Search

At night or in other low‐illumination environments, optical imaging devices cannot capture details and color information in images accurately because of the reduced number of photons captured and the low signal‐to‐noise ratio. Consequently, the image is very noisy with low contrast and inaccurate color information, which affects human visual perception and creates significant challenges in computer vision tasks. Low‐light image enhancement has great research value because it aims to reduce image noise and improve image quality. In this study, we propose an LBP‐based progressive feature aggregation network (P‐FANet) for low‐light image enhancement. The LBP feature has insensitivity to illumination, and it contains rich texture information. In the network, we input the LBP feature into each iteration of the network in an accompanying manner, which helps to restore some detailed information of the low‐light image. First, we input the low‐light image into the dual attention mechanism model to extract global features. Second, the extracted different features enter the feature aggregation module (FAM) for feature fusion. Third, we use the recurrent layer to share the features extracted at different stages, and use the residual layer to further extract deeper features. Finally, the enhanced image is output. The rationality of the method in this study has been verified through ablation experiments. Many experimental results show that the method in this study has greater advantages in subjective and objective evaluations compared with many other advanced methods.

Low-light images have low brightness and contrast, which presents a huge obstacle to computer vision tasks. Low-light image enhancement is challenging because multiple factors (such as brightness, contrast, artifacts, and noise) must be considered simultaneously. In this study, we propose a neural network—a progressive-recursive image enhancement network (PRIEN)—to enhance low-light images. The main idea is to use a recursive unit, composed of a recursive layer and a residual block, to repeatedly unfold the input image for feature extraction. Unlike in previous methods, in the proposed study, we directly input low-light images into the dual attention model for global feature extraction. Next, we use a combination of recurrent layers and residual blocks for local feature extraction. Finally, we output the enhanced image. Furthermore, we input the global feature map of dual attention into each stage in a progressive way. In the local feature extraction module, a recurrent layer shares depth features across stages. In addition, we perform recursive operations on a single residual block, significantly reducing the number of parameters while ensuring good network performance. Although the network structure is simple, it can produce good results for a range of low-light conditions. We conducted experiments on widely adopted datasets. The results demonstrate the advantages of our method compared with other methods, from both qualitative and quantitative perspectives.

Depth of field is one of the critical reasons to limit the richness of image information. Usually, in a scene with multiple targets, when the distance between each target and the lens is different, the clear scene image can be get within a certain distance range. This situation restricts the further image processing, such as semantic segmentation, object recognition and 3D reconstruction. Multi‐focus image fusion uses two or more images focused on different targets to fuse scene information, which can solve this problem to a great extent. In general, two or more multi‐focus images can cover almost all near/far targets. The fusion of more than two multi‐focus images can be accomplished by cascading the fusion results of the previous two images and the next image to be processed many times. Therefore, the paper focus on the fusion of two multi‐focus images. Inspired by this, new Pseudo‐Siamese neural network with several residual atrous convolution pyramids with multi‐level perception ability to perceive the multi‐level features and consistency relations of multi‐focus image pairs is proposed, and multi‐layer residual blocks are used to fuse the extracted features. In this process, the residual of the groundtruth and the generated image will be learned. Finally, a fully focused image without blur will be generated. After several ablation experiments and comparison experiments with other methods, the results show that the performance of the method proposed in this paper is state‐of‐the‐art, and overall better than other methods, which are advanced.

Owing to the influence of light absorption and scattering in underwater environments, underwater images exhibit color deviation, low contrast and detail blur, and other degradations. This paper proposes an underwater image enhancement method combining a residual convolution network, local binary pattern (LBP), and self‐attention mechanism. The LBP operator processes the input underwater images. The LBP feature images and underwater images thus obtained constitute the network input. The network consists of three modules: a color correction module to remove the color deviation in underwater images, detail repair module to restore the integrity of details, and an LBP auxiliary enhancement module for global enhancement of image details. The correction and repair modules generate the correct color image and detailed supplement images, respectively. The final‐result image is obtained by superpositioning the two generated images. The experimental results confirm that our method can reproduce the bright colors and complete details of the visual effect, showing a significant improvement over other advanced methods in quantitative evaluation.

Remote sensing images with high spatial resolution and high spectral resolution have important applications in human society. In general, due to the limitations faced by the optical sensors’, we are limited to obtain only low spatial resolution multispectral images (MS) and high spatial resolution panchromatic images (PAN). To address this limitation, this study proposes a pyramid-attention based multi-scale feature fusion network (PAMF-Net) that combines the pyramid attention mechanism and feature aggregation. Initially, the MS and PAN images are input to the network, and the PAN images pass through the input pyramid branch to generate a multi-level receiving domain. Then, the result is combined with the features of the MS image as the input of the encoder, and these composite features are input to the pyramid attention mechanism module to capture multi-scale corresponding features. Next, the result of the input pyramid branch is input to the feature aggregation module to seamlessly merge with the features of the pyramid attention mechanism. Finally, in the encoding stage, multiple levels of features are multiplexed as encoding secondary lines by skipping connections to obtain high-quality HRMS images. After quantitative and qualitative experiments, the results show that our method is superior to other advanced methods.

