We propose a fuzzy scheme strategy for the generation of the diffuser dot patterns in the light guide of an edge-lit backlight. The fuzzy scheme strategy is based on fuzzy logic and rules, which are closely related to the physical luminance properties of the light guide. During the process of generating diffuser dot patterns, two inputs are the dot radius and the distance from dots to a light source, and one output is the luminance of the light guide panel. This strategy converts the linguistic strategy based on expert knowledge the optimal dot-generation strategy. Furthermore, this study includes the discussion of fuzzification and defuzzification strategies, the derivation of fuzzy logic rules, and the analysis of fuzzy reasoning mechanisms. Experiment results reveal that the proposed strategy can achieve an even luminance condition by establishing dot patterns. Compared to conventional methods, the fuzzy scheme strategy has two advantages. It effectively integrates the dot generation scheme into the subsequent optical design phase to make dot patterns more efficient and easy to control. Moreover, optimized dot patterns realize sufficient luminance uniformity.
To improve dynamic measurement performance and resolution, an optimum design on two-dimensional (2D) micro-angle
sensor based on optical internal-reflection method via critical-angle refractive index measurement is presented in
the paper. The noise signals were filtered effectively by modulating laser-driven and demodulating in signal proceeding.
The system's accuracy and response speed are improved further by using 16-bit high-precision AD converter and
MSP430 CPU which present with a high-speed performance during signals processes such as fitting angle-voltage curve
through specific arithmetic, full range and zero point calibration, filter, scaling transformation etc. The experiment
results indicated that, dynamic signal measurement range can be up to ±600arcsec, the measurement resolution can be
better than 0.1arcsec, and the repeatability could be better than ±0.5arcsec.
Image segmentation is a fundamental image processing technology. There are many kinds of image segmentation methods, but most of them are problem oriented. In this paper, image segmentation method based on lateral inhibition network is presented. Lateral inhibition network is a biological vision model. When an image is filtered by a lateral inhibition network, its low frequency components are inhibited while the high frequency components are enhanced. The lateral inhibited image is much easier to be segmented because of its increased inter-class difference and decreased intra-class difference. The parameters of the lateral inhibition network model determine the inhibited image, thus affect the image segmentation result greatly. But there are no assured rules to determine the parameters. We propose an evolutionary strategy (ES) based method to search the optimal weighting parameters of the lateral inhibition network model. The objective function of ES is a multiattribute fitness function that combines multiple criteria of clustering and entropy information. The original image is filtered using the optimal lateral inhibition network and then the inhibited image is segmented by an optimized threshold. Using test images of various characteristics, the proposed method is evaluated by four objective image segmentation evaluation indexes. The experimental results show its validity and universality.
A multiple neural network classifier fusion system design method using immune genetic algorithm (IGA) is proposed. The IGA is modeled after the mechanics of human immunity. By using vaccination and immune selection in the evolution procedures, the IGA outperforms the traditional genetic algorithms in restraining the degenerate phenomenon and increasing the converging speed. The fusion system consists of N neural network classifiers that work independently and in parallel to classify a given input pattern. The classifiers' outputs are aggregated by a fusion scheme to decide the collective classification results. The goal of the system design is to obtain a fusion system with both good generalization and efficiency in space and time. Two kinds of measures, the accuracy of classification and the size of the neural networks, are used by IGA to evaluate the fusion system. The vaccines are abstracted by a self-adaptive scheme during the evolutionary process. A numerical experiment on the 'alternate labels' problem is implemented and the comparisons of IGA with traditional genetic algorithm are presented.