Eye Tracking in Image Sequences by Competitive Neural Networks

An automatic algorithm is presented for the eye tracking within face image sequences. It is based on the property of local Gabor filters to efficiently determine the location of eyes in face images. The proposed algorithm is implemented by a competitive neural network, that locates and tracks the eyes in a reliable manner as shown by experimental results.     

A Sensitivity Analysis of the Self Organizing Maps as an Adaptive One-pass Non-stationary Clustering Algorithm: the Case of Color Quantization of Image Sequences

In this paper we study the sensitivity of the Self Organizing Map to several parameters in the context of the one-pass adaptive computation of cluster representatives over non-stationary data. The paradigm of Non-stationary Clustering is represented by the problem of Color Quantization of image sequences.     

Expansive and Competitive Learning for Vector Quantization

In this paper, we develop a necessary and sufficient condition for a local minimum to be a global minimum to the vector quantization problem and present a competitive learning algorithm based on this condition which has two learning terms; the first term regulates the force of attraction between the synaptic weight vectors and the input patterns in order to reach a local minimum while the second term regulates the repulsion between the synaptic weight vectors and the input's gravity center to favor convergence to the global minimum This algorithm leads to optimal or near optimal solutions and it allows the network to escape from local minima during training. Experimental results in image compression demonstrate that it outperforms the simple competitive learning algorithm, giving better codebooks.     

New Results on Exponential Stability of Competitive Neural Networks with Multi‐Proportional Delays

In this paper, we are concerned with a class of competitive neural networks with multi‐proportional delays. By applying the Banach fixed point theorem and constructing suitable Lyapunov functions, we obtain new sufficient conditions for the global exponential stability to this class of neural networks, which are easily verifiable. Finally, two examples are given to illustrate the effectiveness of the obtained results.     

A Novel Self-Creating Neural Network for Learning Vector Quantization

This paper presents a novel self-creating neural network scheme which employs two resource counters to record network learning activity. The proposed scheme not only achieves the biologically plausible learning property, but it also harmonizes equi-error and equi-probable criteria. The training process is smooth and incremental: it not only avoids the stability-and-plasticity dilemma, but also overcomes the dead-node problem and the deficiency of local minimum. Comparison studies on learning vector quantization involving stationary and non-stationary, structured and non-structured inputs demonstrate that the proposed scheme outperforms other competitive networks in terms of quantization error, learning speed, and codeword search efficiency.     

模糊系统和神经网络的特征与比较

概述了模糊、神经网络 和人工智能技术之间的关系，尤其探讨了模糊系统和神经网络的特性；指出了模糊系统和神经网络的结合方式，分析了它们的特征。     

Backpropagation of an Image Similarity Metric for Autoassociative Neural Networks

Autoassociative Neural Networks (AANNs) are most commonly used for image data compression. The goal of an AANN for image data is to have the network output be ‘similar’ to the input. Most of the research in this area use backpropagation training with Mean-Squared Error (MSE) as the optimisation criteria. This paper presents an alternative error function called the Visual Difference Predictor (VDP) based on concepts from the human-visual system. Using the VDP as the error function provides a criteria to train an AANN more efficiently, and results in faster convergence of the weights, while producing an output image perceived to be very similar by a human observer. Received: 02 December 1998, Received in revised form: 28 June 1999, Accepted: 05 August 1999     

污水处理中BP神经网络与Elman神经网络的预测比较

以活性污泥污水处理过程为背景,介绍并比较了BP神经网络与Elman神经网络对于污水处理输出化学需氧量(COD)的预测.实验结果表明,Elman神经网络训练时间要比BP神经网络训练时间长,但是Elman神经网络预测的精确度要比BP神经网络预测的精确度高,Elman神经网络能够更好的预测污水处理的进程.     

The LBG-U Method for Vector Quantization – an Improvement over LBG Inspired from Neural Networks

A new vector quantization method (LBG-U) closely related to a particular class of neural network models (growing self-organizing networks) is presented. LBG-U consists mainly of repeated runs of the well-known LBG algorithm. Each time LBG converges, however, a novel measure of utility is assigned to each codebook vector. Thereafter, the vector with minimum utility is moved to a new location, LBG is run on the resulting modified codebook until convergence, another vector is moved, and so on. Since a strictly monotonous improvement of the LBG-generated codebooks is enforced, it can be proved that LBG-U terminates in a finite number of steps. Experiments with artificial data demonstrate significant improvements in terms of RMSE over LBG combined with only modestly higher computational costs.     