Due to insufficient illumination in low‐light conditions, the brightness and contrast of the captured images are low, which affect the processing of other computer vision tasks. Low‐light enhancement is a challenging task that requires simultaneous processing of colour, brightness, contrast, artefacts and noise. To solve this problem, the authors apply the deep residual network to the low‐light enhancement task, and propose a hierarchical guided low‐light enhancement network. The key of this method is recombined hierarchical guided features through the feature aggregation module to realize low‐light enhancement. The network is based on the U‐Net network, and then hierarchically guided with the input pyramid branch in the encoding and decoding network. The input pyramid structure realizes multi‐level receptive fields and generates a hierarchical representation. The encoding and decoding structure concatenates the hierarchical features of the input pyramid and generates a set of hierarchical features. Finally, the feature aggregation module is used to fuse different features to achieve low‐light enhancement tasks. The effectiveness of the components is proved through ablation experiments. In addition, the authors are also evaluating on different data sets, and the experimental results show that the method proposed is superior to other methods in subjective and objective evaluation.

Multi-focus image fusion is always a difficult problem in digital image processing. To achieve efficient integration, we propose a new end-to-end network. This network uses the residual atrous spatial pyramid pooling module to extract multi-level features from the space of different scales and share parameters to ensure the consistency and correspondence of features. We also introduced a disparities attention module for the network which allows for information retention. These two parts can make our method overcome the difficulties of target edge artifacts, small range blur, poor detail capture, and so on. In addition, in order to improve the semantic ambiguity easily caused by unsupervised learning, we also proposed a new multi-focus image fusion dataset with groundtruth for supervised learning. We performed sufficient experiments, and the results show that the network can quickly capture the corresponding features of multi-focus images, and improve the fusion performance with less computation and lower storage cost. Compared with the existing nine fusion methods, our network is superior to other methods in subjective visual evaluation and objective evaluation, reaching a higher level.

Climacium dendroides is a rare bryophyte resource with important medicinal value, which is mainly concentrated in the southwest and northeast China. In recent years, we found in the wild investigat...

In a group of images, the recurrent foreground objects are considered as the key objects in the group of images. In co‐saliency detection, these are described as common saliency objects. The aim is to be able to naturally guide the user's gaze to these common salient objects. By guiding the user's gaze, users can easily find these common saliency objects without interference from other information. Therefore, a method is proposed for reducing user visual attention based on co‐saliency detection. Through the co‐saliency detection algorithm and matting algorithm for image preprocessing, the exact position of non‐common saliency objects (called Region of Interest here, i.e. ROI) in the image group can be obtained. In the attention retargeting algorithm, the internal features of the image to adjust the saliency of the ROI areas are considered. In the HSI colour space, the three components H, S, and I are adjusted separately. First, the hue distribution is constructed by the Dirac kernel function, and then the most similar hue distribution to the surrounding environment is selected as the best hue distribution of ROI areas. The S and I components can be set as the contrast difference between ROI areas and surrounding background areas according to the user's demands. Experimental results show that this method effectively reduces the ROI areas' attraction to the user's visual attention. Moreover, comparing this method with other methods, the saliency adjustment effect achieved is much better, and the processed image is more natural.

According to the atmospheric physical model, we can use accurate transmittance and atmospheric light information to convert a hazy image into a clean one. The scene-depth information is very important for image dehazing due to the transmittance directly corresponds to the scene depth. In this paper, we propose a multi-scale depth information fusion network based on the U-Net architecture. The model uses hazy images as inputs and extracts the depth information from these images; then, it encodes and decodes this information. In this process, hazy image features of different scales are skip-connected to the corresponding positions. Finally, the model outputs a clean image. The proposed method does not rely on atmospheric physical models, and it directly outputs clean images in an end-to-end manner. Through numerous experiments, we prove that the multi-scale deep information fusion network can effectively remove haze from images; it outperforms other methods in the synthetic dataset experiments and also performs well in the real-scene test set.

