To boost up the recognizing ability, and to advance the precision and efficiency of the applications with aerial image and satellite image data, we discuss the best segmental scale to different objects and different images, and compare the final classification result.

Effects of changing scale on spatial analysis have been studied for decades in geography and ecology,but few previous studies expounded the quantitative approach about the optimization-scale.

In order to get the optimization-scale,18 indexes were calculated in 16 analysis scales.

It is proposed an optimal split-scale model of multi-scale segmentation based on object-oriented analysis methods,and made the experiment of image segmentation and the evaluation of segmentation quality.

By researching the false maximum wavelet coefficient points, this paper proposes an advanced algorithm in the basis of optimum scale and a new peak-searching method.

In the course of algorithm realization, this paper uses the corresponding relationship of the signal in time domain and frequency domain to propose a method for dynamically determining the optimal scale, which conquers the deficiency of fixed transform scale when the pitch has a fargoing change, and it induces the statistic in.