Radial invariant of 2D and 3D Racah moments

In this paper, we introduce new sets of 2D and 3D rotation, scaling and translation invariants based on orthogonal radial Racah moments. We also provide theoretical mathematics to derive them. Thus, this work proposes in the first case a new 2D radial Racah moments based on polar representation of an object by one-dimensional orthogonal discrete Racah polynomials on non-uniform lattice, and a circular function. In the second case, we present new 3D radial Racah moments using a spherical representation of volumetric image by one-dimensional orthogonal discrete Racah polynomials and a spherical function. Further 2D and 3D invariants are extracted from the proposed 2D and 3D radial Racah moments respectively will appear in the third case. To validate the proposed approach, we have resolved three problems. The 2D/ 3D image reconstruction, the invariance of 2D/3D rotation, scaling and translation, and the pattern recognition. The result of experiments show that the Racah moments have done better than the Krawtchouk moments, with and without noise. Simultaneously, the mentioned reconstruction converges rapidly to the original image using 2D and 3D radial Racah moments, and the test 2D/3D images are clearly recognized from a set of images that are available in COIL-20 database for 2D image, and PSB database for 3D image.     

基于弹簧质点模型的二维/三维映射算法*

提出了一种用于服装设计的二维/三维映射算法.该算法基于弹簧质点变形模型,服装裁剪片二维到三维映射及三维到二维映射可以在该模型中得到统一的实现.在服装裁剪片二维到三维的映射过程中,二维裁剪片被放置在人体模型附近的初始位置,在缝合力的作用下,裁剪片自动变形并缝合到人体模型上.在服装裁剪片三维到二维映射的过程中,三维裁剪片被初始映射到指定的平面内,在弹性变形力的作用下,逐步变形并得到最终的二维裁剪片.在进行服装裁剪片二维到三维映射的过程中,考虑了干涉检验的问题.     

Radial Hahn Moment Invariants for 2D and 3D Image Recognition

Recently, orthogonal moments have become efficient tools for two-dimensional and three-dimensional (2D and 3D) image not only in pattern recognition, image vision, but also in image processing and applications engineering. Yet, there is still a major difficulty in 3D rotation invariants. In this paper, we propose new sets of invariants for 2D and 3D rotation, scaling and translation based on orthogonal radial Hahn moments. We also present theoretical mathematics to derive them. Thus, this paper introduces in the first case new 2D radial Hahn moments based on polar representation of an object by one-dimensional orthogonal discrete Hahn polynomials, and a circular function. In the second case, we present new 3D radial Hahn moments using a spherical representation of volumetric image by one-dimensional orthogonal discrete Hahn polynomials and a spherical function. Further 2D and 3D invariants are derived from the proposed 2D and 3D radial Hahn moments respectively, which appear as the third case. In order to test the proposed approach, we have resolved three issues: the image reconstruction, the invariance of rotation, scaling and translation, and the pattern recognition. The result of experiments show that the Hahn moments have done better than the Krawtchouk moments, with and without noise. Simultaneously, the mentioned reconstruction converges quickly to the original image using 2D and 3D radial Hahn moments, and the test images are clearly recognized from a set of images that are available in COIL-20 database for 2D image, and Princeton shape benchmark (PSB) database for 3D image.     

Radial Meixner Moment Invariants for 2D and 3D Image Recognition

In this paper, we propose a new set of 2D and 3D rotation invariants based on orthogonal radial Meixner moments. We also present a theoretical mathematics to derive them. Hence, this paper introduces in the first case a new 2D radial Meixner moments based on polar representation of an object by a one-dimensional orthogonal discrete Meixner polynomials and a circular function. In the second case, we present a new 3D radial Meixner moments using a spherical representation of volumetric image by a one-dimensional orthogonal discrete Meixner polynomials and a spherical function. Further 2D and 3D rotational invariants are derived from the proposed 2D and 3D radial Meixner moments respectively. In order to prove the proposed approach, three issues are resolved mainly image reconstruction, rotational invariance and pattern recognition. The result of experiments prove that the Meixner moments have done better than the Krawtchouk moments with and without nose. Simultaneously, the reconstructed volumetric image converges quickly to the original image using 2D and 3D radial Meixner moments and the test images are clearly recognized from a set of images that are available in a PSB database.     