Images captured by cameras in low-light conditions have low quality and appear dark due to insufficient light exposure, which critically affects the view. Most of the traditional enhancement methods are based on the entire image for exposure enhancement, so overexposed areas in the image have the risk of secondary enhancement. In order to fully consider the exposure in low-light images, we propose a low-light image enhancement based on multi-illumination estimation, which can robustly produce high-quality results for various underexposures. The core of the proposed method is to derive multiple exposure correction images using light estimation. Then, we used a Laplacian multi-scale fusion method to combine the weight map and the images with different degrees of exposure. We used gamma correction and inversion on the original image to produce images with different exposure levels (such as underexposure, overexposure, and partial area overexposure and underexposure). The gamma-corrected image is used for lighting adjustment of underexposed areas in low-light images, while the inversion image is used for adjustment of the overexposed regions. We performed experiments on various images using multiple methods and evaluated and compared the experimental results, qualitatively and quantitatively. Experimental results show that the proposed method in this study can effectively eliminate the effects of low light and improve image quality.

Images collected in haze or other weather have problems of quality degradation, blurred details, and low recognition, which seriously affect the application and development of related image application fields. The dark channel prior method is the typical method of image dehazing, but it is not suitable for sky region. The wavelength of near-infrared is longer than that of visible light, which makes it more penetrating, less affected by the scattering of suspended particles in the air, and carries more detailed information. This paper uses near-infrared information to distinguish between sky region and non-sky region, improve the dark channel prior method, enhance the visibility of the image, and restore the contrast of the image. A large number of experiments have proved that our method has achieved satisfactory results in solving problems such as sky region and darker scene. This method has strong pertinence and stability for image dehazing, and the effect is relatively natural and efficient. Therefore, our method is better than the existing method of image dehazing.

With the continuous in-depth implementation of the ”Internet +” development strategy, supply chain finance relying on Internet technology is gradually becoming the main way for small and medium-sized enterprises (SMEs) to finance. Supply chain finance is closely integrated with the physical industry and finance, which has greatly promoted the continuous development of the main bodies of the supply chain, especially the small and medium-sized enterprises. Therefore, by integrating the components and characteristics of the blockchain into the various application links of supply chain finance, it can effectively solve the dilemma of SME financing in supply chain finance.

In this paper, we present a way to create an accurate trimap. Since the matting problem is a serious under-constrained problem, the user is required to provide additional constraint information to estimate the alpha value of the mixed pixels. The smaller the area of the unknown region of the user-provided trimap, the more accurate the alpha value of the estimated mixed pixels. But manually creating the trimap is a complicated and time-consuming task, and it is even impractical to manually create trimaps for some tasks. We use the ant colony algorithm to determine the boundary information of the foreground objects, and fuse different pheromone images at the superpixel level to create an accurate trimap. The trimap generated by our method also has higher precision when the edge of the foreground object has a lot of fine hair. Experiments show that the high-quality trimap can be generated by the method of this paper, which can effectively improve the performance of the matting algorithm and achieve accurate alpha mask estimation.

Improper functioning, or lack, of human cone cells leads to vision defects, making it impossible for affected persons to distinguish certain colors. Colorblind persons have color perception, but their ability to capture color information differs from that of normal people: colorblind and normal people perceive the same image differently. It is necessary to devise solutions to help persons with color blindness understand images and distinguish different colors. Most research on this subject is aimed at adjusting insensitive colors, enabling colorblind persons to better capture color information, but ignores the attention paid by colorblind persons to the salient areas of images. The areas of the image seen as salient by normal people generally differ from those seen by the colorblind. To provide the same saliency for colorblind persons and normal people, we propose a saliency-based image correction algorithm for color blindness. Adjusted colors in the adjusted image are harmonious and realistic, and the method is practical. Our experimental results show that this method effectively improves images, enabling the colorblind to see the same salient areas as normal people.

In this paper, we propose a simple and effective method for creating accurate trimaps based on input images. Most advanced matting algorithms require the user to provide prior information to estimate high-quality alpha masks, where the prior information is primarily in the form of trimaps. A precise trimap is one of the most important factors affecting the performance of the matting algorithm. It is a very tedious task for users to specify a large number of accurate trimaps, and it is even impractical in some applications. Based on manifold ranking, we use strokes to mark the superpixel nodes to create high-quality trimaps. The experimental results show that the method given in this paper can generate high-quality trimaps, thus ensuring the accuracy of the alpha masks that are estimated by the matting algorithm. We verify the performance of the trimaps that are created using the method given in this paper for various matting algorithms.

