Focusing on your subject:Deep subject-aware image composition recommendation networks

Photo composition is one of the most important factors in the aesthetics of photographs.As a popular application,composition recommendation for a photo focusing on a specific subject has been ignored by recent deep-learning-based composition recommendation approaches.In this paper,we propose a subject-aware image composition recommendation method,SAC-Net,which takes an RGB image and a binary subject window mask as input,and returns good compositions as crops containing the subject.Our model first determines candidate scores for all possible coarse cropping windows.The crops with high candidate scores are selected and further refined by regressing their corner points to generate the output recommended cropping windows.The final scores of the refined crops are predicted by a final score regression module.Unlike existing methods that need to preset several cropping windows,our network is able to automatically regress cropping windows with arbitrary aspect ratios and sizes.We propose novel stability losses for maximizing smoothness when changing cropping windows along with view changes.Experimental results show that our method outperforms state-of-the-art methods not only on the subject-aware image composition recommendation task,but also for general purpose composition recommendation.We also have designed a multistage labeling scheme so that a large amount of ranked pairs can be produced economically.We use this scheme to propose the first subject-aware composition dataset SACD,which contains 2777 images,and more than 5 million composition ranked pairs.The SACD dataset is publicly available at https://cg.cs.tsinghua.edu.cn/SACD/.

Color retargeting:Interactive time-varying color image composition from time-lapse sequences

In this paper,we present an interactive static image composition approach,namely color retargeting,to flexibly represent time-varying color editing effect based on time-lapse video sequences.Instead of performing precise image matting or blending techniques,our approach treats the color composition as a pixel-level resampling problem. In order to both satisfy the user's editing requirements and avoid visual artifacts,we construct a globally optimized interpolation field. This field defines from which input video frames the output pixels should be resampled.Our proposed resampling solution ensures that(i) the global color transition in the output image is as smooth as possible,(ii) the desired colors/objects specified by the user from different video frames are well preserved,and(iii) additional local color transition directions in the image space assigned by the user are also satisfied.Various examples have been shown to demonstrate that our efficient solution enables the user to easily create time-varying color image composition results.

Performance of global look-up table strategy in digital image correlation with cubic B-spline interpolation and bicubic interpolation

Global look-up table strategy proposed recently has been proven to be an efficient method to accelerate the interpolation, which is the most time-consuming part in the iterative sub-pixel digital image correlation （DIC） algorithms. In this paper, a global look-up table strategy with cubic B-spline interpolation is developed for the DIC method based on the inverse compositional Gauss-Newton （IC-GN） algorithm. The performance of this strategy, including accuracy, precision, and computation efficiency, is evaluated through a theoretical and experimental study, using the one with widely employed bicubic interpolation as a benchmark. The global look-up table strategy with cubic B-spline interpolation improves significantly the accuracy of the IC-GN algorithm-based DIC method compared with the one using the bicubic interpolation, at a trivial price of computation efficiency.

Applications of Secondary Electron Composition Contrast Imaging Method in Microstructure Studies on Heterojunction Semiconductor Devices and Multilayer Materials

The principle, imaging condition and experimental method for obtaining high resolution composition contrast in secondary electron image were described. A new technique of specimen preparation for secondary electron composition contrast observation was introduced and discussed. By using multilayer P+Si1-xGex/pSi heterojunction internal photoemission infrared detector as an example, the applications of secondary electron composition contrast imaging in microstructure studies on heterojunction semiconducting materials and devices were stated. The characteristics of the image were compared with the ordinary transmission electron diffraction contrast image. The prospects of applications of the imaging method in heterojunction semiconductor devices and multilayer materials are also discussed.

