Hough transformation linear detection method based on dynamic threshold range

Abstract

The invention relates to a Hough transformation linear detection method based on a dynamic threshold range. The method comprises the following steps: performing storage in accordance with a cluster sequence based on adjacent relation, i.e., performing refinement processing on segments with certain line widths in images, outputting a frame line which has only two adjacent pixel points at most in eight neighborhoods of any one pixel point, and then based on the cluster sequence based on the adjacent relation, storing the frame line in a certain segment of arrays; and sampling m adjacent pixels in the certain segment of arrays to construct the threshold range by sampling, determining whether m points are at the same line, and filtering noise at the same time, such that the algorithmic robustness is enhanced. On the basis of constructing the threshold range, linear detection is realized by use of a dynamic sampling mode based on range halving. Each pixel in the pixel arrays is identified, such that the algorithmic detection efficiency and effect are improved.

Description

technical field [0001] The invention belongs to the technical field of image feature extraction and recognition, in particular to a Hough transform line detection method based on a dynamic threshold interval. Background technique [0002] Image feature extraction is the premise of image recognition, which involves computer graphics, digital image processing, pattern recognition, artificial intelligence and other disciplines, and has broad research space and application prospects. Intelligent recognition of engineering drawings is an important application field of image feature extraction. The main geometric elements of engineering graphics objects in various engineering drawings are line segments. How to quickly and effectively detect line segment features is the basis for recognizing graphic objects. [0003] Straight line extraction methods are mainly divided into two categories: the first type of method is to directly extract straight lines in the image domain based on ...

AI Technical Summary

Problems solved by technology

However, this method is a one-to-many mapping from the image domain to the parameter domain, and there are noise points and discretization errors, resulting in a large amount of calculation, and the peak points in the parameter domain are surrounded by sub-peak points, resulting in missed or false detections. Difficult to set etc.

[0004] In view of the large amount of calculation of Hough transform, A.Goldenshluger and A.Zeevi adopt the random Hough transform method, randomly extract a pixel from multiple pixels as sampling information and map it to the parameter space, avoiding a large amount of calculation and more memory overhead. However, since this method randomly obtains sampling points, it causes a large amount of invalid accumulation, which reduces the efficiency of the method.

[0005] Aiming at the problem that the peak point in the parameter domain is surrounded by sub-peaks, Siyu Guo et al. proposed a neighborhood suppression method to weight the voting values ​​projected into the parameter domain, effectively reducing the influence of sub-peaks and improving the accuracy of Hough transform detection , but the weight value setting of this method has a great influence on the detection results, and a large number of tests are required to obtain the accurate value of the weight, which increases the computational complexity of the method and reduces the practicability of the method

Images