Single image reflection removal is an ill-posed problem. To solve this problem, this study develops a network structure based on a deep encoder-decoder RRnet. Unlike most deep learning strategies applied in this context, the authors find that redundant information increases the difficulty of predicting images on the network; thus, the proposed method uses mixed reflection image cascaded edges as input to the network. The proposed network structure is divided into two parts: the first part is a deep convolutional encoder-decoder network. Its function uses the mixed reflection image and the target edge as input to predict the target layer. The second part is an identical encoder-decoder network structure. Its function uses the mixed reflection image and the reflection edge as input to predict the image reflection layer. In addition, the authors use joint loss to optimise the network model. To train the neural network, they also create an image dataset for reflection removal, which includes a true mixed reflection image and a synthetic mixed reflection image. They use four evaluation indicators to evaluate the proposed method and the other six methods. The experimental results indicate that the proposed method is superior to previous methods.

Purpose: Death anxiety is commonly experienced by individuals with advanced cancer who have a limited life expectancy. The Death and Dying Distress Scale (DADDS) is a validated measure that was created to capture this experience; but no Chinese version is available to date. We conducted a cross-sectional study to explore the psychometric properties of a Chinese version DADDS (DADDS-C) and address prevalence of death anxiety among patients with advanced cancer.Methods: Patients with advanced cancer were recruited from Peking University Cancer Hospital. Measures administered included: DADDS-C, Patient Health Questionnaire (PHQ-9), General Anxiety Disorder-7(GAD-7), Quality of Life at End of Life in Cancer (QUAL-EC), Functional Assessment of Chronic Illness Therapy-Spiritual Well-Being Scale (FACIT-sp). McDonald's Omega, Cronbach's alpha, Exploratory Factor Analysis and Confirmatory Factor Analysis were used to test DADDS-C's reliability and validity. Logistic regression analysis was used to identify risk factors for death anxiety.Results: Of 300 patients approached, 256 (85%) provided informed consent and completed the questionnaires. Of these participants, 43 (16.8%) had moderate death anxiety based on scores of ≥45 on the DADDS-C. Three factors (feeling shortness of time, dying and death distress, being a burden to others) explained 71.643% of shared variation with factor loadings ranging from 0.629 to 0.822. Cronbach's alpha was 0.939; Omega total was 0.959. DADDS-C had acceptable convergent and discriminant validity. Logistic regression analysis indicated that two factors (better relationship with healthcare providers and preparation for end of life) protected patients from death anxiety.Conclusion: DADDS-C is a valid tool for measuring death anxiety in Chinese patients with advanced cancer. The presence of at least moderate death anxiety in a substantial minority of these patients calls for screening for this symptom and for more routine psychological interventions to alleviate and prevent such distress in this population.

In this article, we aim to improve the performance of visual tracking by combing different features of multiple modalities. The core idea is to use covariance matrices as feature descriptors and then use sparse coding to encode different features. The notion of sparsity has been successfully used in visual tracking. In this context, sparsity is used along appearance models often obtained from intensity/color information. In this work, we step outside this trend and propose to model the target appearance by local covariance descriptors (CovDs) in a pyramid structure. The proposed pyramid structure not only enables us to encode local and spatial information of the target appearance but also inherits useful properties of CovDs such as invariance to affine transforms. Since CovDs lie on a Riemannian manifold, we further propose to perform tracking through sparse coding by embedding the Riemannian manifold into an infinite-dimensional Hilbert space. Embedding the manifold into a Hilbert space allows us to perform sparse coding efficiently using the kernel trick. Our empirical study shows that the proposed tracking framework outperforms the existing state-of-the-art methods in challenging scenarios.

In this paper, we propose an Iterative Residual Network. By designing the calculation unit, we put the hazy image into the calculation unit to perform an iterative operation that can stitch the hazy image in stages with the unit output and substitute it into the calculation. After multiple iterations, a clean image can be generated. We introduce Long Short-Term Memory network and Residual ideas in the design process of the computing unit to further optimize the model. The Long Short-Term Memory network can be used to connect computing units at different stages. The use of residual block connection in the deep processing of the computing unit can preserve the original features of the image and prevent the model from overfitting. This model directly generates hazy-free images in an end-to-end manner and does not rely on the estimations of the transmission map and atmospheric light. Experiments show that Iterative Residual Network can effectively remove the haze in the image. In the test of the synthetic dataset and the real dataset, Iterative Residual Network is superior to the existing methods in terms of PSNR, SSIM, FADE and subjective visual effects.

For patients with color vision defects, owing to the destruction of cone cells and loss of function, some color information is lost, hence changing the originally transmitted information by the image. The purpose of the traditional method of correction is to help patients distinguish between colors, but it does not take into account the problem of the saliency of the image. In this paper, we propose a saliency consistency-based image re-colorization for color blindness. We use image retrieval methods to select a large number of images and use co-saliency methods to detect salient areas of standard color images and color-blind simulated images. According to the detection results, an image with the same detection result was selected as the reference image. We grayscale the significantly changed image, recolor the grayscale image using the reference image, and the color scheme of the recolored image is similar to the reference image. The color matching scheme of the reference image makes the significance of the image basically unchanged in standard vision and color vision defects, thereby making the color blindness patient’s perception of the image close to standard vision. We invite green blind patients to evaluate CVD simulation images with different recoloring methods subjectively. In addition, we use different evaluation criteria to evaluate the experimental results objectively. In the subjective evaluation and objective evaluation, the method proposed in this paper has achieved good results, which validates the effectiveness of our method.

