The paper is the study of 2D Gabor wavelet and its application in grey image target recognition and tracking. The new
optimization algorithms and technologies in the system realization are studied and discussed in theory and practice.
Optimization of Gabor wavelet's parameters of translation, orientation, and scale is used to make it approximates a local
image contour region. The method of Sobel edge detection is used to get the initial position and orientation value of
optimization in order to improve the convergence speed. In the wavelet characteristic space, we adopt PSO (particle
swarm optimization) algorithm to identify points on the security border of the system, it can ensure reliable convergence
of the target, which can improve convergence speed; the time of feature extraction is shorter. By test in low contrast
image, the feasibility and effectiveness of the algorithm are demonstrated by VC++ simulation platform in experiments.
Adopting improve Gabor wavelet method in target tracking and making up its frame of tracking, which realize moving
target tracking used algorithm, and realize steady target tracking in circumrotate affine distortion.
This paper presents effective multi-objective genetic algorithms (MOGA) method, whose character lies in that evolutionary population is preference ranked based on concordance model, which was applied to a multi-objective optimization of aircraft, measure of fitness degree was discussed as an emphasis. The solutions were analyzed and compares with original BP neural networks algorithm, which is better than the network trained only on alternating momentum, which can performed well neural networks and have shown the superiority to the network structure. Based the pareto optimal approaches are equipped with a fast identifying ability in capturing the learned objects, and in the meantime it can adapt the new objects. The experiments with variety of image show that the method proposed is efficient and useful, the result demonstrates that convergence speed is faster than traditional algorithm; target was recognized by this algorithm and can increase recognition precision.
This paper presents effective multi-objective genetic algorithms (MOGA) method, whose character lies in that evolutionary population is preference ranked based on concordance model, which was applied to a multi-objective optimization of aircraft, measure of fitness degree was discussed as an emphasis. The solutions were analyzed and compares with original BP neural networks algorithm, which is better than the network trained only on alternating momentum, which can performed well neural networks and have shown the superiority to the network structure. Based the pareto optimal approaches are equipped with a fast identifying ability in capturing the learned objects, and in the meantime it can adapt the new objects. The experiments with variety of image show that the method proposed is efficient and useful, the result demonstrates that convergence speed is faster than traditional algorithm; target was recognized by this algorithm and can increase recognition precision.
The Paper is the study of Gabor wavelet neural network algorithm and its application in gray image target recognition. The mostly thought t are real time recognizing gray image target with Gabor wavelet neural networks algorithm. The main thoughts are through combing the forward neural networks (BP net) with Gabor wavelet based on they were applied in target feature extraction and recognition. A model of Gabor wavelet neural network is constructed with automatic target recognition, the good impact is gained when it is applied target recognition. The principle of Gabor filter is expounded. The multi-channel Gabor filter is designed based on theory and practicality, the neural network recognizing algorithm based on multi-channel Gabor filter feature is presented. Training algorithm of Gabor wavelet neural networks model was given out. Principally analyzed Gabor wavelet neural networks from theory, in the mean time training algorithm of Gabor wavelet network suited to target recognition was designed by BP algorithm. Theory and simulate experiment indicated the astringency and robustness of this algorithm excelled BP net. Target was recognized by this algorithm not only increased recognition precision but also overcame the bug of BP algorithm get in minimum
Based on signal direction laser-scanned measuring technology, a double diameters laser-scanned measuring system is presented. The system adopts laser-scanned measuring technology combining with the special spectroscopic optical systems to form double directions laser-scanning beams, and to simultaneously realize high speed and accuracy non-contact automatic measurement of the diameters of two perpendicular directions at one section of measured workpiece. In this paper, the mathematical model of the measuring system is established. The working principle and overall structure of the system are introduced. The semiconductor laser beam transferred optical system, the scanning emitting and receiving optical systems; the optoelectronic transformation electronic system and microcomputer real-time control and data processing system are discussed in detail. The possibility of the system has been verified by experiments and errors analysis.
Based on the principle of laser triangulation and the technology of modern photoelectric sensor, a laser scanning optical triangulation measuring system which is used to measure 3-D curved surface profile is presented, the system uses a semiconductor laser probe and combines with 2-D grating displacement measuring systems and servo-control systems to realize scanning many points for the measured curved surface. Through the Fourier transform profile detection algorithm with the frequency field low-pass filter performing, computer finishes the real time data processing, the profile of 3-D curved surface is given with high accuracy and high speed. In this paper, the mathematical model of the measuring system is introduced and the jump-error processing method of the objects with large gradient change is discussed in detail. The measuring result shows that the 3-D figure is simple in use, convenient in parameter adjustment, especially, is suitable to measure the objects surface with large gradient and low reflecting ratio.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.