A novel 2D and 3D multimodal approach for in-the-wild facial expression recognition

This study proposes a novel deep learning approach for the fusion of 2D and 3D modalities in in-the-wild facial expression recognition (FER). Different from other studies, we exploit the 3D facial information in in-the-wild FER. In particular, in-the-wild 3D FER dataset is not widely available; therefore, 3D facial data are constructed from available 2D datasets thanks to recent advances in 3D face reconstruction. The 3D facial geometry features are then extracted by deep learning technique to exploit the mid-level details, which provides meaningful expression for the recognition. In addition, to demonstrate the potential of 3D data on FER, the 2D projected images of 3D faces are taken as additional input to FER. These features are then jointly fused with 2D features obtained from the original input. The fused features are then classified by support vector machines (SVMs). The results show that the proposed approach achieves state-of-the-art recognition performances on Real-World Affective Faces (RAF) and Static Facial Expressions in the Wild (SFEW 2.0), and AffectNet dataset. This approach is also applied to a 3D FER dataset, i.e. BU-3DFE, to compare the effectiveness of reconstructed and available 3D face data for FER. This is the first time such a deep learning combination of 3D and 2D facial modalities is presented in the context of in-the-wild FER.     

2D and 3D palmprint fusion and recognition using PCA plus TPTSR method

This paper employs both two-dimensional (2D) and three-dimensional (3D) features of palmprint for recognition. While 2D palmprint image contains plenty of texture information, 3D palmprint image contains the depth information of the palm surface. Using two different features, we can achieve higher recognition accuracy than using only one of them. In addition, we can improve the robustness. To recognize palmprints, we use two-phase test sample representation (TPTSR) which is proved to be successful in face recognition. Before TPTSR, we perform principal component analysis to extract global features from the 2D and 3D palmprint images. We make decision based on the fusion of 2D and 3D features matching scores. We perform experiments on the PolyU 2D + 3D palmprint database which contains 8,000 samples and achieve satisfying recognition performance.     

平面电子地图和三维虚拟场景的通信

目前,平面电子地图与三维虚拟场景通信方面的研究是个热点。文章先探讨了两者的结合的必要性,然后对平面电子地图与三维虚拟场景通信进行深入的研究。着重分析了通信的基本原理和表现形式。提供实现通信的思路有:栅格地图和三维虚拟场景的结合;二维矢量地图和三维虚拟场景的结合。结合事例和方案,对二维矢量地图和三维虚拟场景的结合的思路进行了研究。介绍了平面电子地图与三维虚拟场景通信实现的流程和具体实现的方法。     

3D and 2D/3D holograms model

The estimating problem of 3D holograms orientation selectivity on angular, orthogonal, and azimuthal sensitivity parameters is formulated and solved. Tenfold increase of density 3D, 2D/3D holograms in comparison with 2D holograms at given selectivity for ones is shown in theory and experimentally.     

一种无缝集成的二三维联动WebGIS设计及实现

传统二维GIS具有强大的空间查询、分析功能,而三维GIS具有很好的空间直观显示性。实现二三维GIS的联动与互操作,可以充分发挥二三维GIS各自的优点。本文提出了一种有效可行的解决方案,实现了具有实时联动漫游、缩放和信息标注等功能的WebGIS二三维联动系统。     

基于人体行为3D模型的2D行为识别

针对行为识别中行为者朝向变化带来的问题, 提出了一种基于人体行为3D模型的2D行为识别算法. 在学习行为分类器时, 以3D占据网格表示行为样本, 提取人体3D关节点作为描述行为的特征, 为每一类行为训练一个基于范例的隐马尔可夫模型(Exemplar-based hidden Markov model, EHMM), 同时从3D行为样本中选取若干帧作为3D关键姿势集, 这个集合是连接2D观测样本和人体3D关节点特征的桥梁. 在识别2D行为时, 2D观测样本序列可以由一个或多个非标定的摄像机采集. 首先在3D关键姿势集中为每一帧2D观测样本寻找与之最匹配的3D关键姿势帧, 之后由行为分类器对2D观测样本序列对应的3D关键姿势序列进行识别. 该算法在训练行为分类器时要进行行为者的3D重构和人体3D关节点的提取, 而在识别2D行为时不再需要进行3D重构. 通过在3个数据库上的实验, 证明该算法可以有效识别行为者在任意朝向下的行为, 并可以适应不同的行为采集环境.     