Neural Networks for Autonomous Path-Following with an Omnidirectional Image Sensor

This paper presents a path-following system implemented with two different types of neural networks, that enables an autonomous mobile robot to return along a previously learned path in a dynamic environment. The path-following is based on data provided by an omnidirectional conical visual system, derived from the COPIS sensor, but with different optical reflective properties. The system uses optical and software processing and a neural network to learn the path, described as a sequence of selected points. In the navigation phase it drives the robot along this learned path. Interesting results have been achieved using low cost equipment. Test and results are presented.     

一种基于粗糙集理论的神经网络图像分割方法

神经网络用于分割图像时需要大量的训练数据,由于数据量大,计算速度相当慢。不适合实时数据处理。基于此,将粗糙集理论与神经网络相结合,提出基于粗糙集的神经网络图像分割方法。利用粗糙集理论中的约简的计算方法,从图像属性中获取精简的规则,根据这些规则构造神经网络各层的神经元个数,并根据粗糙集理论中的属性重要性来修正神经网络的权值。实验结果表明,该方法抗噪能力强,提高了精度,在大大缩短网络训练时间的同时改善了分割效果。满足图像处理的实时性要求。     

Device-independent Color Correction for Multimedia Applications Using Neural Networks and Abductive Modeling Approaches

Although color has appeal for developers and consumers alike, color reproduction poses a major problem in many computer based applications including multimedia and desktop publishing. The problem arises because of the device-independence of color, and the way each device processes color. Matching the appearance of monitor and print images, and achieving satisfactory results is complex. Not only are there fundamental differences between computer screen (additive) and printers (subtractive), but subtractive color is in general more prone to errors due to dye inadequacies. In order to control the error in porting color, different techniques have been applied. In this paper, the utilization of artificial neural networks as well as abductive modeling approaches to color error reduction are introduced from an RGB (Red Green Blue) color model perspective. Analysis of the results and on-going research issues are discussed.     

Comparison between Lamarckian and Darwinian Evolution on a Model Using Neural Networks and Genetic Algorithms

In this paper, we study the relationship between learning and evolution in a simple abstract model, where neural networks capable of learning are evolved using genetic algorithms (GAs). Each individual tries to acquire a proper behavior under a given environment through its lifetime learning, and the best individuals are selected to reproduce offspring, which then conduct lifetime learning in the succeeding generation. The connective weights of individuals' neural networks undergo modification, i.e., certain characters will be acquired, through their lifetime learning. By setting various rates for the heritability of acquired characters, which control the strength of ‘Lamarckian’ strategy, we observe adaptational processes of populations over successive generations. By taking the degree of environmental changes into consideration, we show the following results. Under static environments, populations with higher rates of heritability adapt themselves more quickly toward the environments, and thus perform well. On the other hand, under nonstationary environments, populations with lower rates of heritability not only show more stable behavior against environmental changes, but also maintain greater adaptability with respect to such changing environments. Consequently, the population with zero heritability, i.e., the Darwinian population, attains the highest level of adaptation towards dynamic environments. Received February 1999 / Revised September 1999 / Accepted in revised form September 1999     

自组织竞争人工神经网络在颜色选择中的应用

颜色的识别一直是目前模式识别中的一个重要课题,介绍了自组织竞争神经网络结构和原理,接着利用其在分类分面的应用,推广到其在图像颜色选择中的应用,并在计算机上的实现,最后统述了该系统在工控方面的应用前景。     

基于神经网络和颜色特征的车牌字符分割方法

论文提出了一种基于神经网络和颜色特征的车牌字符分割方法。在颜色空间中利用树型判决结构,首先由亮度信息识别出车牌区域中的白色、黑色像素,然后利用网络对车牌区域中的蓝、红、黄色以及其他颜色进行识别。根据车牌的颜色特征,在判断出车牌的类型后,对车牌区域进行二值化处理。去除车牌边框和柳钉后,综合利用投影法和字符的连通性来分割车牌字符。实验结果表明,该方法是有效的。     

A Real-Time Multi-Stage Architecture for Pose Estimation of Zebrafish Head with Convolutional Neural Networks

