Shape indexing using self-organizing maps

In this paper, we propose a novel approach to generate the topology-preserving mapping of structural shapes using self-organizing maps (SOMs). The structural information of the geometrical shapes is captured by relational attribute vectors. These vectors are quantised using an SOM. Using this SOM, a histogram is generated for every shape. These histograms are treated as inputs to train another SOM which yields a topology-preserving mapping of the geometric shapes. By appropriately choosing the relational vectors, it is possible to generate a mapping that is invariant to some chosen transformations, such as rotation, translation, scale, affine, or perspective transformations. Experimental results using trademark objects are presented to demonstrate the performance of the proposed methodology.     

一种基于小波变换的马尔可夫随机场的视频对象分割

马尔可夫随机场（Markov Random Field,MRF）理论已经被广泛地应用于视频图像的分割。提出一种基于小波变换的马尔可夫随机场模型的视频对象分割算法。该算法利用小波变换将图像序列分解到小波域,并在此基础上建立马尔可夫随机场模型,构造相应的能量函数。通过迭代求解能量函数的最优解,得出标记场,提取出运动对象。仿真结果表明,该算法能够有效地抑制噪声,提高构成对象边界像素的数量,快速有效地提取出视频对象。     

Bankruptcy analysis with self-organizing maps in learning metrics

We introduce a method for deriving a metric, locally based on the Fisher information matrix, into the data space. A self-organizing map (SOM) is computed in the new metric to explore financial statements of enterprises. The metric measures local distances in terms of changes in the distribution of an auxiliary random variable that reflects what is important in the data. In this paper the variable indicates bankruptcy within the next few years. The conditional density of the auxiliary variable is first estimated, and the change in the estimate resulting from local displacements in the primary data space is measured using the Fisher information matrix. When a self-organizing map is computed in the new metric it still visualizes the data space in a topology-preserving fashion, but represents the (local) directions in which the probability of bankruptcy changes the most.     

Environment classification using Kohonen self-organizing maps

Abstract: This paper describes a new method for classifying three-dimensional environments in real time using Kohonen self-organizing maps (SOMs). The method has been developed to enable autonomous underwater vehicles (AUVs) to navigate without human intervention in previously unexplored subsea environments, but can be generalized to unmanned aircraft equipped with appropriate sensors flying over unchartered terrains, or spacecraft exploring remote planets, subject to appropriate pre-mission training. The method involves a fuzzy comparison between a SOM created in real time using accumulated sensor data and a class atlas of SOMs derived from previously trained and manually classified environments. This enables mission- and environment-appropriate AUV navigation strategies to be selected in real time. Simulation results using real-world, three-dimensional environment data acquired from digital elevation maps are presented, which demonstrate the potential of the method.     

Combining stationary wavelet transform and self-organizing maps for brain MR image segmentation

This study presents an image segmentation system that automatically segments and labels T1-weighted brain magnetic resonance (MR) images. The method is based on a combination of unsupervised learning algorithm of the self-organizing maps (SOM) and supervised learning vector quantization (LVQ) methods. Stationary wavelet transform (SWT) is applied to the images to obtain multiresolution information for distinguishing different tissues. Statistical information of the different tissues is extracted by applying spatial filtering to the coefficients of SWT. A multidimensional feature vector is formed by combining SWT coefficients and their statistical features. This feature vector is used as input to the SOM. SOM is used to segment images in a competitive unsupervised approach and an LVQ system is used for fine-tuning. Results are evaluated using Tanimoto similarity index and are compared with manually segmented images. Quantitative comparisons of our system with the other methods on real brain MR images using Tanimoto similarity index demonstrate that our system shows better segmentation performance for the gray matter while it gives average results for white matter.     

信息熵约束下的视频目标分割

大部分基于图论的视频分割方法往往先通过分析运动和外观信息获得先验显著性区域,然后用最小化能量模型来进一步分割,这些方法常常忽略对外观信息精细化分析,建立的目标模型对复杂场景的鲁棒性不佳。根据信息熵能够度量样本纯度,信息熵最小化和能量模型最小化具有一致的目标,提出一种信息熵约束下的视频目标分割方法。首先在经典光流法基础上结合点在多边形内部原理获得第一阶段的分割结果;然后以超像素为基本分割单元,获得均匀的运动和表现;最后在能量函数中引入信息熵约束项,构建前景背景像素标记的优化问题,通过最小化能量函数得到更精确的分割结果。在公开数据集上的实验结果表明目标模型中引入信息熵约束项能够有效提高视频目标分割的鲁棒性。     