Image editing by object-aware optimal boundary searching and mixed-domain composition

When combining very different images which often contain complex objects and backgrounds,producing consistent compositions is a challenging problem requiring seamless image editing. In this paper, we propose a general approach, called objectaware image editing, to obtain consistency in structure,color, and texture in a unified way. Our approach improves upon previous gradient-domain composition in three ways. Firstly, we introduce an iterative optimization algorithm to minimize mismatches on the boundaries when the target region contains multiple objects of interest. Secondly, we propose a mixeddomain consistency metric for measuring gradients and colors, and formulate composition as a unified minimization problem that can be solved with a sparse linear system. In particular, we encode texture consistency using a patch-based approach without searching and matching. Thirdly, we adopt an objectaware approach to separately manipulate the guidance gradient fields for objects of interest and backgrounds of interest, which facilitates a variety of seamless image editing applications. Our unified method outperforms previous state-of-the-art methods in preserving global texture consistency in addition to local structure continuity.

Improved Geological Interpretation Using Landsat TM Data in Lancang-Jinghong Area, Yunnan Province, China

Landsat TM digital spectral data of Lancang Jinghong area (Yunnan P ro vince) has been used for the purpose of geological interpretation. To meet this object, different image processing techniques including selected band color comp osites, principal component analysis and IHS decorrelation stretching are used t o improve the discrimination of different lithological and structural features i n the area.It was found that IHS decorrelation stretching images obtained from t he transformation of false color composite 741 (in red, green and blue) prov ided the best results based on the original data.By combining the characteristic s of images produced by different approaches and other canonically transformed i mages with available geological data and surface observations, the geological in terpretation could be done with satisfactory degree of accuracy.

Study on algorithm of dynamic uncalibrated eye-in-hand visual servoing system

Currently, most visual servoing system must be calibrated, while it is impossible to calibrate cameras and robot models precisely in industrial practice, so a novel dynamic uncalibrated eye-in-hand visual servoing system of tracking a moving target is proposed. The method does not require calibration of camera and robot kinematic models. Vision guided algorithm for tracking dynamic image is developed through minimizing nonlinear objective function. For the large residual has not been approximated in dynamic environment and the change of composite image Jacobian with time increment has not been computed in visual servoing system now,large residuals are dynamic approximated and the change of composite image Jacobian at each iterative step is computed. Simulation results demonstrate the validity of these approaches.

Facial model fitting algorithm based on active appearance model

Active appearance model（AAM） is an efficient useful for the subsequent work such as face detection and method for the localization of facial feature points, which is also facial expression recognition. In this paper, we mainly discuss the AAMs based on principal component analysis （PCA）. We also propose an efficient facial fitting algorithm, which is named inverse compositional image alignment （ICIA）, to eliminate a considerable amount of computation resulting from traditional gradient descent fitting algorithm. Finally, 3D facial curvature is used to initialize the location of facial feature, which helps select the parameters of initial state for the improved AAM.

In-service Structural Health Monitoring of a Full-scale Composite Horizontal Tail

In-service structural health monitoring（SHM） technologies are critical for the utilization of composite aircraft structures. We developed a Lamb wave-based in-service SHM technology using built-in piezoelectric actuator/sensor networks to monitor delamination extension in a full-scale composite horizontal tail. The in-service SHM technology combine of damage rapid monitoring（DRM） stage and damage imaging diagnosis（DID） stage allows for real-time monitoring and long term tracking of the structural integrity of composite aircraft structures. DRM stage using spearman rank correlation coeffi cient was introduced to generate a damage index which can be used to monitor the trend of damage extension. The DID stage based on canonical correlation analysis aimed at intuitively highlighting structural damage regions in two-dimensional images. The DRM and DID stages were trialed by an in-service SHM experiment of CFRP T-joint. Finally, the detection capability of the in-service SHM technology was verified in the SHM experiment of a full-scale composite horizontal tail. Experimental results show that the rapid monitoring method effectively monitors the damage occurrence and extension tendency in real time; damage imaging diagnosis results are consistent with those from the failure model of the composite horizontal tail structure.

