A Study On The Classification Of Multi-spectral Remote Sensing Image Based On Fuzzy Integrals

Remote sensing (RS) image classification is always a pivotal part of remote sensing study. How to improve the accuracy of RS interpretation is an urgent problem in RS application. In recent years, with the development of the theory about artificial neural network system, the multiple classifier fusion technology is becoming increasingly an effective means of classification processing of remote sensing images. Compared with classification of the traditional Bayesian statistics, the results show it has not only the highest accuracy but also the fastest speed of classification. This thesis tries to apply new techniques of multiple classifier fusion to the area of classification of Multi-spectral image, and make efforts to meliorate the fusion models.Multiple classifier fusion, or combination, is a modern technique in pattern recognition areas. Through pertinently combining different information from varies of simple classifiers, the classification accuracy can be fairly improved and the difficulty of designing a single, high-accuracy classifier could be avoided. In recent years, fusion methods of many kinds have been widely used in the identification of human face, hand-written characters, etc., but relatively rarely studied in the medical image region.The construction of a fusion system mainly concerns to two steps: Devising individual classifiers, selection of the component classifiers, and designing proper fusion model to combine these components. In this paper, after image features selected, BP networks trained as individual classifiers, By analyzing the different fusion theories and comparing their performances, we use the model of multi-classifier fusion based on fuzzy integrals respect to lambda-fuzzy measures to make a decision on the image classification.Fuzzy Integral is an aggregation tool in multi-classifier fusion, which can improve the accuracy of classification and the robustness of systems. In multi-classifier fusion based on fuzzy integrals, fuzzy measures have much influence on the performance of fusion systems. If the fuzzy measures are well defined, the accuracy of classification can be improved distinctly. This paper gives two methods about determining the fuzzy measures: 1. determine the fuzzy measures based on the genetic algorithm; 2. determine the fuzzy measures based on the neural networks. This method is verified to be practical by experiments.