Interfacial phenomena can significantly affect the development, manufacturing, stability, and use of therapeutic proteins. Proteins are exposed to air-liquid, solid-liquid, and liquid-liquid interfaces throughout the product development cycle. The exposure of the protein molecules to different types of interfaces can lead to denaturation and subsequent formation of aggregates and particles. This introduction will emphasize the importance of understanding interfaces and interfacial stresses in the development of biologics. The chapter will also present the overall objectives, scope, and structure of this book. Subsequently, the chapter will introduce the various interfaces encountered in drug development, and the chapter concludes with perspectives on controlling undesired interfacial behavior and future research areas.

This article focuses on the extraction of airport target in remote sensing images. We propose a Guided Edge Net Model based on Convolutional Neural Network. In the first step, we use six convolutional layers to convolve the original image to obtain a preliminary feature image. In the second step, we concatenate the convolution results of 2-6 layers and put it into the VGG-19 model. At the same time, we use the target edge image as a reference to train the edge guidance network. In the third step, we obtain a result image with the same size as the input image by deconvolution. The Guide Edge Net Model reduces the false detection rate of the candidate airport area for a certain extent. From the perspective of MAE, the algorithm proposed in this paper performs better than other methods, only 0.0063, Compared with the method based machine learning, it reduced by 3%. Experimental results demonstrate that the network can achieve higher detection accuracy and segment the target accurately. The results are highly consistent with the actual object and easy to accomplish.

Remote sensing satellites can provide a large number of multispectral images. However, due to the limitations of optical sensors embedded in satellites, the spatial resolution of multispectral images is relatively low. Pansharpening aims to combine high-resolution panchromatic and multi-spectral images to generate high-resolution multi-spectral images. In this paper, we propose a pansharpening method based on a component substitution framework. We use fractional-order differential operators and guided filter to balance the spectral distortion and spatial information loss that occur when remote sensing image fusion. Fractional-order differentiation can better define the detailed map, and the guided filter can enhance the spectral information of the detailed map. Experiments show that the proposed method in this paper can better combine the spectral information and spatial information, as well as obtain satisfactory results in both subjective visual perception and objective object evaluation.

In this paper, we propose a simple and efficient approach to generate a high-quality trimap from the input image. Most of the state-of-the-art matting algorithms require human intervention in the form of trimap or scribbles to generate the alpha matte from the input image. An attentively created trimap is required to acquire an accurate alpha matte. This is a very tedious task and may even become impractical for some applications. The accuracy of trimap-based approach reduces drastically as the trimap becomes thicker and coarser. We use the co-fusion-based method to generate a high-quality trimap in less time, which assists in obtaining accurate and fast results. The experimental results demonstrate that our method produces good quality trimap, which results in an accurate matte estimation. We validate our results by replacing our generated trimap by manually created trimap while using the same image matting algorithm.

The learning-based super-resolution reconstruction method inputs a low-resolution image into a network, and learns a non-linear mapping relationship between low-resolution and high-resolution through the network. In this study, the multi-scale super-resolution reconstruction network is used to fuse the effective features of different scale images, and the non-linear mapping between low resolution and high resolution is studied from coarse to fine to realise the end-to-end super-resolution reconstruction task. The loss of some features of the low-resolution image will negatively affect the quality of the reconstructed image. To solve the problem of incomplete image features in low-resolution, this study adopts the multi-scale super-resolution reconstruction method based on guided image filtering. The high-resolution image reconstructed by the multi-scale super-resolution network and the real high-resolution image are merged by the guide image filter to generate a new image, and the newly generated image is used for secondary training of the multi-scale super-resolution reconstruction network. The newly generated image effectively compensates for the details and texture information lost in the low-resolution image, thereby improving the effect of the super-resolution reconstructed image.Compared with the existing super-resolution reconstruction scheme, the accuracy and speed of super-resolution reconstruction are improved.

This paper proposes a novel method for detecting a photographer's shooting trajectory based on select images. Firstly, in a Lab color space, directional information and perceived color information were combined, and similar images were found by a color difference histogram. Local invariant descriptors were then constructed by the contrast context histogram method to match feature point areas and their context, and to judge whether these areas corresponded. Through this, the corresponding relationship for feature points between image sequences was obtained. Furthermore, the essential matrix for a pair of images was obtained through the singular value decomposition method to determine photographer trajectories.

