scholarly journals Supervised Classification High-Resolution Remote-Sensing Image Based on Interval Type-2 Fuzzy Membership Function

2018 ◽  
Vol 10 (5) ◽  
pp. 710 ◽  
Author(s):  
Chunyan Wang ◽  
Aigong Xu ◽  
Xiaoli Li
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Membership Function ◽  
Supervised Classification ◽  
Remote Sensing Image ◽  
Fuzzy Membership ◽  
Fuzzy Membership Function ◽  
Interval Type

scholarly journals INTERVAL TYPE-2 FUZZY BASED NEURAL NETWORK FOR HIGH RESOLUTION REMOTE SENSING IMAGE SEGMENTATION

2016 ◽  
Vol XLI-B7 ◽  
pp. 385-391 ◽  
Author(s):  
Chunyan Wang ◽  
Aigong Xu ◽  
Chao Li ◽  
Xuemei Zhao
Keyword(s):  
Remote Sensing ◽  
Image Segmentation ◽  
High Resolution ◽  
Fuzzy Model ◽  
Remote Sensing Image ◽  
Fuzzy Membership ◽  
Fuzzy Membership Functions ◽  
Interval Type

Recently, high resolution remote sensing image segmentation is a hot issue in image procesing procedures. However, it is a difficult task. The difficulties derive from the uncertainties of pixel segmentation and decision-making model. To this end, we take spatial relationship into consideration when constructing the interval type-2 fuzzy neural networks for high resolution remote sensing image segmentation. First, the proposed algorithm constructs a Gaussian model as a type-1 fuzzy model to describe the uncertainty contained in the image. Second, interval type-2 fuzzy model is obtained by blurring the mean and variance in type-1 model. The proposed interval type-2 model can strengthen the expression of uncertainty and simultaneously decrease the uncertainty in the decision model. Then the fuzzy membership function itself and its upper and lower fuzzy membership functions of the training samples are used as the input of neuron network which acts as the decision model in proposed algorithm. Finally, the relationship of neighbour pixels is taken into consideration and the fuzzy membership functions of the detected pixel and its neighbourhood are used to decide the class of each pixel to get the final segmentation result. The proposed algorithm, FCM and HMRF-FCM algorithm and an interval type-2 fuzzy neuron networks without spatial relationships are performed on synthetic and real high resolution remote sensing images. The qualitative and quantitative analyses demonstrate the efficient of the proposed algorithm, especially for homogeneous regions which contains a great difference in its gray level (for example forest).

scholarly journals INTERVAL TYPE-2 FUZZY BASED NEURAL NETWORK FOR HIGH RESOLUTION REMOTE SENSING IMAGE SEGMENTATION

2016 ◽  
Vol XLI-B7 ◽  
pp. 385-391
Author(s):  
Chunyan Wang ◽  
Aigong Xu ◽  
Chao Li ◽  
Xuemei Zhao
Keyword(s):  
Remote Sensing ◽  
Image Segmentation ◽  
High Resolution ◽  
Fuzzy Model ◽  
Remote Sensing Image ◽  
Fuzzy Membership ◽  
Fuzzy Membership Functions ◽  
Interval Type

Recently, high resolution remote sensing image segmentation is a hot issue in image procesing procedures. However, it is a difficult task. The difficulties derive from the uncertainties of pixel segmentation and decision-making model. To this end, we take spatial relationship into consideration when constructing the interval type-2 fuzzy neural networks for high resolution remote sensing image segmentation. First, the proposed algorithm constructs a Gaussian model as a type-1 fuzzy model to describe the uncertainty contained in the image. Second, interval type-2 fuzzy model is obtained by blurring the mean and variance in type-1 model. The proposed interval type-2 model can strengthen the expression of uncertainty and simultaneously decrease the uncertainty in the decision model. Then the fuzzy membership function itself and its upper and lower fuzzy membership functions of the training samples are used as the input of neuron network which acts as the decision model in proposed algorithm. Finally, the relationship of neighbour pixels is taken into consideration and the fuzzy membership functions of the detected pixel and its neighbourhood are used to decide the class of each pixel to get the final segmentation result. The proposed algorithm, FCM and HMRF-FCM algorithm and an interval type-2 fuzzy neuron networks without spatial relationships are performed on synthetic and real high resolution remote sensing images. The qualitative and quantitative analyses demonstrate the efficient of the proposed algorithm, especially for homogeneous regions which contains a great difference in its gray level (for example forest).

scholarly journals COMPARISON OF FUZZY LOGIC CONTROLLERS FOR A MULTIVARIABLE PROCESS

2014 ◽  
pp. 138-143
Author(s):  
KARTHICK S ◽  
Dr.P. Lakshmi ◽  
DEEPA T
Keyword(s):  
Fuzzy Logic ◽  
Fuzzy Logic Controller ◽  
Dynamic Performance ◽  
Absolute Error ◽  
Fuzzy Membership ◽  
Fuzzy Membership Function ◽  
Error Performance ◽  
Fuzzy Membership Functions ◽  
Interval Type

The Interval Type-2 Fuzzy Logic Controller (IT2FLC) for a Quadruple Tank Process (QTP) is demonstrated in this paper. Here the Interval Type-2 based Fuzzy membership function is used. The QTP is made to operate in minimum phase mode. The vertices of fuzzy membership functions are tuned with IT2FLC to minimize Integral Absolute Error. Performance of IT2FLC and Type-1 Fuzzy Logic Controller (T1FLC) are compared with decentralized PI controller, by simulation using MATLAB/Simulink. Simulation results show that satisfactory performance for both servo and regulatory responses.It has been observed that dynamic performance of IT2FLC is better than the other two controllers. Moreover, compared with the T1FLC controller, IT2FLC performs better, particularly in noisy environments.

Sign in / Sign up

Export Citation Format

Share Document