Co-adaptation of self-organizing maps by evolution and learning

This paper proposes two co-adaptation schemes of self-organizing maps that incorporate the Kohonen's learning into the GA evolution in an attempt to find an optimal vector quantization codebook of images. The Kohonen's learning rule used for vector quantization of images is sensitive to the choice of its initial parameters and the resultant codebook does not guarantee a minimum distortion. To tackle these problems, we co-adapt the codebooks by evolution and learning in a way that the evolution performs the global search and makes inter-codebook adjustments by altering the codebook structures while the learning performs the local search and makes intra-codebook adjustments by making each codebook's distortion small. Two kinds of co-adaptation schemes such as Lamarckian and Baldwin co-adaptation are considered in our work. Simulation results show that the evolution guided by a local learning provides the fast convergence, the co-adapted codebook produces better reconstruction image quality than the non-learned equivalent, and Lamarckian co-adaptation turns out more appropriate for the VQ problem.     

Using self-organizing maps to learn geometric hash functions formodel-based object recognition

A major problem associated with geometric hashing and methods which have emerged from it is the nonuniform distribution of invariants over the hash space. In this paper, a new approach is proposed based on an elastic hash table. We proceed by distributing the hash bins over the invariants. The key idea is to associate the hash bins with the output nodes of a self-organizing feature map (SOFM) neural network which is trained using the invariants as training examples. In this way, the location of a hash bin in the space of invariants is determined by the weight vector of the node associated with the hash bin. The advantage of the proposed approach is that it is a process that adapts to the invariants through learning. Hence, it makes absolutely no assumptions about the statistical characteristics of the invariants and the geometric hash function is actually computed through learning. Furthermore, SOFM's topology preserving property ensures that the computed geometric hash function should be well behaved.     

Dynamic muscle fatigue detection using self-organizing maps

Wavelets are used for the processing of signals that are non-stationary and time varying. The electromyogram (EMG) contains transient signals related to muscle activity. Wavelet coefficients are proposed as features for identifying muscle fatigue. By observing the approximation coefficients it is shown that their amplitude follows closely the muscle fatigue development. The proposed method for detecting fatigue is automated by using neural networks. The self-organizing map (SOM) has been used to visualize the variation of the approximation wavelet coefficients and aid the detection of muscle fatigue. The results show that a 2D SOM separates EMG signatures from fresh and fatigued muscles, thus providing a visualization of the onset of fatigue over time. The map is able to detect if muscles have recovered temporarily. The system is adaptable to different subjects and conditions since the techniques used are not subject or workload regime specific.     

基于变化检测的视频对象分割方案

由于运行时平均法建立的背景随更新系数的不同而波动,提出了一种新的更新系数选择方法,并利用了基于分块代替基于像素的帧差处理方法来减少差分技术对噪声的敏感性。在研究背景差分容易把背景中变化大的部分判决为运动物体,而帧间差分容易把运动物体中缓慢变化的部分判为背景的基础上,提出了一种新的帧间差分、背景差分和边缘检测相结合的视频对象分割方案。实验结果表明,新方案实时性高,分割得到的视频对象相对于单独使用帧间差分或背景差分的效果有明显的改进。     

特征一致性约束的视频目标分割

目的 视频目标分割是计算机视觉领域的一个重要方向,已有的一些方法在面对目标形状不规则、帧间运动存在干扰信息和运动速度过快等情况时,显得无能为力。针对以上不足,提出基于特征一致性的分割算法。方法 本文分割算法框架是基于马尔可夫随机场（Markov random field,MRF）的图论方法。使用高斯混合模型,对预先给定的已标记区域分别进行颜色特征的建模,获得分割的数据项。结合颜色、光流方向等多种特征,建立时空平滑项。在此基础之上,加入基于特征一致性的能量约束项,以增强分割结果的外观一致性。这项添加的能量本身属于一种高阶能量约束,会显著增加能量优化的计算复杂度。为此,添加辅助结点,以解决能量的优化问题,从而提高算法速度。结果 在DAVIS_2016（densely annotated video segmentation）数据集上对该算法进行评估与测试,并与最新的基于图论的方法进行对比分析,对比算法主要有HVS（efficient hierarchical graph-based video segmentation）、NLC（video segmentation by non-local consensus voting）、BVS（bilateral space video segmentation）和OFL（video segmentation via object flow）。本文算法的分割结果精度排在第2,比OFL算法略低1.6%;在算法的运行速度方面,本文算法领先于对比方法,尤其是OFL算法的近6倍。结论 所提出的分割算法在MRF框架的基础之上融合了特征一致性的约束,在不增加额外计算复杂度的前提下,提高了分割精度,提升了算法运行速度。     

Shades of green: A psychographic segmentation of the green consumer in Kuwait using self-organizing maps

This study uses self-organizing maps (SOM) to examine the effect of various psychographic and cognitive factors on green consumption in Kuwait. SOM is a machine learning method that can be used to explore patterns in large and complex datasets for linear and non-linear patterns. The results show that major variables affecting green consumption are related to altruistic values, environmental concern, environmental knowledge, skepticism towards environmental claims, attitudes toward green consumption, and intention to buy green products. The study also shows that SOM models are capable of improving clustering quality while extracting valuable information from multidimensional data.     

