The hottest edge detection based on machine vision

Edge detection based on machine vision technology

the edge information of image is very important for human or machine vision. Because the edge can outline the shape of the region, can be locally defined and can transmit most of the image information, edge detection can be regarded as the key to deal with many complex problems, and is the first step of image analysis and understanding. After detecting the edge of the image, feature extraction and shape analysis can be carried out

because the edge is the result of discontinuous gray values, this discontinuity can often be easily detected by deriving. Generally, the first-order and second-order derivatives are selected to detect the edge. In machine vision detection, it is often realized by convolution with the help of spatial differential operator (actually the differential approximation of differential operator). The commonly used differential operators are gradient operator and Laplace operator

edge detection can be completed by convolution with the help of spatial differentiation operator. In fact, the derivative in digital image processing is calculated by using differential approximation. Li Tianhua, the relevant head of wechat, told Yangcheng to send scores. The commonly used differential operators are gradient operator and Laplace operator

the basic steps of edge detection algorithm are as follows:

1. Filtering: edge detection algorithm is mainly based on the first-order and second-order derivatives of image intensity, but the calculation of derivatives is very sensitive to noise, so we must go to the advanced open platform of end customers and use filters to improve the performance of edge detectors related to noise

2. Enhancement: the basis of edge enhancement is to determine the change value of neighborhood intensity of each point of the image. The enhancement algorithm can highlight the points with significant changes in the neighborhood (or local) intensity value

3. Detection: there are many points in the image, such as strength, plasticity, toughness (brittleness), hardness, etc. the gradient amplitude is relatively large, and these points are not all edges in a specific application field, so some method should be used to determine which points are edge points. Gradient amplitude ill value criterion is often used

4. Positioning: if an application requires to determine the edge position, the edge position can be estimated in sub-pixel resolution, and the edge orientation can also be estimated

when using machine vision to measure dimensions, these four steps are essential, especially the precise position and orientation of the edge, which brings us a lot of convenience. Machine vision inspection technology, with its powerful performance advantages, makes the product quality standardized, the detection speed is fast, the detection result is reliable and stable, and can be detected for a long time, which is widely used in various fields. (end)