Object extraction provides the basis for subsequent tasks such as object recognition, and its importance is self-evident. For this purpose, this paper proposes an object extraction algorithm based on saliency prior information. Firstly, the SIFT operator and the oriented edge forest method are used to extract the saliency points and the saliency edges respectively. Then construct a simple small convolutional neural network for the saliency fusion task, and fuse the saliency point and the saliency edge to obtain the saliency fusion map. Then the fusion map is added to the object extraction network structure as a priori information. In this paper, the residual network is used for the object extraction task, and finally the high-quality object extraction work is realized. The algorithm uses IOU parameters and Precision as the quantitative evaluation index, and uses qualitative analysis to comprehensively analyse the experimental results. Experiments show that the proposed algorithm has good results in both image quality and visual, and has good robustness.

In this paper, the physical layer security (PLS) of fractional orbital angular momentum (OAM) multiplexing under atmospheric turbulence channels is studied. Based on the PLS theory, the secrecy capacities and the probabilities of positive secrecy capacities of fractional OAM (FrOAM) multiplexing systems with different topological charge intervals are analyzed. The influence of the eavesdropping ratio and the power allocation on secrecy capacities are compared. The simulation results show that, under the finite aperture limitation, the FrOAM multiplexing technique provides higher security over the integer OAM multiplexing in terms of the total secrecy capacities under weak and medium turbulence.

Biologic products encounter various types of interfacial stress during development, manufacturing, and clinical administration. When proteins come in contact with vapor-liquid, solid-liquid, and liquid-liquid surfaces, these interfaces can significantly impact the protein drug product quality attributes, including formation of visible particles, subvisible particles, or soluble aggregates, or changes in target protein concentration due to adsorption of the molecule to various interfaces. Protein aggregation at interfaces is often accompanied by changes in conformation, as proteins modify their higher order structure in response to interfacial stresses such as hydrophobicity, charge, and mechanical stress. Formation of aggregates may elicit immunogenicity concerns; therefore, it is important to minimize opportunities for aggregation by performing a systematic evaluation of interfacial stress throughout the product development cycle and to develop appropriate mitigation strategies. The purpose of this white paper is to provide an understanding of protein interfacial stability, explore methods to understand interfacial behavior of proteins, then describe current industry approaches to address interfacial stability concerns. Specifically, we will discuss interfacial stresses to which proteins are exposed from drug substance manufacture through clinical administration, as well as the analytical techniques used to evaluate the resulting impact on the stability of the protein. A high-level mechanistic understanding of the relationship between interfacial stress and aggregation will be introduced, as well as some novel techniques for measuring and better understanding the interfacial behavior of proteins. Finally, some best practices in the evaluation and minimization of interfacial stress will be recommended.

Spray-dried dispersions (SDDs) have become an important formulation technology for the pharmaceutical product development of poorly water-soluble (PWS) compounds. Although this technology is now widely used in the industry, especially in the early-phase development, the lack of mechanistic understanding still causes difficulty in selecting excipients and predicting stability of SDD-based drug products. In this review, the authors aim to discuss several principles of polymer science pertaining to the development of SDDs, in terms of selecting polymers and solvents, optimizing drug loading, as well as assessing physical stability on storage and supersaturation maintenance after dissolution, from both thermodynamic and kinetic considerations. In order to choose compatible solvents with both polymers and active pharmaceutical ingredients (APIs), a symmetric Flory-Huggins interaction (Δχ ∼0) approach was introduced. Regarding spray drying of polymer-API solutions, low critical solution temperature (LCST) was discussed for setting the inlet temperature for drying. In addition, after being exposed to moisture, SDDs are practically converted to ternary systems with asymmetric Flory-Huggins interactions, which are thermodynamically not favored. In this case, the kinetics of phase separation plays a significant role during the storage and dissolution of SDD-based drug products. The impact of polymers on the supersaturation maintenance of APIs in dissolution media was also discussed. Moreover, the nature of SDDs, with reference to solid solution and the notion of solid solubility, was examined in the context of pharmaceutical application. Finally, the importance of robust analytical techniques to characterize the SDD-based drug products was emphasized, considering their complexity.

