Yuan Baozong

An OOPR-based rose variety recognition system

This paper describes a rose analysis and recognition system and presents the main principles used to realize the recognition system. The major principles presented in this paper are the mathematical description methods for rose features such as shape, size and color of the flower, petal, leaf, etc, and the object-oriented pattern recognition (OOPR) approach which mathematically deals with how to comprehensively use all different rose features rationally in the recognition scheme. The recognition system is described and some of its experimental results are given which demonstrate the efficiency of our methods.

Multiple moving objects tracking for video surveillance systems

This paper is devoted to present an algorithm that is able to perform simultaneous moving objects tracking for video surveillance systems. The algorithm starts with the distinction between the moving objects versus background scene. The distinction is achieved based on background subtraction method. To be immune to anomalous components, background subtraction is integrated with two additional mechanisms: shadow detection and background frame adaptation. When the moving objects are identified and characterized by their features, the algorithm switches to tracking mode. The goals of tracking are to determine when a new object enters the filed of view, compute the correspondence matching between objects in previous frame and objects currently to be tracked, and estimate the spatial position of each object. The algorithm uses two similarity functions and dynamic template matching to achieve the aforementioned goals. The results are shown the flexibility of the proposed algorithm to cope with multiple simultaneously objects and occlusions.

Fourier transform based image shape analysis and its application to flower recognition

This paper describes a rose variety recognition project and proposes the modified Fourier descriptor. Based on the modified descriptor, a new measurement, angle measurement, is proposed for image shape analysis. We use it for rose flower shape analysis and the experimental results show that this measurement is quite efficient for image shape analysis.

An extended BAM neural network model

Proposes an extended bidirectional associative memory (BAM) neural network model which can do auto- and hetero-associative memory. The theoretical proof for this neural network models stability is given. Experiments show that this neural network model is much more powerful than the M-P model, discrete Hopfield neural network, continuous Hopfield neural network, discrete bidirectional associative memory neural network, continuous and adaptive bidirectional associative memory neural network, backpropagation neural network and optimal designed nonlinear continuous neural network. Experimental results also show that, when it does auto-associative memory, the power of this model is the same as the loop neural network model which can only do auto-associative memory.

Analysis and optimal design of continuous neural networks with applications to associative memory

The asymptotic stability of a continuous neural network is analyzed for associative memory. An optimal design method is proposed which ensures the highest associative memory speed and guarantees the storage of each desired memory with attractivity. The network asymptotic stability is analyzed by means of a new energy function, and four theorems are obtained. By comparing these theorems with existing ones, it can be shown that in some cases they are consistent, while in others they are not equivalent but complementary to each other. Further study results in two more generalized conclusions, of which the existing conclusions are special cases. The network optimal design method is proposed in terms of an optimal associative memory theorem. Two application examples are presented to demonstrate the defeffectiveness of the optimal design method, which can be used to design the network for many applications.

A NN image understanding system for maps and animals recognition

The paper presents the structure and design principle of a neural network (NN) image understanding system which is used to recognize and analyze maps and animals with the features of translation-, scale-, and rotation-invariance. The utilized network is nonlinear continuous neural network using its associative memory function. We designed this neural network system using an optimal design method. The feature parameters which are inputted into the system to carry out the recognition task are Zernike moments. Through extensive experimentation with translation, scale, rotation as well as distortion (such as cutting off some parts of the inputted image), we can see this system is a high robustness and fault-tolerance image understanding system.<<ETX>>

Loop neural network model for associative memory

Proposes a new associative memory neural net (NN) model called the loop neural network model, and the theoretical proof of this NNs stability is given. Experiments show that this NN model is much more powerful than the McCulloch-Pitts model, the discrete Hopfield NN, the continuous Hopfield NN, the discrete bidirectional associative memory NN, the continuous and adaptive bidirectional associative memory NN, the backpropagation NN, and the optimally designed nonlinear continuous NN.<<ETX>>

Moving shadows detection in video sequences

Video surveillance and traffic monitoring systems can be heavily improved using vision-based techniques that able to detect manage, and track objects in the field of view. However, problems arise due to shadows can affect the correct localization and detection of moving objects. This paper aims to present a method for detecting shadows that accompany moving objects. The proposed method is based on three sources of information. First, shadows are attached their respective objects. Second, a region covers by shadow in current frame is always darker than the same region in background frame. Finally, the ratio between current and background pixels are roughly constant under shadow regions. The proposed method can be exploited in a system for moving visual object detection to improve detection accuracy. The experimental results on real video sequences show the effectiveness of this method.

Seamless messaging in a multimedia network environment

This paper introduces the first-generation seamless messaging system of the National Research Council and describes its further development version, the multimedia seamless messaging system.

Handwritten character recognition by extended loop neural networks

Presents an extended loop neural network approach to handwritten character recognition. Experiments show that this method is very effective. The recognition rate by this method is higher than that by a backpropagation network.<<ETX>>