Comparison of 3D and 2D menus for cell phones

Few prior studies have directly compared 3D and 2D menus for cell phones. Because the technology available for cell phone interfaces has changed in recent years, interface guidelines for cell phones need to be re-evaluated, especially with regard to the use of 3D interfaces. In the present study, we first compared performance of tasks for menus with different breadths using three 3D menus (revolving stage, 3D carousel, and collapsible cylindrical tree) shown on the small display screen of an iPhone® simulator. Performance was best with the revolving stage menu, and there was a nonsignificant tendency for it to be rated as preferred by the participants. Then, we compared the 3D revolving stage menu to a 2D overview menu, for tasks of different complexity and menus of different breadths, on an actual iPhone. The 3D menu was preferred by users at high breadth levels, and the 2D menu showed better performance than the 3D menu with low memory load. From the results, recommendations for the design of menus for small displays were developed.     

2D representation of facial surfaces for multi-pose 3D face recognition

The increasing availability of 3D facial data offers the potential to overcome the intrinsic difficulties faced by conventional face recognition using 2D images. Instead of extending 2D recognition algorithms for 3D purpose, this letter proposes a novel strategy for 3D face recognition from the perspective of representing each 3D facial surface with a 2D attribute image and taking the advantage of the advances in 2D face recognition. In our approach, each 3D facial surface is mapped homeomorphically onto a 2D lattice, where the value at each site is an attribute that represents the local 3D geometrical or textural properties on the surface, therefore invariant to pose changes. This lattice is then interpolated to generate a 2D attribute image. 3D face recognition can be achieved by applying the traditional 2D face recognition techniques to obtained attribute images. In this study, we chose the pose invariant local mean curvature calculated at each vertex on the 3D facial surface to construct the 2D attribute image and adopted the eigenface algorithm for attribute image recognition. We compared our approach to state-of-the-art 3D face recognition algorithms in the FRGC (Version 2.0), GavabDB and NPU3D database. Our results show that the proposed approach has improved the robustness to head pose variation and can produce more accurate 3D multi-pose face recognition.     

一种2D+3D人耳融合识别方法研究

提出一种2D和3D模式相融合的人耳识别方法.利用基于Adaboost算法的人耳检测器在2D图像上进行人耳检测,在对应的深度图像中定位出人耳区域.对于2D人耳图像,利用核Fisher鉴别分析法进行特征提取,再利用最近邻分类器进行识别;对于3D人耳深度图,利用3D局部二值模式进行特征提取,结合几何约束和位置约束在测试耳和注册原型耳上进行特征点匹配,并利用匹配点数进行识别.最后将两者进行决策层融合.在UND人耳图像库上的实验结果表明,与单独2D或3D人耳识别相比,文中提出的2D+3D人耳融合识别方法在光照变化情况下能取得更好的识别性能.     

Taking a 2D educational title into 3D

Maturing software for creating real-time interactive 3D (3D/VR) and hardware enabling its delivery give us the chance to explore practical issues involved in making commercially viable 3D/VR content. In October 1996, The Learning Company released the educational title Logic Quest, built using Sense8's WorldToolKit software. One of the first commercial 3D/VR children's titles for Windows 95, Logic Quest provides an example of what is involved in converting a 2D title (Think Quick!) to 3D. Studying the process the company followed lets us evaluate some of the challenges and benefits of moving a 2D title to 3D     

Exploiting AML algorithm for multiple acoustic source 2D and 3D DOA estimations

The approximate maximum likelihood (AML) algorithm shows promises for joint estimations of acoustic source spectrum and direction-of-arrival (DOA). For the multisource case, the AML algorithm remains feasible as one considers an alternating projection procedure based on sequential iterative search on single source parameters. In order to perform multisource beamforming operations, earlier, we used a two-dimensional (2D) sensor array with 2D AML to obtain the DOA estimations for sources in the far field of t...     

