There is over-segmentation phenomenon based on watershed segmentation algorithm,so this paper presents a new segmentation algorithm,which is followed with floating-point moving image based on morphological grad image,then watershed transformation is done,edge orientation will be more precise.

First,gradient image is constructed by using direction templates convolve with image.

The gradient image is introduced to replace the floating video images to process watershed transformation in the algorithm, .

Firstly, it is obtained gradient image by taking dynamic morphological structual elements, then detecting the edge with SUSAN operator according to gradient image.

A new objective functional is formulated using a reflectance map equation and an image gradient equation.

The image gradient reflects the spatial structure of the image and the correlation coefficient of the image reflects the activity masking characteristic of the human visual system.

Finally,verifying by the sociable reality data,what the complexity of block definition based on the image gradient characteristic can be fairly more accurate estimates a motion vector of background,and the function is superior to others.

Traveling-wave starting algorithm based on morphological gradient and wavelet transform modulus sum

On the basis of basic morphological transforms and their combined modes,transient current signals can be extracted by use of morphological gradient with adaptive weighting.

This paper presents a novel algorithm of identifying the inrush current and short circuit current caused by internal fault on the basis of transient detection using morphological gradient, meanwhile transient current signals are extracted by use of morphological opening and closing algorithm.

Then edge detection based on morphological grads provides better license plate s edge and is propitious to locate exactly.