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.     

点状屏彩色显示管校正透镜优化设计

本文在条状屏彩色显象管校正透镜设计的基础上，提出了蹼状屏彩色显示管校正透镜的优化设计方法并给出了设计实例，通过计算机模拟电子束轨迹和光线追迹，分析了校正透镜面型修正程序的精度。     

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.     

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.     

Results of the ASTM field test of tristimulus weighting functions

In 1993, the American Society for Testing and Materials carried out a field test of newly calculated tristimulus weighting factors. These weighting factors had been calculated by a method proposed by Venable. the test also included a method of correction for bandpass dependence put forth by Stearns. the purpose of the trial was to assess the possible reduction in bandpass dependence introduced by each of these sets of weights. A large number of sets of spectral data were gathered from the cooperators in the field test. Results of integration by the various sets of tristimulus weighting factors were calculated. A total of 15 120 color differences were calculated and statistics were derived to test the probable error resulting from each method of correction. Errors attributable to bandpass dependence were on the order of a few tenths to as much as one CIELAB unit when uncorrected weight sets were used. These errors could be reduced to a few hundreths of a CIELAB unit, and in some cases to a few thousandths of a unit, by employing one correcting strategy or the other. an overall mix of strategies was ultimately chosen to minimize the bandpass dependence over the entire range of weight sets. Utilizing this mixed strategy, the median error introduced into 10-nm integration by bandpass dependence was only 0.004 CIELAB units. © 1995 John Wiley & Sons, Inc.     

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.     

Treatment of Humic Waters By Ozone

Two different generators for ozone were tested, a traditional electrical discharge generator and a generator based upon UV–irradiation of air at 150–180 nm. It was demonstrated that the traditional generator gave slightly higher reductions in levels of color for equivalent ozone dosages. Both gases affected the molecular weight distribution in the way that the bigger molecules were broken down to smaller ones. No significant difference between the molecular weight reduction efficiency of the gases was found.     

彩色显像管电子束亮度分布自动测量系统

电子束轮廓的描述是彩色显像管特性检测中的难点之一。采用光电转换与计算机信息处理技术，通过自动调整边界条件和三次样条拟合的方法建立了电子束轮廓自动测量系统。与传统测量方法相比，该系统精度高，测试速度快，极大地减轻了测试人员的工作强度，并增加了对排列率和并列率等的测试功能。     

动态聚焦电子枪的模拟与实验研究

动态聚焦技术是为了满足大屏幕高分辨率彩色显像管及高分辨率彩色显示管的发展需求而产生的一项新技术。在本文中，作者首先提出了一种动态聚焦电子枪结构，进行了数值计算与分析，制作了动态聚焦电子枪并装管实验。通过对实验样管的测试与分析。证实该枪性能良好，动态聚集效果明显。     

漫谈汽车产品的包装

从汽车外形设计、车身色彩及内装饰三个方面讨论汽车内外包装的发展现状和有关走向，并指出这方面正有迅猛的发展势头，以上起包装界和汽车设计界的高度重视。