Improved probability Hough transform curve detection method based on partitioning minimum samples fixing

A Hough transform and block technology, applied in the application field, achieves the effects of convenient programming, improved detection speed, and simple principle

CN103955925AActive Publication Date: 2014-07-30HUNAN UNIV
4 Cites 4 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2014-07-30

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses an improved probability Hough transform curve detection method based on partitioning minimum samples fixing. The method comprises the steps that the edge or a framework of an image is extracted, so that a binary feature image is obtained; according to a given partitioning size, the feature image is partitioned; a feature point set of each partition is obtained; according to a given random sampling rate, the partitioning minimum sampling number, the partition area and the size of each feature point set, the actual sampling number of each partition is obtained; through unrepeated random sampling, feature points with the number equal to the actual sampling number are extracted from the feature point set of each partition; a union set of feature point sample sets extracted from the partitions serves as a total sample set; standard Hough transform is conducted on the total sample set, so that curve detection is finished. The method can combine the advantage that standard Hough transform is simple and easy to achieve and the advantage that probability Hough transform is high in speed, false curves caused by complex texture regions in the image can be restrained, and the detection rate of a highest peak value point set in Hough space is improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the application fields of industrial and agricultural production, transportation, remote sensing, etc., and in particular relates to an improved probability Hough transform method for detecting parameterized curves in complex scenes by using a block-fixed minimum sampling method. Background technique

[0002] The detection of parametric curves is an important task in image analysis, understanding and machine vision, such as the detection and measurement of straight line and arc-shaped contours of workpieces in industrial production detection, automatic fruit picking robots in agricultural production detect circles or ellipses Typical examples of parametric curve detection include shaped fruit, lane line recognition in smart cars, line graph understanding in document image analysis, and road and rule artifact recognition in remote sensing images.

[0003] The standard Hough transform is one of the mainstream methods for parametr...

Examples

Embodiment Construction

[0036] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0037] The overall flow chart of the proposed method of the present invention is as figure 1 shown.

[0038] Such as figure 2 Shown is a scanned image of an example printed document. The image of the embodiment is read into MATLAB7.0 in the computer, and the im2bw function is used to perform adaptive threshold segmentation. After the obtained binary image is inversely colored, the bwmorph function is used to extract the skeleton, and the following is obtained: image 3 The binary feature image shown. For convenience of observation, in image 3 The feature points are represented in black, while the background points are represented in white.

[0039] Such as Figure 4 Shown is using the standard Hough transform in figure 2 The test results obtained above. In an embodiment, the discretized polar angle sequence used by the stan...