A skeleton detection system and detection method for noisy images
A detection system and skeleton technology, applied in the field of computer vision, can solve problems such as poor robustness, and achieve the effect of easy implementation, simple structure, and good robustness advantages
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0054] A noise-oriented skeleton detection system according to the present invention includes eight skeleton filters, each skeleton filter includes a pair of two-dimensional Gabor-like filters with mutually opposite directions; each Gabor-like filter It consists of a pair of positive and negative Gaussian filters, where the positive Gaussian filter is located in the center position, and the negative Gaussian filter is located in the surrounding position, which ensures that each skeleton filter has reflection symmetry; The absolute value is uniformly normalized, so that the sum of positive and negative in each skeleton filter is zero, which ensures that each skeleton filter has a zero-sum structure.
[0055] Eight skeleton filters are respectively set in eight directions of the x-y plane of the Cartesian coordinate system, wherein the skeleton filters in seven directions are obtained by rotating the skeleton filters in one direction in the x-y plane of the Cartesian coordinate s...
Embodiment 2
[0068] The principle of Embodiment 2 is basically the same as that of Embodiment 1, the difference is that in Embodiment 2, the positive Gaussian filter is located at the center position, and the negative Gaussian filter is located at the surrounding position.
[0069] When using the skeleton detection method described in Example 1 for noise image detection, the obtained skeleton feature image is as follows Image 6 As shown, the noise interference in the noise image to be detected can be handled very robustly, and it is suitable for the target object brightness in the noise image to be detected is lower than the background image.
Embodiment 3
[0071] When there are parts of the same noise image to be detected that the brightness of the target object is higher than that of the background image, and there are also parts of the target object that are lower than the background image, the noise image to be detected is processed by using Embodiment 1 and Embodiment 2 respectively, The results obtained in Embodiment 1 and Embodiment 2 are combined by an addition operation, so as to realize the processing of noise images with different brightness of target objects in the noise images to be detected.
[0072] When using the skeleton detection method described in Example 3 for noise image detection, the obtained skeleton feature image is as follows Figure 7 As shown, the noise interference in the noise image to be detected can be handled very robustly, and is suitable for the noise image to be detected in various situations.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


