Object segmentation and labeling by learning from examples

We propose a system that employs low-level image segmentation followed by color and two-dimensional (2-D) shape matching to automatically group those low-level segments into objects based on their similarity to a set of example object templates presented by the user. A hierarchical content tree data structure is used for each database image to store matching combinations of low-level regions as objects. The system automatically initializes the content tree with only "elementary nodes" representing homogeneous low-level regions. The "learning" phase refers to labeling of combinations of low-level regions that have resulted in successful color and/or 2-D shape matches with the example template(s). These combinations are labeled as "object nodes" in the hierarchical content tree. Once learning is performed, the speed of second-time retrieval of learned objects in the database increases significantly. The learning step can be performed off-line provided that example objects are given in the form of user interest profiles. Experimental results are presented to demonstrate the effectiveness of the proposed system with hierarchical content tree representation and learning by color and 2-D shape matching on collections of car and face images.     

Green learning: Introduction,examples and outlook

Rapid advances in artificial intelligence (AI) in the last decade have been largely built upon the wide applications of deep learning (DL). However, the high carbon footprint yielded by larger and larger DL networks has become a concern for sustainability. Furthermore, DL decision mechanism is somewhat obscure in that it can only be verified by test data. Green learning (GL) is being proposed as an alternative paradigm to address these concerns. GL is characterized by low carbon footprints, lightweight model, low computational complexity, and logical transparency. It offers energy-efficient solutions in cloud centers as well as mobile/edge devices. GL also provides a more transparent, logical decision-making process which is essential to gaining people’s trust. Several statistical tools such as unsupervised representation learning, supervised feature learning, and supervised decision learning, have been developed to achieve this goal in recent years. We have seen a few successful GL examples with performance comparable with state-of-the-art DL solutions. This paper introduces the key characteristics of GL, its demonstrated applications, and future outlook.     

Object localization and border detection criteria design in edge-based image segmentation: automated learning from examples

This paper provides methodology for fully automated model-based image segmentation. All information necessary to perform image segmentation is automatically derived from a training set that is presented in a form of segmentation examples. The training set is used to construct two models representing the objects--shape model and border appearance model. A two-step approach to image segmentation is reported. In the first step, an approximate location of the object of interest is determined. In the second step, accurate border segmentation is performed. The shape-variant Hough transform method was developed that provides robust object localization automatically. It finds objects of arbitrary shape, rotation, or scaling and can handle object variability. The border appearance model was developed to automatically design cost functions that can be used in the segmentation criteria of edge-based segmentation methods. Our method was tested in five different segmentation tasks that included 489 objects to be segmented. The final segmentation was compared to manually defined borders with good results [rms errors in pixels: 1.2 (cerebellum), 1.1 (corpus callosum), 1.5 (vertebrae), 1.4 (epicardial), and 1.6 (endocardial) borders]. Two major problems of the state-of-the-art edge-based image segmentation algorithms were addressed: strong dependency on a close-to-target initialization, and necessity for manual redesign of segmentation criteria whenever new segmentation problem is encountered.     

Perceptually uniform color spaces for color texture analysis: anempirical evaluation

RGB, a nonuniform color space, is almost universally accepted by the image processing community as the means for representing color. On the other hand, perceptually uniform spaces, such as L*a*b*, as well as approximately-uniform color spaces, such as HSV, exist, in which measured color differences are proportional to the human perception of such differences. This paper compares RGB with L*a*b* and HSV in terms of their effectiveness in color texture analysis. There has been a limited but increasing amount of work on the color aspects of textured images. The results have shown that incorporating color into a texture analysis and recognition scheme can be very important and beneficial. The presented methodology uses a family of Gabor filters specially tuned to measure specific orientations and sizes within each color texture. Effectiveness is measured by the classification performance of each color space, as well as by classifier-independent measures. Experimental results are obtained with a variety of color texture Images. Perceptually uniform spaces are shown to outperform RGB in many cases     

Incorporating prior information in machine learning by creatingvirtual examples

One of the key problems in supervised learning is the insufficient size of the training set. The natural way for an intelligent learner to counter this problem and successfully generalize is to exploit prior information that may be available about the domain or that can be learned from prototypical examples. We discuss the notion of using prior knowledge by creating virtual examples and thereby expanding the effective training-set size. We show that in some contexts this idea is mathematically equivalent to incorporating the prior knowledge as a regularizer, suggesting that the strategy is well motivated. The process of creating virtual examples in real-world pattern recognition tasks is highly nontrivial. We provide demonstrative examples from object recognition and speech recognition to illustrate the idea     

Analog VLSI neural networks: implementation issues and examples inoptimization and supervised learning

Time-critical neural network applications that require fully parallel hardware implementations for maximal throughput are considered. The rich array of technologies that are being pursued is surveyed, and the analog CMOS VLSI medium approach is focused on. This medium is messy in that limited dynamic range, offset voltages, and noise sources all reduce precision. The authors examine how neural networks can be directly implemented in analog VLSI, giving examples of approaches that have been pursued to date. Two important application areas are highlighted: optimization, because neural hardware may offer a speed advantage of orders of magnitude over other methods; and supervised learning, because of the widespread use and generality of gradient-descent learning algorithms as applied to feedforward networks     

Project based learning in mechatronics education in close collaboration with industrial: Methodologies,examples and experiences

The paper describes how the philosophy of project based learning (PBL) was integrated into the mechatronics capstone design course “Mechatronics Project Design and Management (MPDM)” at The Chinese–German School of Applied Sciences (Chinesisch–Deutsche Hochschule für Angewandte Wissenschaften, CDHAW) of Tongji University, Shanghai, China. The course teaching philosophy, implementation methodologies, examples and experiences were discussed.     