Electrospun polyimide (PI) nanofibers possessed high tensile strength (δ), but the breaking load (BL) is very small. It is also a challenge to prepare electrospun PI microfibers from the PAA precursor in high boiling point solvents. In this work, PI microfibers with diameter more than 2 μm were prepared from their PAA-salt in water mixed with low boiling point solvent, such as ethanol. The single electrospun PI microfiber (S-EPIMF) showed excellent mechanical properties with BL, δ, modulus and tensile strain of 4872 μN, 1064 MPa, 5.6 GPa and 15.7%, respectively. The high BL allows a single electrospun PI microfiber even be able to hold a 0.5 g metal ring. The superior mechanical properties of the electrospun PI microfibers could be attributed to the high molecular orientation and crystallinity in the fibers, and the high BL is due to the large diameter of the electrospun PI microfibers.

The rate and extent of granule growth and densification during high-shear wet granulation (HSWG) depends on a variety of formulation and process variables, including material attributes of critical formulation excipients, such as binders. The effects of known binder attributes to the rate and extent of granule growth and densification in a wet granulation process could be either specific or agnostic to a particular active pharmaceutical ingredient (API) or drug product formulation. The effect of binder properties and process variables, such as mode of addition, on the HSWG process and product performance can be explored both experimentally as well as through in silico modeling and simulation. Examples and case studies on the effect of material attributes on process performance using both experimental and modeling methodologies are presented. This chapter demonstrates the essential role of combining multiscale models such as the mechanistic, first principles-based particle-level models, and process models with experimental observations to fully understand and characterize the role of binder attributes on the process outcomes.

Multifocus image fusion is the merging of images of the same scene and having multiple different foci into one all-focus image. Most existing fusion algorithms extract high-frequency information by designing local filters and then adopt different fusion rules to obtain the fused images. In this paper, a wavelet is used for multiscale decomposition of the source and fusion images to obtain high-frequency and low-frequency images. To obtain clearer and complete fusion images, this paper uses a deep convolutional neural network to learn the direct mapping between the high-frequency and low-frequency images of the source and fusion images. In this paper, high-frequency and low-frequency images are used to train two convolutional networks to encode the high-frequency and low-frequency images of the source and fusion images. The experimental results show that the method proposed in this paper can obtain a satisfactory fusion image, which is superior to that obtained by some advanced image fusion algorithms in terms of both visual and objective evaluations.

At present, the video background extraction algorithm of static scene has been nearly mature. However, video background extraction in dynamic scenes remains a challenge. In order to solve this problem, this paper proposes a dynamic scenes video background extraction algorithm. Here, our dynamic scene is based on camera movement. Firstly, we detect saliency target of video frame according to context information and do a processing of fuzzy enhancement. Meanwhile, we analyze flow filed by SIFT Flow method to do a nonlinear fusion with fuzzy enhancement result. Up to now, we can obtain moving target .Because of other gray information in the foreground affect target extraction, so we have to do a process of binarization and find out bounding box. After these preparations, we will track moving object with real-time algorithm. Finally, we use KNN algorithm to get accurate moving targets. Experiment results show that the proposed method for dynamic scenes video background extraction could get better results.

UHF based single station RTK is widely used for auto-steering guidance of agricultural machinery in China currently. Too many reference stations in a region will cause serious interference of radio frequency. Moreover, the reliability is very low, since most of the stations were built on the residential buildings. Considering the above problems, we propose to construct the reference station on the communication tower because of the advantages including distribution density, infrastructure guarantee, high quality communication, and relative height compared with ordinary building. We select three communication towers for experiment in Beijing. The average baseline is 43.3 km. We place the GNSS antennas on the roof of communication equipment room, and put the reference receivers (PD318) in the room. An agri-CORS is constructed by using PowerNetwork software. We use 4G of China Mobile to transfer observation data and ephemeris data in real time. We put the antennas of UHF radio on the tower, which is nearly 50 m high. Results show that the data integrity of three reference stations are better than 99%. The signal-to-noise ratio of L1, L2, B1, B2, and B3 are greater than 46, 35, 44, 46, and 40% respectively. The multipath of all the bands are less than 0.50. The average accuracy of baseline after adjustment is better than 0.001 m. Both average internal accord accuracy of CORS and single station RTK are better than 0.01 m, and both average external accord accuracy of CORS and single station RTK are better than 0.025 m. Therefore, we get the basic conclusion that the selected communication towers are suitable for construction of GNSS reference station and the CORS and single station RTK meet the application requirement of auto-steering guidance of agricultural machinery.

