Edge detection

Algorithm

Pixel

Biology

Sorting

Image processing

Computer science

Scale-space segmentation

Image segmentation

Genetics

Segmentation

Sequence (biology)

Mathematics

Image (mathematics)

Tree traversal

Artificial intelligence

Geometry

Point (geometry)

Linear equation

Computer vision

Measurement

The premise of identifying, locating, and sorting coal and gangue using photoelectric sorting technology is that independent image targets should be obtained. In this study, concave point detection and segmentation algorithm are proposed to segment overlapping particles. First, the edge coordinate sequence is obtained for the overlapping part of the concave defect area of the adhesion target and the binary image of the adhesion target. Subsequently, the initial linear equation passing through the beginning and ending points of the sequence is built. The traversal sequence updates the new linear equation parallel to the initial linear equation, and the positional relationship between the front and back points of the search point and the linear equation is determined. The concave point detection is transformed into the positional relationship between pixels and linear equations. Lastly, the segmentation line segmentation image is generated based on concave points, and the segmentation accuracy reaches 93.15%.

Multi-scale coal and gangue dual-energy X-ray image concave point detection and segmentation algorithm