Integration of self-organizing feature maps neural network and genetic K-means algorithm for market segmentation

This study is dedicated to proposing a novel two-stage method, which first uses Self-Organizing Feature Maps (SOM) neural network to determine the number of clusters and the starting point, and then uses genetic K-means algorithm to find the final solution. The results of simulated data via a Monte Carlo study show that the proposed method outperforms two other methods, K-means and SOM followed by K-means (Kuo, Ho & Hu, 2002a), based on both within-cluster variations (SSW) and the number of misclassification. In order to further demonstrate the proposed approach's capability, a real-world problem of the fright transport industry market segmentation is employed. A questionnaire is designed and surveyed, after which factor analysis extracts the factors from the questionnaire items as the basis of market segmentation. Then the proposed method is used to cluster the customers. The results also indicate that the proposed method is better than the other two methods     

A filter based neuron model for adaptive incremental learning of self-organizing maps

In this work a learning algorithm is proposed for the formation of topology preserving maps. In the proposed algorithm the weights are updated incrementally using a higher-order difference equation, which implements a low-pass digital filter. It is shown that by suitably choosing the filter the learning process can adaptively follow a specific dynamic. Numerical results, for time-varying and static distributions, show the potential of the proposed method for unsupervised learning.     

Asynchronous self-organizing maps

A recently defined energy function which leads to a self-organizing map is used as a foundation for an asynchronous neural-network algorithm. We generalize the existing stochastic gradient approach to an asynchronous parallel stochastic gradient method for generating a topological map on a distributed computer system (MIMD). A convergence proof is presented and simulation results on a set of problems are included. A practical problem using the energy function approach is that a summation over the entire network is required during the computation of updates. Using simulations we demonstrate effective algorithms that use efficient sampling for the approximation of these sums.     

Identification of trends from patents using self-organizing maps

Patent users such as governments, inventors, and manufacturing organizations strive to identify the directions in which new technology is advancing, and their goal is to outline the boundaries of existing knowledge. The paper analyzes patent knowledge to identify research trends. A model based on knowledge extraction from patents and self-organizing maps for knowledge representation is presented. The model was tested on patents from the United States Patent and Trademark Office. The experiments show that the method provides both an overview of the directions of the trends and a drill-down perspective of current trends.     

基于双重金字塔网络的视频目标分割方法

针对复杂视频场景中难以分割特定目标的问题，提出一种基于双重金字塔网络（DPN）的视频目标分割方法。首先，通过调制网络的单向传递让分割模型适应特定目标的外观。具体而言，从给定目标的视觉和空间信息中学习一种调制器，并通过调制器调节分割网络的中间层以适应特定目标的外观变化。然后，通过基于不同区域的上下文聚合的方法，在分割网络的最后一层中聚合全局上下文信息。最后，通过横向连接的自左而右结构，在所有尺度中构建高阶语义特征图。所提出的视频目标分割方法是一个可以端到端训练的分割网络。大量实验结果表明，所提方法在DAVIS2016数据集上的性能与较先进的使用在线微调的方法相比，可达到相竞争的结果，且在DAVIS2017数据集上性能较优。     

特征注意金字塔调制网络的视频目标分割

目的 视频目标分割是在给定第1帧标注对象掩模条件下,实现对整个视频序列中感兴趣目标的分割。但是由于分割对象尺度的多样性,现有的视频目标分割算法缺乏有效的策略来融合不同尺度的特征信息。因此,本文提出一种特征注意金字塔调制网络模块用于视频目标分割。方法 首先利用视觉调制器网络和空间调制器网络学习分割对象的视觉和空间信息,并以此为先验引导分割模型适应特定对象的外观。然后通过特征注意金字塔模块挖掘全局上下文信息,解决分割对象多尺度的问题。结果 实验表明,在DAVIS 2016数据集上,本文方法在不使用在线微调的情况下,与使用在线微调的最先进方法相比,表现出更具竞争力的结果,J-mean指标达到了78.7%。在使用在线微调后,本文方法的性能在DAVIS 2017数据集上实现了最好的结果,J-mean指标达到了68.8%。结论 特征注意金字塔调制网络的视频目标分割算法在对感兴趣对象分割的同时,针对不同尺度的对象掩模能有效结合上下文信息,减少细节信息的丢失,实现高质量视频对象分割。