mSwap: a large-scale image-compositing method with optimal m-ary tree

With the increasing of computing ability,large-scale simulations have been generating massive amounts of data in aerodynamics.Sort-last parallel rendering is the most classical image compositing method for large-scale scientific visualization.However,in the stage of image compositing,the sort-last method may suffer from scalability problem on large-scale processors.Existing image compositing algorithms tend to perform well in certain situations.For instance,Direct Send is well on small and medium scale;Radix-k gets well performance only when the k-value is appropriate and so on.In this paper,we propose a novel method named mSwap for scientific visualization in aerodynamics,which uses the best scale of processors to make sure its performance at the best.mSwap groups the processors that we can use with a(m,k)table,which records the best combination of m(the number of processors in subgroup of each group)and k(the number of processors in each group).Then in each group,using a m-ary tree to composite the image for reducing the communication of processors.Finally,the image is composited between different groups to generate the final image.The performance and scalability of our mSwap method is demonstrated through experiments with thousands of processors.

一种用于位移场分析的应变模式频域数字图像相关方法

本文提出了一种在频域中考虑应变对位移影响的频域数字图像相关方法.研究并建立了一个在频域中评价参考图像子区与目标图像子区之间匹配的评价标准,并在此基础之上,提出了可用于位移和应变计算的频域迭代算法,其中,Hessian矩阵在迭代过程中保持不变.在Hessian矩阵的形成过程中,参考图像子区中灰度的梯度可以通过快速傅里叶变换进行计算,具有很高的计算效率和精度.同时,一种离散傅里叶变换重采样技术被用于代替传统的插值方法对变形图像子区中亚像素位置的灰度进行重建和更新.为了验证所提方法的有效性和准确性,使用了国际DIC挑战委员会(IDCC)提供的系列图像(2D-Challenge 1.0,样本6)进行位移分析.分析的误差结果表明,在子区大小为41×41像素的条件下,对变形为50%的模拟实验进行了计算,位移分析结果的精度约为0.0032像素(最大绝对值误差),在精度上优于已发表的文献.最后,对硅橡胶试件进行了14.85%的单轴拉伸试验,通过相关系数分布检验了本文所提方法在实际应用中的有效性,并给出了分析的位移和应变分布.

OOADS: An Object-Oriented Design Model for Advertising CAD System

The advances of computer graphics and imape processing have made it possible to design advertisements by computers. Presently, many commercial systems have come into being, such as CorelDraw and PhotoShop. All of them are developed out of the idea of graphics system or image system. For the ads designer, what is actually needed is a system developed from the point of view of ads design domain. In this paper, an object-oriented design model called OOADS is presented, around which five categories of operations, namely CMPDS (Clip / Modify / Paste / Draw/ Select ) are organized. Key approaches with the operations such as representation and organization of objects, virtual clipping, shadow images are demonstrated. In the end, the implementation of OOADS is discussed.

Making Slide Shows with Zoomquilts

We present a novel method for generating a slide show, which takes as input a collection of images, and outputs a video consisting of these images, switching between images smoothly in a continuous zoom-like process： as the sequence plays, a miniature of the next image is embedded in the current image and enlarges until eventually replaces the current image. Color differences, texture similarity, image complexity, etc. are taken into account to measure the distance between two images. Based on this distance, a dynamic programming algorithm is used to generate the best playing sequence which minimizes the sum of distances between successive images. The embedded image is naturally merged with the current one for smooth sequence through a graph-cut-guided blending strategy, and interframe coherence is maintained to avoid abrupt change. Experiments show that our approach is very effective on image collections of scenic spots.

Elastic deformation behavior of CuZrAlNb metallic glass matrix composites with different crystallization degrees

The room temperature brittleness has been a long standing problem in bulk metallic glasses realm.This has seriously limited the application potential of metallic glasses and their composites.The elastic deformation behaviors of metallic glass matrix composites are closely related to their plastic deformation states.The elastic deformation behaviors of Cu48-xZr48Al4Nbx（x=0,3at.%）metallic glass matrix composites（MGMCs）with different crystallization degrees were investigated using an in-situ digital image correlation（DIC）technique during tensile process.With decreasing crystallization degree,MGMC exhibits obvious elastic deformation ability and an increased tensile fracture strength.The notable tensile elasticity is attributed to the larger shear strain heterogeneity emerging on the surface of the sample.This finding has implications for the development of MGMCs with excellent tensile properties.