Food recognition using neural network classifier and multiple hypotheses image segmentation

ABSTRACT

This paper proposes the multiple-hypotheses image segmentation and feed-forward neural network classifier for food recognition to improve the performance. Initially, the food or meal image is given as input. Then, the segmentation is applied to identify the regions, where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the features of every food item are extracted by the global feature and local feature extraction. After the features are obtained, the classification is performed for each segmented region using a feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food volume and (ii) calorie and nutrition measure based on mass value. The experimental results and performance evaluation are validated. The outcome of the proposed method attains 0.947 for Macro Average Accuracy (MAA) and 0.959 for Standard Accuracy (SA), which provides better classification performance.     

Breakdown characteristics of oil and paper insulation for a very fast transient voltage

This paper describes the dielectric breakdown characteristics of oil and oil‐impregnated paper for very fast transient (VFT) voltages. Blumlein circuits generate VFT voltages of 60 and 300 ns in a pulse width that simulates disconnecting switching surges in gas‐insulated switch gears. We measured the breakdown voltages of needle‐to‐plane, plane‐to‐plane oil gaps and several pieces of paper between plane electrodes for VFT and lightning impulse voltages. The measured data were formulated in V‐t characteristics and Weibull probability distributions. The inclination n of V‐t characteristics of insulating paper is 150, which is less than n = 13.7 of the plane‐to‐plane oil gap in the VFT time range. The shape parameters of Weibull distribution obtained in this study show that the scattering of breakdown voltages of paper is much less than that of oil. © 2002 Wiley Periodicals, Inc. Electr Eng Jpn, 141(4): 16–24, 2002; Published online in Wiley InterScience ( www.interscience.wiley.com ). DOI 10.1002/eej.10043     

钠冷快堆中喷雾钠火的计算分析

根据钠冷快堆中喷雾钠火的特点建立了理论模型，编制了SSPRAY程序。该程序模拟钠喷雾燃料过程中钠滴的运动、钠和氧气的燃烧反应、热量传递和质量传递等瞬态过程。用该程序计算了气体和墙壁温度、气体压力、氧气摩尔份额、喷雾流燃烧速率和热量热递速率等主要参数。利用AI实验数据和美国SPRAY－3A的计算结果对程序进行了验证，结果符合较好。     

Cluster analysis in industrial market segmentation through artificial neural network

Market segmentation has commonly applied cluster analysis. This study intends to make the comparison of conventional two-stage method with proposed two-stage method through the simulated data. The proposed two-stage method is the combination of self-organizing feature maps and K-means method. The simulation results show that the proposed scheme is better than the conventional two-stage method based on the rate of misclassification.     

气体绝缘封闭电器的高速瞬变过程和现场试验

随着ＧＩＳ的工作电压不断提高和发展，一系列新的现象和问题也同时出现。从国外一些科研，设计，制造部门所研究发表的内容看，大致有隔离开关操作和高速瞬变过程，粒子影响和对干扰定位的技术，元件的监督，现场试验等课题，本文对以上问题加以综合介绍。     

江苏省县级电力信息网的3种组网方案

对江苏省县级电力信息网工程采用的利用ATM设备、SDH设备和WDM设备的3种组网方案进行了阐述，并分析了各种方案的优缺点。     

A Novel Segmentation and Feedback Model for Resolving Contention in Optical Burst Switching

A novel segmentation and feedback model (SFM) applied to resolve contention is proposed. Simulation and performance analyses show that the SFM effectively avoids contentions in optical burst switching (OBS). The long delay time of deflection routing and the immature technology of wavelength converters and optical buffers are not deployed in the SFM. The SFM does not only realize fast switching but also allows preemption by higher priority bursts.     

Learning-based dynamic coupling of discrete and continuous trackers

We present a data-driven dynamic coupling between discrete and continuous methods for tracking objects of high dofs, which overcomes the limitations of previous techniques. In our approach, two trackers work in parallel, and the coupling between them is based on the tracking error. We use a model-based continuous method to achieve accurate results and, in cases of failure, we re-initialize the model using our discrete tracker. This method maintains the accuracy of a more tightly coupled system, while increasing its efficiency. At any given frame, our discrete tracker uses the current and several previous frames to search into a database for the best matching solution. For improved robustness, object configuration sequences, rather than single configurations, are stored in the database. We apply our framework to the problem of 3D hand tracking from image sequences and the discrimination between fingerspelling and continuous signs in American Sign Language.     

一种基于MPEG-2的立体视频编码中的视差匹配快速算法

高效，快速的视差匹配是立体视频处理中的一项关键技术。本文在分析立体图像序列的视差矢量与运动矢量之间的相关性的基础上，提出一种基于MPEG-2的立体视频编码中的视差匹配快速算法。实验结果表明，与全搜索法相比，在保证重建图像质量的前提下，快速算法能显著降低视差估计的计算复杂度。     

纳秒级上升时间的高压脉冲群电源

按照IEC 61000-4-4/GB 17626.4—1998的要求，首先应用PSPICE仿真确定电路中各元件的参数值，然后基于拉普拉斯变换用MATLAB求解二阶电路验证各元件参数。在此基础上研制了一台以开关电源作为高压直流电源、以氢闸流管作为主控开关的脉冲群电源。该电源体积小、重量轻、效率高、成本低廉。试验结果表明，其输出信号符合标准要求，可用于快速瞬变脉冲群抗扰度试验。