Zong Mu Yeh

Contrast enhancement by automatic and parameter-free piecewise linear transformation for color images

Conventional contrast enhancement methods have four shortcomings. First, most of them need transformation functions and parameters which are specified manually. Second, most of them are application-oriented methods. Third, most of them are performed on gray level images. Fourth, the histogram equalization (HE) based enhancement methods use non-linear transform function. Thus, this paper proposes an automatic and parameter-free contrast enhancement algorithm for color images. This method includes following steps: First, RGB color space is transformed to HSV color space. Second, image content analysis is used to analyze the image illumination distribution. Third, the original image is enhanced by piecewise linear based enhancement method. Finally, the enhancement image is transformed back to RGB color space. This novel enhancement is automatic and parameter-free. Our experiments included various color images with low and high contrast. Experiment results show that the performance of the proposed method is better than histogram equalization (HE) and its six variations in non-over enhancement and natural clearly revealed. Moreover, the proposed algorithm can be run on an embedded environment (such as mobile device, digital camera, or other consumer products) and processed in real-time system due to its simplicity and efficiently.

A performance approach to fuzzy control design for nonlinear systems

Abstract This paper presents a systematic methodology to the design of a decentralized fuzzy logic controller for large-scale nonlinear systems. A new method which is based on a performance index of sliding mode control is used to derive fuzzy rules and an adaptive algorithm is used to reduce the chattering phenomenon. The simulation results of a two-inverted pendulum system and a two-link manipulator demonstrate that the attractive features of the proposed approach include a smaller residual error and robustness against nonlinear interactions.

Genetic synthesis of fuzzy logic controllers in turning

Abstract The paper presents an optimal fuzzy logic controller design using efficient robust optimization techniques called genetic algorithms. It is shown that genetic algorithms can automatically search input and output scaling factors, membership functions, and fuzzy rules of the fuzzy logic controllers based on a fitness function. As a result, fuzzy logic controllers with optimal control performance can be systematically constructed instead of using a time-consuming trial and error approach. An adaptive force control system in turning operations is then used to illustrate the proposed method. It is shown that the developed fuzzy logic controller can achieve an automatic adjustment of feed rate to optimize the production rate with a constant cutting force in turning operations.

A systematic approach for designing multistage fuzzy control systems

This paper proposes a systematic approach for designing a multistage fuzzy logic controller (MFLC) for large scale nonlinear systems. In designing such a controller, the major tasks are to derive fuzzy rule bases, determine membership functions of input/output variables, and design input/output scaling factors. In this work, the fuzzy rule bases are generated by rule-generated functions which are based on the negative gradient of a system performance index. The membership functions of isosceles triangle of input/output variables are fixed in the same cardinality, and only the input/output scaling factors are optimized from a genetic algorithm based on a fitness function. As a result, the search space of the parameters is narrowed down to a small space so that the MFLC can be quickly constructed and the fuzzy rules and scaling factors can easily be determined. The performance of the proposed approach is examined by computer simulations on an inverted pendulum system. The performance of single stage structure, binary tree structure and skew-binary tree structure are compared. The binary tree structure has better performance and use fewer fuzzy rules in the illustrative example.

A study of backlash on the motion accuracy of CNC lathes

In this paper, an analytical solution is reported to explain the experimentally observed backlash behaviors on the motion accuracy of CNC lathes. It is found that backlash occurs when the feed direction is reversed. Due to the imperfect transient response of the driving mechanism, not only the static backlash error but also the dynamic backlash error is generated on the contouring profile. A simple control strategy is then developed to reduce the static and dynamic backlash errors. Computational simulations and experimental results are presented to illustrate the proposed method.

A systematic method for design of multivariable fuzzy logic control systems

This paper proposes a systematic method to design a multivariable fuzzy logic controller for large-scale nonlinear systems. In designing a fuzzy logic controller, the major task is to determine fuzzy rule bases, membership functions of input/output variables, and input/output scaling factors. In this work, the fuzzy rule base is generated by a rule-generated function, which is based on the negative gradient of a system performance index; the membership functions of isosceles triangle of input/output variables are fixed in the same cardinality and only the input/output scaling factors are generated from a genetic algorithm based on a fitness function. As a result, the searching space of parameters is narrowed down to a small space, the multivariable fuzzy logic controller can quickly constructed, and the fuzzy rules and the scaling factors can easily be determined. The performance of the proposed method is examined by computer simulations on a Puma 560 system and a two-inverted pendulum system.

Cross-coupled fuzzy logic control for multiaxis machine tools

Abstract This paper presents a design and implementation case study that focuses on contour control of a biaxial CNC machine tools. Since, it is difficult to obtain an accurate nonlinear mathematical model of cross-coupled multiaxis machine tools, here we investigate an alternative to conventional approaches where we employ crosscoupled fuzzy logic controllers for improving the contouring accuracy of multiaxis CNC machine tools. A new fuzzy rule-generated method which is based on a performance index of the contour error obtained from an on-line estimation algorithm is proposed. An adapted output scale factor is adopted to improve the system performance. Experimental results have shown that the desired contouring accuracy can be achieved, and the proposed approach outperforms over uncoupled approaches. In conventional control, increasing contour feedrate for productivity may result in larger contour errors. However, the experimental results have shown that the performance of the proposed approach is still quite good with increasing contour feedrate.

A self-organizing neural fuzzy logic controller for turning operations

This paper proposes a neural fuzzy logic controller to achieve self-organizing control for turning operations. A new learning method which is based on a performance index of sliding mode control is used for control rule modifications and some supervision rules are also given to secure rule modifications. One of the major advantages of the proposed model is that it can start from an empty control rule base. Simulation and experimental results of the control of a constant turning force under varying cutting conditions are given to illustrate the effectiveness of the proposed method.

Adaptive multivariable fuzzy logic controller

Abstract This paper presents a systematic methodology to the design of a multivariable fuzzy logic controller (MFLC) for large-scale nonlinear systems. A new general method which is based on a performance index of sliding motion is used to generate a fuzzy control rule base. Reducible input variables obtained from sliding motion are adopted as input variable of the fuzzy controller and the output scale factors of the MFLC are tuned by the switching variable. Thus, the determination of the input/output scale factors becomes easier and the system performance is significantly improved. The simulation results of a Puma 560 system and a two-inverted pendulum system demonstrate that the attractive features of this proposed approach include a smaller residual error and robustness against nonlinear interactions.

Decision tree-based contrast enhancement for various color images

Conventional contrast enhancement methods are application-oriented and they need transformation functions and parameters which are specified manually. Furthermore, most of them do not produce satisfactory enhancement results for certain types of color images: dark, low-contrast, bright, mostly dark, high-contrast, and mostly bright. Thus, this paper proposes a decision tree-based contrast enhancement algorithm to enhance the above described color images simultaneously. This method includes three steps: first, statistical image features are extracted from the luminance distribution. Second, a decision tree-based classification is proposed to divide the input images into dark, low-contrast, bright, mostly dark, high-contrast, and mostly bright categories. Finally, these image categories are handled by piecewise linear based enhancement method. This novel enhancement method is automatic and parameter-free. Our experiments included different color and gray images. Experimental results show that the performance of the proposed enhancement method is better than other available methods in skin detection, visual perception, and image subtraction measurements.