Genetic algorithm and self organizing map based fuzzy hybrid intelligent method for color image segmentation

The grouping of pixels based on some similarity criteria is called image segmentation. In this paper the problem of color image segmentation is considered as a clustering problem and a fixed length genetic algorithm (GA) is used to handle it. The effectiveness of GA depends on the objective function (fitness function) and the initialization of the population. A new objective function is proposed to evaluate the quality of the segmentation and the fitness of a chromosome. In fixed length genetic algorithm the chromosomes have same length, which is normally set by the user. Here, a self organizing map (SOM) is used to determine the number of segments in order to set the length of a chromosome automatically. An opposition based strategy is adopted for the initialization of the population in order to diversify the search process. In some cases the proposed method makes the small regions of an image as separate segments, which leads to noisy segmentation. A simple ad hoc mechanism is devised to refine the noisy segmentation. The qualitative and quantitative results show that the proposed method performs better than the state-of-the-art methods.     

融入局部几何特征的流形谱聚类图像分割

为了改善谱聚类图像分割的精准性和时效性,文中提出融入局部几何特征的流形谱聚类图像分割算法.首先,考虑图像数据的流形结构,在数据点的K近邻域内执行局部PCA,得到数据间本征维数的关系.然后,引入流形学习中的局部线性重构技术,通过混合线性分析器得到数据间局部切空间的相似性,结合二者构造含有局部几何特征的相似性矩阵.再利用Nystr m技术逼近待分割图像的特征向量,对构造的k个主特征向量执行谱聚类.最后,在Berkeley数据集上的对比实验验证文中算法的准确性和时效性优势.     

Core dimensions of food-related lifestyle: A new instrument for measuring food involvement,innovativeness and responsibility

Segmentation is crucial for targeting product development initiatives and marketing communication nationally as well as internationally. In this paper we use the Food Related Lifestyle instrument that has been applied in the food arena for many years as a ‘stepping stone’ to develop a contemporary, targeted and smaller version of the Food Related Lifestyle instrument, still following the original theoretical framework. In particular we focus on three dimensions that have proven to be of core value in segmentation: food involvement; food innovativeness; and, food responsibility. Based on data collection in six countries (DK, AU, HU, UK, USA and NZ) across two rounds from 2017 to 2019 (total N = 3396), we propose a new core instrument consisting of 15 items that have been tested for cross-cultural validity. Next, we used these three dimensions for segmentation across the six countries by applying multi-level latent class analysis. A solution leading to five different segments could be identified; the foodies, the moderates, the adventurous, the uninvolved and the conservatives. The segments were profiled by means of Schwartz’s ten value domains and measures of self-reported food-related behaviour to check for nomonological validity. We conclude that the 15 items were cross-culturally valid, could be used for segmentation across six countries, and that segment profiling by means of Schwartz values and behavioural items were in line with the theoretical background.     

Customers segmentation in eco-friendly hotels using multi-criteria and machine learning techniques

This study aims to investigate the travellers' choice behaviour towards green hotels through existing online travel reviews on TripAdvisor. Accordingly, a method combining segmentation and the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) techniques was developed to segment travellers based on their provided reviews and to prioritize green hotel attributes based on their level of importance in each segment. The data were taken from travellers' online reviews of Malaysian eco-friendly hotels on TripAdvisor. The results showed that the sleep quality was one of the most imporant factors for eco-hotel selection in the majority of segments. The developed method in this study was able to analyse travellers’ reviews and ratings on eco-friendly hotels to identify the future choice behaviour and aid travellers in their decision-making process. The study provides new insights for hotel managers and green policy makers on developing environmental-friendly practices.     

Unsupervised regions based segmentation using object discovery

We present a new unsupervised algorithm to discovery and segment out common objects from multiple images. Compared with previous cosegmentation methods, our algorithm performs well even when the appearance variations in the foregrounds are more substantial than those in some areas of the backgrounds. Our algorithm mainly includes two parts: the foreground object discovery scheme and the iterative region allocation algorithm. Two terms, a region-saliency prior and a region-repeatness measure, are introduced in the foreground object discovery scheme to detect the foregrounds without any supervisory information. The iterative region allocation algorithm searches the optimal solution for the final segmentation with the constraints from a maximal spanning tree, and an effective color-based model is utilized during this process. The comparative experimental results show that the proposed algorithm matches or outperforms several previous methods on several standard datasets.     

A Novel Ni/YSZ Anode Image Segmentation Method for Solid Oxide Fuel Cell Electrodes Microstructure

For the three‐phase identification of solid oxide cuel cell (SOFC) electrode, this paper presents a novel segmentation method based on gaussian mixture model (GMM) for YSZ/Ni anode optical microscopy (OM) images. A coarseness‐entropy adaptive factor is defined to incorporate the spatial information based on markov random field (MRF) into GMM. Furthermore, the proposed method can obtain the trade‐off between robustness to noise and effectiveness of preserving the details. Experimental results show that the proposed method outperforms the compared method on three‐phase microstructure identification. It can provide reliable foundation for the quantification of SOFC microstructure parameters.     

Using modified nodal analysis in cavity-mode resonances printed circuit board power bus structures with the segmentation method

In this paper, we used the modified nodal analysis (MNA) method to obtain the cavity-mode equation for the segmentation method. In the experiment, the calculation result of MNA is more accurate than traditional double summation with discrete capacitors. The proposed approaches decrease computation and easily add discrete capacitors. The MNA and segmentation methods can be combined to conveniently calculate an irregularly shaped cavity by using computers. This approach can reduce the time required for deriving the impedance equation. The result can be used to build a mathematical model of the MNA method, which can suppress cavity-mode resonances within the power bus by using discrete capacitors. We used electromagnetic simulation software to verify these models.     

基于Kohonen神经网络算法的医学图像分割

长期以来,在医学图像处理方面,图像分割一直是该项工作中的重点,同时也是其中的难点。所谓的图像分割实质上就是遵照相关的原则对图像进行分割,使其被分为几个部分的过程。它是以图像测量、配准、融合和三维重建作为基础,所以在临床医学研究中起着举足轻重的作用。文中研究的Kohonen聚类神经网络算法是以VC++为基础,并在此基础上进行了一定的优化,为图像分割的具体应用提供基础条件,提高效果,这对医生临床诊断具有十分重要的意义。     

基于DenseNet的复杂交通场景语义分割方法

针对交通场景语义分割方法存在参数量较大、计算效率较低、精度不足等问题,文中提出基于全卷积化DenseNet的多尺度端到端语义分割模型.首先,构建一种含混合空洞卷积的密集连接模块,同时沿通道维度级联各模块,用于提取图像特征.然后,采集多尺度视觉信息并以此作为监督信号回传至原通道中.最后,通过双线性插值法获得预测输出.在CityScapes数据集上的测试实验表明,文中方法对复杂交通场景的解析能力较强,预测精度和分割效率较高.