摘要：为了识别人脸表情中包含复杂背景、面部遮挡等因素的真实环境下的图像,提出基于区域增强型注意力网络的人脸表情识别方法.首先提出基于注意力的区域增强网络,减弱外部因素的影响以及增强表情识别在真实环境下的鲁棒性;然后提出通道-空间注意力融合网络,作用于全局的特征提取;最后通过分区损失和交叉熵损失相结合的方式提升表情图像的辨识度,从而提升识别准确率.在公开数据集RAF-DB,FERPlus和AffectNet上的实验结果表明,表情识别准确率分别达到88.81%,89.32%和60.45%;所提方法具有更高的准确率和鲁棒性.

摘要：多模态医学图像融合已成为有效结合正常组织结构和异常改变信息、提高医学诊断效率的强有力辅助技术.针对空域融合技术在处理图像细节丢失、光谱退化等方面的缺陷,提出一种在联合双边滤波器(JBF)域内实现图像结构与细节信息增强的双通道频域多模态医学图像融合方法.该方法将源图像分解为结构和能量2个通道,分别处理图像纹理细节信息和边缘强度信息.在结构通道中,通过改进梯度能量得到局部梯度能量算子,进一步提升融合图像对小尺度细节信息的表达能力和对噪声的鲁棒性;在能量通道中,利用非下采样轮廓波变换提高模型的多方向多尺度特性,并提出一种局部熵细节增强算子和脉冲耦合神经网络结合的高频子带处理框架,达到增强能量通道中结构信息和细节信息的效果.在Atlas公开数据集上,与基于MST、稀疏表示、PCNN以及JBF的6种具有代表性的频域融合方法进行对比及消融实验的结果表明,所提方法的融合图像与源图像相似度提升35.0%,空间频率提升16.2%,边缘保持度提升12.5%,对比度提升11.2%;并在视觉方面有较好的效果,明显优于对比方法.

摘要：多模态医学图像融合旨在利用跨模态图像的相关性和信息互补性,以增强医学图像在临床应用中的可读性和适用性。然而,现有手工设计的模型无法有效地提取关键目标特征,从而导致融合图像模糊、纹理细节丢失等问题。为此,提出了一种新的基于高低频特征分解的深度多模态医学图像融合网络,将通道注意力和空间注意力机制引入融合过程,在保持全局结构的基础上保留了局部纹理细节信息,实现了更加细致的融合。首先,通过预训练模型VGG-19提取两种模态图像的高频特征,并通过下采样提取其低频特征,形成高低频中间特征图。其次,在特征融合模块嵌入残差注意力网络,依次从通道和空间维度推断注意力图,并将其用来指导输入特征图的自适应特征优化过程。最后,重构模块形成高质量特征表示并输出融合图像。实验结果表明,该算法在Harvard公开数据集和自建腹部数据集峰值信噪比提升8.29%,结构相似性提升85.07%,相关系数提升65.67%,特征互信息提升46.76%,视觉保真度提升80.89%。

摘要：Superpixel segmentation is the oversegmentation of an image into a set of homogeneous regions. Superpixel has many specific properties and has been commonly used as supporting regions for primitives to reduce computations in various computer vision tasks. One property of superpixels is compactness, which is preferred in some applications. In this paper, we give an review on image superpixel segmentation algorithms proposed in recent years. Superpixel segmentation approaches are classified based on the compactness constraint and their main idea are introduced. We also compare these algorithms in visual and evaluate them with five common measurements.

摘要：Parameterization is one of the key problems in the construction of a curve to interpolate a set of ordered points. We propose a new local parameterization method based on the curvature model in this paper. The new method determines the knots by mi- nimizing the maximum curvature of quadratic curve. When the knots by the new method are used to construct interpolation curve, the constructed curve have good precision. We also give some comparisons of the new method with existing methods, and our method can perform better in interpolation error, and the interpolated curve is more fairing.

摘要：Point-based surface has been widely used in computer graphics for modeling, animation, visualization, simulation of liq- uid and so on. Furthermore, particle-based approach can distribute the surface sampling points and control its parameters according to the needs of the application. In this paper, we examine several kinds of algorithms presented over the last decades, with the main focus on particle sampling technologies for implicit surface. Therefore, we classify various algorithms into categories, describe main ideas behind each categories, and compare the advantages and shortcomings of the algorithms in each category.

摘要：It is proved that among the regular polygons with prime edges, only the regular polygons with Fermat prime edges are constructable with compass and straightedge. As 17 is a Fermat prime number, the construction of heptadecagon has been discussing all the time. Many different construction methods are proposed although they are based on the same theory. Simplification of the construction is still a sensible problem. Here, we propose a simple method for constructing regular heptadecagon with the fewest steps. The accumulation of construction errors is also avoided. This method is more applicable than the previous construction.

摘要：In this paper we present a new image zooming algorithm based on surface fitting with edge constraint. In surface fitting,we consider not only the relationship of corresponding pixels between the original image and the enlarged image, but also the neighbor pixels in the enlarged image according to the local structure of original image. Furthermore, during surface fitting, more interpolation constraints are used in the new algorithm for improving the precision of the super sampling pixels. The experimental results show that the new method outperforms the previous methods which based on surface fitting.

摘要：In this paper we present a novel image decomposition method via credible data fitting with local total variation filter. The oscillation rate is used to measure the image complexity and characteristics. The filter parameter can be determined by a fitting curve which is reconstructed by oscillation rate. In addition, the approximate Gaussian algorithm and integral image are used to reduce the algorithm computation and the sensitivity of the filter window selection. Experiments show the new method is better than the exist- ing methods.

摘要：含光源影响的雾图像中光源极易引入雾天原本不存在的光晕,从而影响大气光值和透射率估算的准确率,针对此问题,提出一种简单、易实现的去光源影响的雾天图像去雾算法.首先,基于超像素分割在CIELab颜色空间进行光源区域确定;然后,引入基于距离度量的光衰减因子计算并去除光源的影响;最后,以超像素块为单位估计大气光值,并采用加权导向滤波迭代优化透射率获得光源影响下的去雾结果图,提高效率和准确率.在光源影响下雾图集合和SOTS等数据集上进行了复原实验,将雾天图像复原结果与现有主流算法复原结果进行主客观对比,实验结果表明,文中算法复原结果的NIQE和BRISQUE值更低,并具有清晰度高、噪声低、纹理细节丰富和色彩恢复度高的优点.