电力电子实训案例：感应耦合无线电能传输系统

本文以感应式无线电能传输系统作为电力电子教学实训案例,围绕当下新能源汽车无线充电技术的应用热点,结合电力电子教学大纲内容,通过实践操作,使学生加深对无线电能传输系统中逆变、整流、松耦合变压器等模块的理解,认识无线电能传输系统输出参数的频率相关性和距离相关性,具备初步的电路设计能力,从而在教学上做到理论与实践相互结合。     

Multi-objective super resolution: concepts and examples

Described methods for simultaneously generating the super-resolved depth map and the image from LR observations. Structural information is embedded within the observations and, through the two formulations of DFD and SFS problems, we were able to generate the super-resolved images and the structures. The first method described here avoids correspondence and warping problems inherent in current SR techniques involving the motion cue in the LR observations and uses a more natural depth-related defocus as a natural cue in real aperture imaging. The second method, while again avoiding the correspondence problems, also demonstrates the usefulness of the generalized interpolation scheme leading to more flexibility in the final SR image, in the sense that the LR image can be viewed at SR with an arbitrary light source position. The quality of the super-resolved depth and intensity maps has been found to be quite good. The MAP-MRF framework that was used in both methods models both the surface normal and the intensity field as separate MRFs, and this helps in regularizing the solution.     

Inductive grids in the resonant region: Theory and experiment

We compare rigorous modal expansion methods with transmission-line models for the spectral properties of inductive grids. We compare the predictions of the former with measurements of grid transmittance, reflectance and phase angles as a function of wavelength. We show that the rigorous theory can accurately reproduce measured grid properties, both for normal and oblique incidence, and for both fundamental polarizations of incident radiation. We pay particular attention to the so-called “thickness dip”, an abrupt drop in transmittance which occurs for one polarization at off-normal incidence. We study the variation of \(\lambda _a\) , the wavelength of the thickness dip, with grid parameters. We also study the variation of \(\lambda _m\) , the wavelength of maximum transmittance, with grid parameters. We give four design rules which enable the optimization of grid parameters for use in multi-element filter stacks not relying on interference properties. We present a comprehensive set of curves showing the variation of spectral transmittance with grid aperture and thickness, for both fundamental polarizations and for a range of angles of incidence.     

Inductive grids in the resonant region: Theory and experiment

Journal of Infrared, Millimeter, and Terahertz Waves -     

面向认知对抗的学习训练与仿真评估系统设计

针对认知电子战装备面临的作战场景复杂多样、真实数据难以获取、实战训练成本高昂等问题,为满足认知电子战系统方案论证、关键技术研究需求,将人工智能技术与系统仿真技术相结合,通过建立认知电子战装备及其典型作战对象的信号级模型,以及模拟电子战装备与作战对象在复杂电磁环境下的信息交互过程,构建面向未来战场认知对抗的学习训练与仿真...     

Intelligent inferencing and haptic simulation for Chinese acupuncture learning and training.

This paper presents an intelligent virtual environment for Chinese acupuncture learning and training using state-of-the-art virtual reality technology. It is the first step toward developing a comprehensive virtual human model for studying Chinese medicine. Students can learn and practice acupuncture in the proposed 3-D interactive virtual environment that supports a force feedback interface for needle insertion. Thus, students not only "see" but also "touch" the virtual patient. With high performance computers, highly informative and flexible visualization of acupuncture points of various related meridian and collateral can be highlighted to guide the students during training. A computer-based expert system using our newly proposed intelligent fuzzy petri net is designed and implemented to train the students to treat different diseases using acupuncture. Such an intelligent virtual reality system can provide an interesting and effective learning environment for Chinese acupuncture.     

校企合作、工学结合的技能人才培养模式分析

随着社会经济的不断发展和科技的日新月异，社会对学生的实践和学习能力提出了更高的要求。在此背景下，我国推出了一系列的保障性措施鼓励我国高校特别是高职类院校开展校企合作工作，通过校企合作模式，达到学以致用的目的，但是由于校企模式进入我国刚刚不久，合作机制尚不健全，造成在实践中出现了很多问题。本文将通过对校企合作办学的优势和现状分析，对校企合作办学提出符合实际工作的意见，为校企长久合作尽绵薄之力。     

贝叶斯网络结构学习研究

针对贝叶斯网络结构学习方法难以兼顾高准确率和高效率的问题,提出了一种基于Markov Chain Monte Carlo(MCMC)方法的贝叶斯网络结构学习方法的改进.改进包括:使用依赖关系分析,利用统计学的方法对采样空间进行大幅缩减,能够在精确控制准确度的情况下大幅提高时间效率;结合先验知识,从理论角度将先验知识融入评分中得到完全服从后验分布的结果;搜索最优子结构,对于特定的一些结构搜索最优子结构而不是采用贪心的方法,提高了贝叶斯网络结构学习的准确率.通过理论分析可以证明时间复杂度得到了大幅的降低.并且可以在牺牲可预知的准确率的情况下,将指数时间复杂度降为线性时间.大量的数据实验表明,经改进后的方法在时间和准确性上都具有良好的表现.     

采用粒子性对衍射现象进行研究的实例

采用粒子性观点,用概率波对光栅衍射和环孔衍射过程进行了讨论,所得结论与采用光的波动性观点的惠更斯-菲涅耳原理及Fourier变换方法所得结果相同。通过分析,进一步加深了对衍射的本质和光的粒子性的认识。