multiplication of an identity mapping and a switch, and finally present a novel nonlinear unit, called a selection unit (SU). While conventional ReLU has no direct control through which data is passed, the proposed SU optimizes this on-off switching control, and is therefore capable of better handling nonlinearity functionality than ReLU in a more flexible way. Our proposed deep network with SUs, called SelNet, was top-5th ranked in NTIRE2017 Challenge, which has a much lower computation complexity compared to the top-4 entries. Further experiment results show that our proposed SelNet outperforms our baseline only with ReLU (without SUs), and other state-of-the-art deep-learning-based SR methods.

Single image super-resolution using a deep encoder–decoder symmetrical network with iterative back projection

Traditional power quality disturbances(PQDs) recognition methods are based on selecting features manually and then use classifiers to classify. For huge amounts of data, this method has the problem of insufficient features or redundant features, which leads to low recognition accuracy. With the development of deep learning technology, this paper proposes a PQDs identification method based on a deep residual network. This method links the two sets of convolutional layers in the traditional convolutional network into a residual block through short-cut. Then, it learns layer by layer through residual blocks, acquiring the deep features of data. Thus it realizes the identity mapping of the redundant layer by short-line connections to solve the network degradation problem of deep networks, and reduces the difficulty of network training. Finally, the softmax layer is used for classification. In order to test the anti-noise ability of the network, the deep residual network model is trained with the data added with Gaussian white noise. Simulation results show that, comparing with ordinary convolutional networks, the method proposed can accurately identify 7 types of single disturbances and 5 types of composite disturbances in different noise conditions. Furthermore, it has higher robustness and better network convergence speed.

Air pollution has a serious impact on our daily life, and how to quickly and easily measure the air pollution level without any expensive equipment is a quite challenging task. This paper proposes an air pollution estimation method using deep hybrid convolutional neural network from a single image, e.g., captured by a smartphone. The captured image is input to the main network, a very deep network, which solves the side effects of increased depth (degradation issues) by skip connection. This can improve network performance by simply increasing the depth of the network. Dark channel map is computed and fed into a secondary network to enrich the features with implicit representation. We have collected 1575 images of different scenes with different values of PM 2 . 5 to train the network in the end-to-end fusion mode. Experimental results on synthetic dataset and real captured dataset demonstrate that our method achieves excellent performance on classification of air pollution levels from a single captured image.

Convolutional Neural Networks (CNNs) have demonstrated great results for the single-image super-resolution (SISR) problem. Currently, most CNN algorithms promote deep and computationally expensive models to solve SISR. However, we propose a novel SISR method that uses relatively less number of computations. On training, we get group convolutions that have unused connections removed. We have refined this system specifically for the task at hand by removing unnecessary modules from original CondenseNet. Further, a reconstruction network consisting of deconvolutional layers has been used in order to upscale to high resolution. All these steps significantly reduce the number of computations required at testing time. Along with this, bicubic upsampled input is added to the network output for easier learning. Our model is named SRCondenseNet. We evaluate the method using various benchmark datasets and show that it performs favourably against the state-of-the-art methods in terms of both accuracy and number of computations required.

Lightweight single image super-resolution with attentive residual refinement network

Text recognition in natural scene images is a challenging problem in computer vision. Different than the optical character recognition (OCR), text recognition in natural scene images is more complex due to variations in text size, colors, fonts, orientations, complex backgrounds, occlusion, illuminations and uneven lighting conditions. In this paper, we propose a segmentation-free method based on a deep convolutional recurrent neural network to solve the problem of cursive text recognition, particularly focusing on Urdu text in natural scenes. Compared to the non-cursive scripts, Urdu text recognition is more complex due to variations in the writing styles, several shapes of the same character, connected text, ligature overlapping, stretched, diagonal and condensed text. The proposed model gets a whole word image as an input without pre-segmenting into individual characters, and then transforms into the sequence of the relevant features. Our model is based on three components: a deep convolutional neural network (CNN) with shortcut connections to extract and encode the features, a recurrent neural network (RNN) to decode the convolutional features, and a connectionist temporal classification (CTC) to map the predicted sequences into the target labels. To increase the text recognition accuracy further, we explore deeper CNN architectures like VGG-16, VGG-19, ResNet-18 and ResNet-34 to extract more appropriate Urdu text features, and compare the recognition results. To conduct the experiments, a new large-scale benchmark dataset of cropped Urdu word images in natural scenes is developed. The experimental results show that the proposed deep CRNN network with shortcut connections outperform than other network architectures. The dataset is publicly available and can be downloaded from <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://data.mendeley.com/datasets/k5fz57zd9z/1</uri> .

In this paper, we propose a new image super-resolution (SR) approach based on a convolutional neural network (CNN), which jointly learns the feature extraction, upsampling, and high-resolution (HR) reconstruction modules, yielding a completely end-to-end trainable deep CNN. However, directly training such a deep network in an end-to-end fashion is challenging, which takes a longer time to converge and may lead to sub-optimal results. To address this issue, we propose to jointly train an ensemble of deep and shallow networks. The shallow network with weaker learning capability restores the main structure of the image content, while the deep network with stronger representation power captures the high-frequency details. Since the shallow network is much easier to optimize, it significantly lowers the difficulty of deep network optimization during joint training. To further ensure more accurate restoration of HR images, the high-frequency details are reconstructed in a multi-scale manner to simultaneously incorporate both short- and long-range contextual information. The proposed method is extensively evaluated on widely adopted data sets and compares favorably against state-of-the-art methods. In-depth ablation studies are conducted to verify the contributions of different network designs to image SR, providing additional insights for future research.