基于机器学习和几何变换的实时2D/3D脊椎配准

在图像引导的脊柱手术中,实时高效的2D/3D配准是一项重要且具有挑战性的任务.通常的2D/3D配准一般是将三维图像投影到二维平面,然后进行2D/2D的配准.由于投影空间涉及到3个平移以及3个旋转参数,其投影空间的复杂度为O（n6）,使得配准很难兼具高准确性和高实时性.本文提出了一个结合机器学习与几何变换的2D/3D配准方法,首先,使用统计形状模型对目标脊椎进行建模,并构建了一种新的投影方式,使得6个投影参数中的4个可以使用几何的方法计算出来;接下来利用回归学习的方法学习目标脊椎的形状与投影参数之间的关系;最终,结合学到的关系和几何变换完成配准.本方法的两个姿态参数的平均预测误差为0.84°和0.81°,平均目标配准误差（Mean target registration error,mTRE）为0.87mm,平均配准时间为0.9s.实验结果表明本方法具有很好的实时性和准确性.     

Java 3D中的Text2D的扩展与应用

Java3D中Text2D类虽然能生成二维文本,但由于文本的字体、字号、颜色在文本生成后就不可改变,字的排列也只有“从左向右”方式。所以,Text2D不能满足交互式建立虚拟环境中二维文本的需要。Java3D中的Text3D类支持交互式地建立文本,但Text3D的三维文本却不能退化为二维文本,这使得Text3D不能替代Text2D。所以,有必要扩展Text2D类以支持交互地建立虚拟环境中二维文本。文章给出实现这一扩展的关键技术,为用Java3D开发交互式虚拟环境建模器的二维文本生成功能提供支持。扩展的Text2D在智能型虚拟汽车驾驶道路环境建模器中的使用表明它是有效的。     

Extending distortion viewing from 2D to 3D

Addresses the visual exploration of 3D information layouts. Several visual exploration techniques have been proposed for 2D information layouts. Many of these try to take advantage of humans' natural visual pattern-recognition abilities to understand global relationships while simultaneously integrating this knowledge with local details. This desire for detail-in-context views (also called fisheye, multiscale and distortion views) has fueled considerable research in the development of distortion viewing tools. Generally, these tools provide space for magnification of local detail by compressing the rest of the image. In considering a possible detail-in-context view for 3D layouts, we first examine 2D distortion techniques, bearing in mind the particular 3D problem of occlusion. Comparing 2D and 3D information layout adjustment tools leads directly to a 3D visual access tool that clears a line of sight to any region of interest. While our technique can extend to any type of 3D information display, we focus on graphs     

基于ArcEngine的三维GIS的设计与实现

三维GIS能够很好地描述我们的三维客观世界,但在查询分析以及宏观表达等方面尚有不足之处,目前不同的应用目的往往需要二维GIS与三维GIS两种方式交替运作。因此提出在构建三维GIS应用系统的基础上融合二维GIS的功能,并成功开发实现了一个实例应用系统。     

Switching directional BLUs for full‐resolution auto‐stereoscopic 3D/2D and 2D/3D LCDs

Directional backlight unit (BLU) design concept was applied to realize full‐resolution field alternate auto‐stereoscopic liquid crystal displays (LCDs) with built‐in 3D/2D and 2D/3D. The application‐oriented BLU design requires priority in realizing 2D mode or 3D mode. The switching characteristic of BLU with two confronting illuminating sets was applied to build 2D mode into 3D display and 3D mode into 2D display. An LCD with 2D mode as primary function requires higher double‐sided luminance uniformity than 3D mode. On the other hand, an LCD with 3D mode requires higher single‐sided luminance uniformity than 2D mode. For increasing the double‐sided luminance uniformity for 2D mode as a primary function of the display, the former BLU design was realized by using uniform prismatic structure, that is, using uniform bilateral prismatic structure with a cross section of isosceles triangle on the back surface of the light‐guide plate. For increasing single‐sided luminance uniformity for 3D mode as a primary function of the display, the latter was realized by using graded angle design, that is, unilateral prisms with a cross section of a scalene triangle on the back surface of the light‐guide plate. The LCDs of small‐sized‐handheld game devices and still cameras were fabricated using the 3D/2D and 2D/3D displays.