Image-based steel bar end face automatic recognition counting algorithm

Abstract

The invention relates to an image-based steel bar end face automatic recognition counting algorithm. First of all, the end face region which needs to be processed in the image is extracted. the imageis preprocessed, which includes image scaling, Gaussian filtering; using cloud model to classify pixel color, obtaining preliminary segmentation of image according to the classification result, extracting parameters after closed operation to the segmented large connected region, including area ratio, center of gravity, aggregation degree, linear weighting to obtain reference value and selection, and obtaining end face region to be processed. Then the end face area is counted by fixed branch separation. Some images are preprocessed, including grayscale, histogram equalization and adaptive threshold binarization, and the binary image of the face region is obtained. Estimated radius of a single face is obtained by particle size measurement method, template is constructed according to formula,template matching is carried out, and the center position of the face is obtained. Finally, the robustness of the algorithm is improved by restriction conditions. The average correct rate of the invention can reach 97%.

Description

technical field [0001] The invention designs an automatic identification and counting algorithm for steel bar end faces, which involves traditional image processing algorithms, color image segmentation based on cloud models, particle size measurement methods, and template matching methods, and designs an automatic end face recognition and counting algorithm with higher accuracy, which belongs to related areas of image processing. Background technique [0002] In actual production, irregular round objects are ubiquitous, such as tubular workpieces, steel bars, bars, etc. are all round objects, and the recognition research on these objects is usually called round recognition. Circle-like recognition technology is an important content of digital image processing. The bar counting problem in steel production is one important application example. [0003] Bar production is an extremely important link in the industrial production of steel plants. Round steel and rebar, as finish...

AI Technical Summary

Problems solved by technology

However, the method of image processing to solve the automatic counting of bars has the following problems: (1) The boundary line of the bars is not obvious after packing, resulting in serious adhesion of the image; (2) The end faces of the bars are uneven, forming holes and uneven illumination; (3) The bending and irregular shape of the bar during shearing affect the counting

Using the idea of ​​distance transformation to determine the center of the bar to realize the automatic counting of the bar can not solve the problem of bar deformation and deep adhesion, which may easily lead to misjudgment

The bar counting method based on the template covering method, due to the deformation of the bar due to shearing, it is difficult to obtain an accurate count due to the difficulty of template matching

The method of edge detection is used to obtain the center information of the bar and realize the counting of the bar. The edge information is greatly affected by the outside world, and it is difficult to achieve reliable extraction.

Images