基于分形特征的二值图像检索方法的研究

论述了基于分形特征的二值图像检索方法。图像的内容由4种特征来描述:图像分形维数、图像分形矢量、边界分形矢量和骨架分形矢量。实验表明该方法计算简单、有效,匹配快速,检索结果比较理想,只要查询图像在图库中,就一定能通过该方法检索出来。另外,该方法还具有一定的鲁棒性,证明这种检索方法是具有较大实用意义的。     

Recognition of shapes by attributed skeletal graphs

In this paper, we propose a framework to address the problem of generic 2-D shape recognition. The aim is mainly on using the potential strength of skeleton of discrete objects in computer vision and pattern recognition where features of objects are needed for classification. We propose to represent the medial axis characteristic points as an attributed skeletal graph to model the shape. The information about the object shape and its topology is totally embedded in them and this allows the comparison of different objects by graph matching algorithms. The experimental results demonstrate the correctness in detecting its characteristic points and in computing a more regular and effective representation for a perceptual indexing. The matching process, based on a revised graduated assignment algorithm, has produced encouraging results, showing the potential of the developed method in a variety of computer vision and pattern recognition domains. The results demonstrate its robustness in the presence of scale, reflection and rotation transformations and prove the ability to handle noise and occlusions.     

Route guidance by a car navigation system based on augmented reality

Car navigation systems play a prominent role in road traffic safety and traffic regulation. However, it is necessary to improve the route guidance of car navigation systems so that they accurately and quickly recognize small differences in location. Thus, to increase the ease of understanding and safety of car navigation systems, navigation systems based on augmented reality have been proposed for providing guidance at road intersections. We are currently developing a car navigation system based on augmented reality, called AR‐Navi. We investigated designs for the display of road intersection guidance that can be easily understood even when limited information is available and proposed a “best shot” display method that does not use moving images. In addition, we implemented a prototype system that includes these methods and conducted driving experiments on public roads to evaluate the ease of understanding and safety of AR‐Navi. Using the evaluation results, we confirmed that the ease of understanding and safety is similar in the case of AR‐Navi and CG‐Navi. We also clarified the characteristics of AR‐Navi. © 2012 Wiley Periodicals, Inc. Electr Eng Jpn, 180(2): 43–54, 2012; Published online in Wiley Online Library (wileyonlinelibrary.com). DOI 10.1002/eej.22278     

How to draw free trees inside bounded rectilinear polygons

Drawing graphs on a 2D grid with prescribed size is NP-complete, even if we restrict ourselves to planar orthogonal grid drawings of trees. In this paper, we introduce a new algorithm for polyline drawing of free trees on 2D grids which are bounded by rectilinear polygons. Our algorithm uses straight skeleton and simulated annealing and aims to distribute the vertices of the given trees uniformly on the given bounded grids. Our experimental results show that our algorithm is relatively successful to achieve uniform distribution of the nodes of the given trees. To our knowledge, this paper is the first attempt to develop algorithms that draw trees on restricted 2D grids which are bounded by simple rectilinear polygons.     

Supporting comprehensible presentation of clone candidates through two-dimensional maximisation

Duplicated code detection has been an active research field for several decades. Although many algorithms have been proposed, only a few researches have focussed on the comprehensive presentation of the detected clones. During the evaluation of clone detectors developed by the authors, it was observed that the results of the clone detectors were hard to comprehend. Therefore, in this paper a broadly suitable grouping method with which clone pairs can be easily grouped together to provide a more compact result is presented. The grouping algorithm is examined and a more precise revised algorithm is proposed to present all of the candidates to the user.     

面向可解释性的物体拓扑结构骨架表征方法

目的 模式识别中，通常使用大量标注数据和有效的机器学习算法训练分类器应对不确定性问题。然而，这一过程缺乏知识表征和可解释性。认知心理学和实验心理学的研究表明，人类往往不使用代价如此巨大的机制，而是使用表征、归纳、推理、解释和约束传播等与符号主义人工智能方法类似的手段来应对物体识别中的不确定性并提供可解释性。因此本文旨在从传统的符号计算出发，利用骨架拓扑结构表征提供一种可解释性的思路。方法 以骨架树为基本手段来形成物体拓扑结构特征和几何特征的形式化表征，并基于泛化框架对少量同类表征进行知识抽取来形成关于物体类别的知识概括显式化表征。结果 在形成物体类别的概括表征实验中，通过路径重建直观展示了同类属物体上得到的最一般表征的几何物理意义。在可解释性验证实验中，通过跨数据的拓扑应用展示了新测试样本相对于概括表征的特定差异，表明该表征具有良好的可解释性。最后在形状补全的不确定性推理实验中，不仅可以得到识别结论，而且清晰展示了识别背后做出的判断依据，进一步验证了该表征的可解释性。结论 实验表明一般化的形式表征能够应对尺寸、颜色和形状等不确定性问题，本文方法避免了基于纹理特征所带来的不确定性，适用于任意基于基元的表征方式，具有更好的鲁棒性、普适性和可解释性，计算代价更小。     