Lubrication plays a key role in successful manufacturing of pharmaceutical solid dosage forms; lubricants are essential ingredients in robust formulations to achieve this. Although many failures in pharmaceutical manufacturing operations are caused by issues related to lubrication, in general, lubricants do not gain adequate attention in the development of pharmaceutical formulations. In this paper, the fundamental background on lubrication is introduced, in which the relationships between lubrication and friction/adhesion forces are discussed. Then, the application of lubrication in the development of pharmaceutical products and manufacturing processes is discussed with an emphasis on magnesium stearate. In particular, the effect of its hydration state (anhydrate, monohydrate, dihydrate, and trihydrate) and its powder characteristics on lubrication efficiency, as well as product and process performance is summarized. In addition, the impact of lubrication on the dynamics of compaction/compression processes and on the mechanical properties of compacts/tablets is presented. Furthermore, the online monitoring of magnesium stearate in a blending process is briefly mentioned. Finally, the chemical compatibility of active pharmaceutical ingredient (API) with magnesium stearate and its reactive impurities is reviewed with examples from the literature illustrating the various reaction mechanisms involved.

Image degradation caused by shadows is likely to cause technological issues in image segmentation and target recognition. In view of the existing shadow removal methods, there are problems such as small and trivial shadow processing, the scarcity of end-to-end automatic methods, the neglecting of light, and high-level semantic information such as materials. An end-to-end deep convolutional neural network is proposed to further improve the image shadow removal effect. The network mainly consists of two network models, an encoder&ndash, decoder network and a small refinement network. The former predicts the alpha shadow scale factor, and the latter refines to obtain sharper edge information. In addition, a new image database (remove shadow database, RSDB) is constructed, and qualitative and quantitative evaluations are made on databases such as UIUC, UCF and newly-created databases (RSDB) with various real images. Using the peak signal-to-noise ratio (PSNR) and the structural similarity (SSIM) for quantitative analysis, the algorithm has a big improvement on the PSNR and the SSIM as opposed to other methods. In terms of qualitative comparisons, the network shadow has a clearer and shadow-free image that is consistent with the original image color and texture, and the detail processing effect is much better. The experimental results show that the proposed algorithm is superior to other algorithms, and it is more robust in subjective vision and objective quantization.

In this paper, we propose a new robust feature extraction algorithm for 3D models based on principal curvature direction. Generally, the feature regions tend to be more noisy, so it demands a robust technique to handle features effectively. Because the integral invariants are robust against noise, the principal curvature information is estimated based on principal component analysis. After fuzzy filtering of the principal curvature direction, it becomes a good description of the geometric discontinuity. Compared with the curvature values, the impact of noise on the principal curvature direction is small. Therefore, feature extraction based on principal curvature direction is more robust and accurate. The experimental results show that the proposed algorithm can efficiently extract feature and distinguish noise.

A novel image retrieval algorithm using the double density DWT is proposed in this paper. The double density DWT has the advantages of good directionality, nearly shift-invariance and limited redundancy. Our simulation results demonstrate that the high frequency sub-band coefficient of double density DWT can be described by the generalized Gaussian density (GGD). Then the parameters of GGD can denote the texture feature of high frequency sub-band. The local binary pattern (LBP) histogram is used to describe the texture feature of low frequency sub-band. Experiments show that the proposed algorithm using the double density DWT outperforms the SD algorithm based on the Contourlet in the natural image retrieval.

In this paper, we combined with efficient image signal processing algorithms, according to the manifestations of the blur of polish operation in the frequency domain,proposed a blind detection algorithm for image tampering evidence. First, the target image transformed into a new Nonsubsampled dyadic contourlet domain which based on contrast a trous wavelet, then homomorphic filtering on it in this domain to enhance the edge whcih was blurred, and then combined with morphological Filter to eroded the area of non-tampering, to complete the blurred image tampering detection. Through experiments, the algorithm in this paper have a excellent recognition for the blurred retouch images.

Visual attention model has a good visual attention characteristic, which can accurately detect the salient region in images. Image scaling algorithm based on salient region will be studied. The salient region in original images is firstly detected, and the different region will be resized by the different scaling rules. At last, the resized image will be obtained by the fitting function. The salient region is resized by the nonlinear scaling rules adjust the scaling weights, which avoid the linear scaling rules causing morphing and ensuring the visual attention regional image not distortion. The other region is resized by the linear scaling rules use the interpolation method. Experimental results validate that this paper algorithm has not only achieved image scaling, and ensure the image no distortion and the integrity of salient region content, show good visual effect, and improve the quality of image scaling.

This paper constructs a dyadic non-subsampled Contourlet transform for denoising on the image, the transformation has more directional subband, using the non-subsampled filter group for decompositing of direction, so has the translation invariance, eliminated image distortion from Contourlet transform’s lack of translation invariance. Non-subsampled filter reduces noise interference and data redundancy. Using the feature of NSCT translation invariance, multiresolution, multi-direction, and can according to the energy of NSCT in all directions and in all scale, adaptive denoising threshold. Experimental results show that compared to wavelet denoising and traditional Contourlet denoising, the method achieves a higher PSNR value, while preserving image edge details, can effectively reduce the Gibbs distortion, improve visual images.