Contextual Information Aided Generative Adversarial Network for Low-Light Image Enhancement

Low-light image enhancement has been gradually becoming a hot research topic in recent years due to its wide usage as an important pre-processing step in computer vision tasks. Although numerous methods have achieved promising results, some of them still generate results with detail loss and local distortion. In this paper, we propose an improved generative adversarial network based on contextual information. Specifically, residual dense blocks are adopted in the generator to promote hierarchical feature interaction across multiple layers and enhance features at multiple depths in the network. Then, an attention module integrating multi-scale contextual information is introduced to refine and highlight discriminative features. A hybrid loss function containing perceptual and color component is utilized in the training phase to ensure the overall visual quality. Qualitative and quantitative experimental results on several benchmark datasets demonstrate that our model achieves relatively good results and has good generalization capacity compared to other state-of-the-art low-light enhancement algorithms.

The Research on Rejoining of the Oracle Bone Rubbings Based on Curve Matching

The rejoining of oracle bone rubbings is a fundamental topic for oracle research. However, it is a tough task to reassemble severely broken oracle bone rubbings because of detail loss in manual labeling, the great time consumption of rejoining, and the low accuracy of results. To overcome the challenges, we introduce a novel CFDA&CAP algorithm that consists of the Curve Fitting Degree Analysis (CFDA) algorithm and the Correlation Analysis of Pearson (CAP) algorithm. First, the orthogonalization system is constructed to extract local features based on the curve features analysis. Second, the global feature descriptor is depicted by using coordinate points sequences. Third, we screen candidate curves based on the features as well as the CFDA algorithm, so the search range of the candidates is narrowed down. Finally, image recommendation libraries for target curves are generated by adopting the CAP algorithm, and the rank for each target matching curve generates simultaneously for result evaluation. With experiments, the proposed method shows a good effect in rejoining oracle bone rubbings automatically: (1) it improves the average accuracy rate of curve matching up to 84%, and (2) for a low-resource task, the accuracy of our method has 25% higher accuracy than that of other methods.

Augmentation of Contextualized Concatenated Word Representation and Dilated Convolution Neural Network for Sentiment Analysis

Deep learning-based methodologies are significant to perform sentiment analysis on social media data. The valuable insights of social media data through sentiment analysis can be employed to develop intelligent applications. Among many networks, convolution neural networks (CNNs) are widely used in many conventional text classification tasks and perform a significant role. However, to capture long-term contextual information and address the detail loss problem, CNNs require stacking multiple convolutional layers. Also, the stacking of convolutional layers has issues requiring massive computations and the tuning of additional parameters. To solve these problems, in this paper, a contextualized concatenated word representation (CCWRs) is initialized from social media data based on text which is essential to misspelled and out of vocabulary words (OOV). In CCWRs, different word representation models, for example, Word2Vec, its optimized version FastText and Global Vectors, and GloVe, collectively create contextualized representations upon the sequence of input. Second, a three-layered dilated convolutional neural network (3D-CNN) is proposed that places dilated convolution kernels instead of conventional CNN kernels. Incorporating the extension in the receptive field’s size successfully solves the detail loss problem and achieves long-term context information with different dilation rates. Experiments on datasets demonstrate that the proposed framework achieves reliable results with the selection of numerous hyperparameter tuning and configurations for improved optimization leads to reduced computational resources and reliable accuracy.

Dynamic Line Scan Thermography Optimisation Using Response Surfaces Implemented on PVC Flat Bottom Hole Plates

Nowadays, performing dynamic line scan thermography (DLST) is very challenging, and therefore an expert is needed in order to predict the optimal set-up parameters. The parameters are mostly dependent on the material properties of the object to be inspected, but there are also correlations between the parameters themselves. The interrelationship is not always evident even for someone skilled in the art. Therefore, optimisation using response surface can give more insights in the interconnections between parameters, but also between the material properties and the variables. Performing inspections using an optimised parameter set will result in high contrast thermograms showing the size and shape of the defect accurately. Using response surfaces to predict the optimal parameter set enables to perform fast measurements without the need of extensive testing to find adequate measurement parameters. Differing from the optimal parameters will result in contrast loss or detail loss of the size and shape of the detected defect.

Blind Tone-Mapped Image Quality Assessment Based on Regional Sparse Response and Aesthetics

High dynamic range (HDR) images give a strong disposition to capture all parts of natural scene information due to their wider brightness range than traditional low dynamic range (LDR) images. However, to visualize HDR images on common LDR displays, tone mapping operations (TMOs) are extra required, which inevitably lead to visual quality degradation, especially in the bright and dark regions. To evaluate the performance of different TMOs accurately, this paper proposes a blind tone-mapped image quality assessment method based on regional sparse response and aesthetics (RSRA-BTMI) by considering the influences of detail information and color on the human visual system. Specifically, for the detail loss in a tone-mapped image (TMI), multi-dictionaries are first designed for different brightness regions and whole TMI. Then regional sparse atoms aggregated by local entropy and global reconstruction residuals are presented to characterize the regional and global detail distortion in TMI, respectively. Besides, a few efficient aesthetic features are extracted to measure the color unnaturalness of TMI. Finally, all extracted features are linked with relevant subjective scores to conduct quality regression via random forest. Experimental results on the ESPL-LIVE HDR database demonstrate that the proposed RSRA-BTMI method is superior to the existing state-of-the-art blind TMI quality assessment methods.

Inverse Halftoning Methods Based on Deep Learning and Their Evaluation Metrics: A Review

Inverse halftoning is an ill-posed problem that refers to the problem of restoring continuous-tone images from their halftone versions. Although much progress has been achieved over the last decades, the restored images still suffer from detail loss and visual artifacts. Recent studies show that inverse halftoning methods based on deep learning are superior to other traditional methods, and thus this paper aimed to systematically review the inverse halftone methods based on deep learning, so as to provide a reference for the development of inverse halftoning. In this paper, we firstly proposed a classification method for inverse halftoning methods on the basis of the source of halftone images. Then, two types of inverse halftoning methods for digital halftone images and scanned halftone images were investigated in terms of network architecture, loss functions, and training strategies. Furthermore, we studied existing image quality evaluation including subjective and objective evaluation by experiments. The evaluation results demonstrated that methods based on multiple subnetworks and methods based on multi-stage strategies are superior to other methods. In addition, the perceptual loss and the gradient loss are helpful for improving the quality of restored images. Finally, we gave the future research directions by analyzing the shortcomings of existing inverse halftoning methods.