Spectral recognition using a modified Eckhorn neural network model

Studies of the visual cortex of the cat highlight the role of temporal processing using synchronous oscillations for object identification. In this paper, the original neural network model of Eckhorn has been modified according to the proposal of Johnson and others and used for spectral recognition. The method developed turns out to be a much simpler, faster and elegant way of spectral recognition than reported elsewhere.     

Deformation invariant visual object recognition: Experiments with a self-organising neural architecture

A self-organising neural network architecture for grey-scale visual object rcognition is presented. The network is composed of three processing layers with an architecture designed to give deformation tolerance. The processing layers involve feature extraction, sub-pattern detection and classification. Training is generally performed on-line in an unsupervised manner, classes being created when objects are presented that cannot be classified. The results given show the effect of the two discrimination parameters when the network is applied to two very different sets of images, namely hand written numerals and hand gestures images. The sensitivity of the network to the parameters that govern the size of detectable patterns and the areas over which they are detected is also tested. The robustness of the network to the order of image presentation is also demonstrated. The results show that parameter choice is not critical and heuristically chosen parameters provide near optimum performance.     

Analysis and application of a self-organising image recognition neural network

This paper investigates the effect of various feature extraction methods on the recognition ability of a self-organising neural network called Paradise when applied to the problems of the classification of face images and hand written character recognition. The feature extraction methods investigated are, oriented Gaussian filters, Gabor filters and oriented Laplacian of Gaussian (LG) filters. The recognition results for the two applications are shown to compare favourably with other techniques designed specifically for the two tasks.     

LBP和HOG的分层特征融合的人脸识别

针对LBP描述子提取的纹理特征有限且不能有效地描述图像边缘和方向信息的问题,提出了LBP和HOG的分层特征融合的方法.首先利用LBP算子提取图像的分层纹理谱特征,然后利用HOG算子提取原始图像的边缘特征和基于分层LBP特征的分层HOG特征,最后将分层LBP特征分别与2种HOG边缘特征融合,得到2种不同的多层融合特征.通过在ORL,Yale和GT人脸库上进行实验,比较了15种算法的识别性能,结果证明了文中方法的有效性;相对于传统的经典降维算法、单一的LBP特征提取算法和HOG特征提取算法,该方法的识别率有很大的提高,分别达到99%,99.5%和99.14%.     

Combining monoSLAM with object recognition for scene augmentation using a wearable camera

In wearable visual computing, maintaining a time-evolving representation of the 3D environment along with the pose of the camera provides the geometrical foundation on which person-centred processing can be built. In this paper, an established method for the recognition of feature clusters is used on live imagery to identify and locate planar objects around the wearer. Objects’ locations are incorporated as additional 3D measurements into a monocular simultaneous localization and mapping process, which routinely uses 2D image measurements to acquire and maintain a map of the surroundings, irrespective of whether objects are present or not. Augmenting the 3D maps with automatically recognized objects enables useful annotations of the surroundings to be presented to the wearer. After demonstrating the geometrical integrity of the method, experiments show its use in two augmented reality applications.     

Usability issues in the design of an intuitive interface for planning and simulating maintenance interventions using a virtual environment

This paper presents some of the results obtained in the VRIMOR project (virtual reality for inspection, maintenance, operation and repair of nuclear power plants). The general aim was to integrate environmental scanning technologies with human modelling and radiological dose estimation tools, and to deliver an intuitive and cost-effective system for use by operators involved with interventions in radiologically controlled areas. The usability of the resulting products was one of the main success criteria. This paper describes the general approach and design mechanisms used in the HeSPI (HeSPI stands for the Spanish for Herramienta para la Simulación y Planificación de Intervenciones, or tool for the simulation and planning of interventions) tool that has been developed by one of the teams. The tool provides the designer of an intervention with a humanoid 3D model, or mannequin, that can be loaded into the desired environment and will be used by the designer as if he was manipulating a puppet, making it move around the environment and perform different kinds of actions, adopting varied postures, interacting with the objects in the environment and manipulating tools and equipment. A combination of a graphical user interface (GUI) and a voice recognition system, together with the selected design mechanisms, has proven to offer good enough interaction possibilities for this kind of desktop virtual environment.     

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