scholarly journals A surface defect identification method based on improved threshold segmentation algorithm

2020 ◽  
Vol 1651 ◽  
pp. 012072
Author(s):  
Xinglong Feng ◽  
Xianwen Gao ◽  
Ling Luo
Keyword(s):  
Surface Defect ◽  
Segmentation Algorithm ◽  
Threshold Segmentation ◽  
Defect Identification ◽  
Identification Method

The Detection Method of Lane Line Based on the Improved Otsu Threshold Segmentation

2015 ◽  
Vol 741 ◽  
pp. 354-358 ◽  
Author(s):  
Yang Shan Tang ◽  
Dao Hua Xia ◽  
Gui Yang Zhang ◽  
Li Na Ge ◽  
Xin Yang Yan
Keyword(s):  
Image Segmentation ◽  
Processing Time ◽  
Detection Method ◽  
Segmentation Algorithm ◽  
Test Results ◽  
Threshold Segmentation ◽  
Otsu Method ◽  
Time Requirements ◽  
Lane Line ◽  
Center Distance

For overcoming the shortage of Otsu method, proposed an improved Otsu threshold segmentation algorithm. On the basis of Otsu threshold segmentation algorithm, the gray level was divided into two classes according to the image segmentation, to determine the best threshold by comparing their center distance, so as to achieve peak line recognition under the condition of multiple gray levels. Then did experiments on image segmentation of the lane line with MATLAB by traditional Otsu threshold segmentation algorithm and the improved algorithm, the threshold of traditional Otsu threshold segmentation algorithm is 144 and the threshold of the improved Otsu threshold segmentation algorithm is 131, the processing time is within 0.453 s. Test results show that the white part markings appear more, the intersection place of white lines and the background is more clear, so this method can identify lane markings well and meet the real-time requirements.

ANALYSIS OF THE ERROR IN DETERMINING THE EQUIVALENT SIZE OF A DEFECT BY THE STANDARDLESS METHOD DURING ULTRASONIC TESTING

2021 ◽  
pp. 50-57
Author(s):  
A. N. Kireev ◽  
M. A. Kireeva
Keyword(s):  
Relative Error ◽  
High Reliability ◽  
Ultrasonic Method ◽  
Experimental Studies ◽  
Standard Samples ◽  
Defect Identification ◽  
Identification Method ◽  
Maximum Value ◽  
Software Product ◽  
The Relationship

The article provides a review and analysis of the defect identification method for determining the size of discontinuities when diagnosing various machine parts and units by the manual ultrasonic method. This method makes it possible to determine the equivalent size of discontinuities of various types without using standard samples of an enterprise: point planar and volumetric; extended planar and volumetric. The method is based on the use of the relationship between the amplitude and time characteristics of the echo signal from the discontinuity and the backside signal in the object being diagnosed and the equivalent size of the discontinuity. The article presents the mathematical apparatus for the implementation of this method. Also presented is a software product that allows you to automate calculations when using this defect identification method. The article contains experimental studies of the method for determining the equivalent dimensions of discontinuities of various types, which have shown its high reliability. The maximum value of the relative error in determining the equivalent size of a point planar discontinuity was 2.867 %. The maximum value of the relative error in determining the equivalent size of a point volumetric discontinuity was 1.986 %. The maximum value of the relative error in determining the transverse equivalent size of an extended planar discontinuity was 0.667 %. The maximum value of the relative error in determining the transverse equivalent size of an extended volumetric discontinuity was 1.95 %.

Image Threshold Segmentation Algorithm Based on Histogram Statistical Property

2014 ◽  
Vol 644-650 ◽  
pp. 4027-4030
Author(s):  
Hong Li ◽  
Zhong An Lai ◽  
Jun Wei Lei
Keyword(s):  
Normal Distribution ◽  
Complex Shape ◽  
Good Method ◽  
Segmentation Algorithm ◽  
Gray Level ◽  
Background Region ◽  
Threshold Segmentation ◽  
Target Region ◽  
Statistical Property ◽  
Otsu’S Method

The traditional Otsu threshold algorithm is not a good method for processing the real images because of complex shape and unbalanced distribution. To solve this problem, the paper uses the thinking of Otsu’s method for reference, introduces a threshold segmentation algorithm based on histogram statistical property. In addition, the paper draws a comparison between the new algorithm and Otsu’s algorithm. Experimental results show that the new algorithm can get better segmentation effect than that of Otsu’s method when the gray-level distribution of the background follows normal distribution approximatively, and the target region is less than the background region.

Sign in / Sign up

Export Citation Format

Share Document