Stabilizing effect of the cyclodextrins additive to spray-dried particles of curcumin/polyvinylpyrrolidone on the supersaturated state of curcumin

Although curcumin is considered to have various therapeutic effects, its use as a functional food or supplement is restricted owing to its low water solubility and bioavailability. To increase the solubility of curcumin in water, the use of polyvinylpyrrolidone (PVP) and vinylpyrrolidone-vinyl acetate copolymers with a pyrrolidone skeleton was noted to be promising. In particular, the bi-component formulations of curcumin/PVP prepared through spray drying exhibited an amorphous state in powder X-ray diffraction observations and temporally increased the apparent solubility of curcumin to over 5000 times that of untreated curcumin; nevertheless, after 24 h, the solubility decreased owing to the unstable supersaturated state of curcumin. The addition of α-cyclodextrin (α-CyD) in the bi-component curcumin/PVP formulation helped maintain the supersaturated state of curcumin, whereas the addition of β- and γ-CyD led to the collapse of the supersaturated state. The addition of α-CyD can likely help inhibit the nucleation and crystal growth of curcumin, through the interaction among the solubilized units of curcumin/PVP and α-CyD.     

Laser damage resistance of plasma-sprayed alumina and honeycomb skeleton/alumina composite ceramic coatings

Al₂O₃ and honeycomb skeleton-Al₂O₃ composite coatings on Titanium alloy (Ti–6Al–4V) were prepared by atmospheric plasma spraying. A laser ablation experiment on as-sprayed coatings was performed. In this paper, the laser damage resistance, microstructure, phase composition of Al₂O₃ coatings were examined. 3D Dimensional Confocal Microscopy, Scanning Electron Microscopy (SEM), X-ray Diffraction (XRD), and Energy Dispersive Spectrometry (EDS) characterized the laser damage morphology, microstructure, phase composition, and element analysis, respectively. The influence of the honeycomb skeleton on the laser ablation damage on as-sprayed coatings was investigated by a comparative analysis of the laser damage morphology with different laser ablation times and gas flow. The results show that the honeycomb skeleton raises thermal conductivity and thermal diffusivity. Moreover, a “tower”-like dendrite was generated during the laser irradiation of the composite coating. The honeycomb skeleton refined the structure, suppressed crack propagation, and reduced the influence of gas flow on cracks. Under the same experimental laser ablation parameters, the laser damage area of the honeycomb skeleton-Al₂O₃ composite coating was smaller than that of the Al₂O₃ coating. It was demonstrated that the laser damage resistance of the honeycomb skeleton-Al₂O₃ composite coating was superior to that of the Al₂O₃ coating.     

How neutral coloured backgrounds affect the attractiveness and expensiveness of fresh produce

The colour of the background on which products are presented may affect their perceived attractiveness. In order to find out on which type of background various fresh food products look most attractive, we presented five different vegetables (tomato, carrot, yellow bell pepper, eggplant, mushroom) on five different backgrounds with neutral grey colours varying in degree of blackness: 5, 30, 50, 65, and 90%. Forty-six participants provided colour matches for the vegetables and evaluated them on 10 attributes.Overall, the blackness of the backgrounds had little or no effect on the perceived colour of the vegetable. Only for carrots we found a small but significant difference, mainly between the 5% and 90% blackness backgrounds. On the darkest background, the carrot would be perceived as a bit lighter, more saturated, and more yellow rather than red, compared to the lightest background.Differences in perceived attractiveness on the grey backgrounds varied between 0.3 and 1.0 units on a 9-point scale. Attractiveness and expensiveness ratings for most vegetables were highest on the 90% blackness background. In comparison to our previous study where we presented vegetables on hued backgrounds, differences between mean attractiveness ratings were smaller. Because mean attractiveness ratings in the current study were higher, we expect that grey backgrounds are more likely to present vegetable assortments with a variety of hues in an attractive way than hued backgrounds.