In order to conduct optical neurophysiology experiments on a freely swimming zebrafish,it is essential to quantify the zebrafish head to determine exact lighting positions.To efficiently quantify a zebrafish head's behaviors with limited resources,we propose a real-time multi-stage architecture based on convolutional neural networks for pose estimation of the zebrafish head on CPUs.Each stage is implemented with a small neural network.Specifically,a light-weight object detector named Micro-YOLO is used to detect a coarse region of the zebrafish head in the first stage.In the second stage,a tiny bounding box refinement network is devised to produce a high-quality bounding box around the zebrafish head.Finally,a small pose estimation network named tiny-hourglass is designed to detect keypoints in the zebrafish head.The experimental results show that using Micro-YOLO combined with RegressNet to predict the zebrafish head region is not only more accurate but also much faster than Faster R-CNN which is the representative of two-stage detectors.Compared with DeepLabCut,a state-of-the-art method to estimate poses for user-defined body parts,our multi-stage architecture can achieve a higher accuracy,and runs 19x faster than it on CPUs.     

基于纹理特征与BP神经网络的一类图像检索

1 引言随着网络通信及多媒体技术的发展,特别是因特网的广泛应用,图像作为一种越来越重要的信息载体得到了广泛的应用。融合图像理解技术,直接针对静止图像或视频帧的图像特征进行处理,在高度信息化的今天,已成为内容图像库中图像信息组织和管理不可     

互补学习：一种面向图像应用和噪声标注的深度神经网络训练方法

近几年来,深度神经网络在图像识别、语音识别、自然语言处理等众多领域取得了突破性的进展.互联网以及移动设备的快速发展极大地推进了图像应用的普及,也为深度神经网络的训练积累了大量数据.其中,大规模人工标注的数据是成功训练深度神经网络的关键.但随着数据规模的快速增长,人工标注图像的成本也越来越高,同时不可避免地产生标注错误,从而影响神经网络的训练.为此,提出了一种称为互补学习的方法,面向图像应用中深度神经网络的训练,将简单样本挖掘和迁移学习的思想相结合,利用少量人工标注的干净数据和大量带有噪声标注的数据,同时训练一主一辅2个深度神经网络模型,在训练过程中采用互补的策略分别选择部分样本进行学习,同时将辅模型的知识迁移给主模型,从而减少噪声标注对训练的影响.实验表明：提出的方法能有效地利用带有噪声标注的数据训练深度神经网络,并对比其他方法有一定的优越性,有较强的应用价值.     

生物神经网络仿真的方法和工具

大脑作为人体的关键器官,其复杂程度非常高,被了解的也最少。为了研究与大脑相关的疾病和人类智能的机理,出现了新的学科——神经网络的仿真。神经网络仿真是和传统的神经网络算法完全不同的一个领域,属于信息学、生物学、计算机科学、仿真等多个领域相互交叉的学科。本文介绍了神经网络仿真的基本原理以及国外出现的开源工具和支撑项目,并对存在的仿真建模工具进行了全面的比较,以便于用户根据自身建模的需要选择合适的工具。文章对生物神经网络仿真的计算量进行了评估,并结合我国最新研制的天河1-A超级并行计算机讨论了并行生物神经网络仿真的前景。     

CNN和三维Gabor滤波器的高光谱图像分类

卷积神经网络(CNN)具有强大的特征提取能力,能够有效地提高高光谱图像的分类精度.然而CNN模型训练需要大量的训练样本参与,以防止过拟合,Gabor滤波器以非监督的方式提取图像的边缘和纹理等空间信息,能够减轻CNN模型对训练样本的依赖度及特征提取的压力.为了充分利用CNN和Gabor滤波器的优势,提出了一种双通道CNN和三维Gabor滤波器相结合的高光谱图像分类方法Gabor-DC-CNN.首先利用二维卷积神经网络(2D-CNN)模型处理原始高光谱图像数据,提取图像的深层空间特征;同时利用一维卷积神经网络(1D-CNN)模型处理三维Gabor特征数据,进一步提取图像的深层光谱-纹理特征.连接2个CNN模型的全连接层实现特征融合,并将融合特征输入到分类层中完成分类.实验结果表明,该方法能够有效地提高分类精度,在Indian Pines,Pavia University和Kennedy Space Center 3组数据上分别达到98.95%,99.56%和99.67%.