基于计算机视觉和声学的小粒咖啡破裂机理特性的研究

为提高小粒咖啡加工效果,从多角度分析其破裂机理。通过制备小粒咖啡样本,利用电子试验机发现小粒咖啡样本在不同阶段下的裂纹数目(宽度大于0.1 mm)与裂纹最大宽度的变化情况,并获得有无钻孔处理的小粒咖啡样本在裂纹压密阶段、增长阶段、平稳阶段、非平稳阶段的变化情况,以及两者的能量、应力变化趋势。由COMSOL分析有无钻孔处理的小粒咖啡样本裂纹声源位置以及数目。分析有无孔洞的小粒咖啡样本内应力波的损失系数以及小粒咖啡样本表面光点的损失系数,将应力波的损失系数、光点的损失系数所得理论小粒咖啡样本内应力结果与试验所得应力结果进行比较。结果显示:有无钻孔处理的小粒咖啡样本的裂纹声源数目,两者分别为1573、876,有钻孔处理的小粒咖啡样本要比无钻孔处理的小粒咖啡样本破裂程度更为明显。由应力波的损失系数、光点的损失系数所得理论小粒咖啡样本内应力结果与试验所得结果总体变化大致相同。通过SPSS求得有无孔洞的小粒咖啡样本情况下,应力波的损失系数所得应力波峰前后两者的相关系数分别为0.976、0.912;0.932、0.824。光点的损失系数所得应力波峰前后两者的相关系数分别为0.993、0.967;0.973、0.864。

A method of automatic plane detection without random search

Plane detection is a prerequisite for many computer vision tasks. This paper proposes a new method which can automatically detect planes from two projective images. Firstly, we modify Scott’s feature point matching method by post-processing its result with the concept of similarity, and then get the lines matching according to feature points matching based on the approximate invariance of the features’ distribution between two images. Finally, we group all feature points into subsets in terms of their geometric relations with feature lines as initial sets to estimate homography rather than by a random search strategy (like RANSAC) as in most existing methods. The proposed method is especially suitable to detecting planes in man-made scenes. This method is validated on real images.

Facial expression feature extraction method based on improved LBP

Local binary pattern(LBP)is an important method for texture feature extraction of facial expression.However,it also has the shortcomings of high dimension,slow feature extraction and noeffective local or global features extracted.To solve these problems,a facial expression feature extraction method is proposed based on improved LBP.Firstly,LBP is converted into double local binary pattern(DLBP).Then by combining Taylor expansion(TE)with DLBP,DLBP-TE algorithm is obtained.Finally,the DLBP-TE algorithm combined with extreme learning machine(ELM)is applied in seven kinds of ficial expression images and the corresponding experiments are carried out in Japanese adult female facial expression(JAFFE)database.The results show that the proposed method can significantly improve facial expression recognition rate.

Semantic image annotation based on GMM and random walk model

Automatic image annotation has been an active topic of research in computer vision and pattern recognition for decades.A two stage automatic image annotation method based on Gaussian mixture model(GMM) and random walk model(abbreviated as GMM-RW) is presented.To start with,GMM fitted by the rival penalized expectation maximization(RPEM) algorithm is employed to estimate the posterior probabilities of each annotation keyword.Subsequently,a random walk process over the constructed label similarity graph is implemented to further mine the potential correlations of the candidate annotations so as to capture the refining results,which plays a crucial role in semantic based image retrieval.The contributions exhibited in this work are multifold.First,GMM is exploited to capture the initial semantic annotations,especially the RPEM algorithm is utilized to train the model that can determine the number of components in GMM automatically.Second,a label similarity graph is constructed by a weighted linear combination of label similarity and visual similarity of images associated with the corresponding labels,which is able to avoid the phenomena of polysemy and synonym efficiently during the image annotation process.Third,the random walk is implemented over the constructed label graph to further refine the candidate set of annotations generated by GMM.Conducted experiments on the standard Corel5 k demonstrate that GMM-RW is significantly more effective than several state-of-the-arts regarding their effectiveness and efficiency in the task of automatic image annotation.

Improved nonconvex optimization model for low-rank matrix recovery

Low-rank matrix recovery is an important problem extensively studied in machine learning, data mining and computer vision communities. A novel method is proposed for low-rank matrix recovery, targeting at higher recovery accuracy and stronger theoretical guarantee. Specifically, the proposed method is based on a nonconvex optimization model, by solving the low-rank matrix which can be recovered from the noisy observation. To solve the model, an effective algorithm is derived by minimizing over the variables alternately. It is proved theoretically that this algorithm has stronger theoretical guarantee than the existing work. In natural image denoising experiments, the proposed method achieves lower recovery error than the two compared methods. The proposed low-rank matrix recovery method is also applied to solve two real-world problems, i.e., removing noise from verification code and removing watermark from images, in which the images recovered by the proposed method are less noisy than those of the two compared methods.

Design and Implementation of User Centered Interface on Mobile Phone

Mobile device research has been increasing rapidly in Human Computer Interaction （HCI） recently. Following this trend, this paper proposes a user-centered interface, which has been designed, completely installed and independently run on a mobile phone. Video signal is steamed through its camera as the image input to the interface by employing techniques of image processing, computer vision and graphics to identify automatically absolute positions of human face, neck and two hands. A paradigm is also put up theoretically. And it embeds this interface to perceive the human postures and convert them into relaxed comic character according to its context.

Recognition of Multifunctional Coded Target in Single-camera Mobile 3D-vision Coordination Measurement

Single-camera mobile-vision coordinate measurement is one of the primary methods of 3D-coordinate vision measurement, and coded target plays an important role in this system. A multifunctional coded target and its recognition algorithm is developed, which can realize automatic match of feature points, calculation of camera initial exterior orientation and space scale factor constraint in measurement system. The uniqueness and scalability of coding are guaranteed by the rational arrangement of code bits. The recognition of coded targets is realized by cross-ratio invariance restriction, space coordinates transform of feature points based on spacial pose estimation algorithm, recognition of code bits and computation of coding values. The experiment results demonstrate the uniqueness of the coding form and the reliability of recognition.

Unwrapping and stereo rectification for omnidirectional images

Omnidirectional imaging sensors have been used in more and more applications when a very large field of view is required.In this paper,we investigate the unwrapping,epipolar geometry and stereo rectification issues for omnidirectional vision when the particular mirror model and the camera parameters are unknown in priori.First,the omnidirectional camera is calibrated under the Taylor model,and the parameters related to this model are obtained.In order to make the classical computer vision algorithms of conventional perspective cameras applicable,the ring omnidirectional image is unwrapped into two kinds of panoramas:cylinder and cuboid.Then the epipolar geometry of arbitrary camera configuration is analyzed and the essential matrix is deduced with its properties being indicated for ring images.After that,a simple stereo rectification method based on the essential matrix and the conformal mapping is proposed.Simulations and real data experimental results illustrate that our methods are effective for the omnidirectional camera under the constraint of a single view point.