Monocular machine vision method for judging the positive and negative attitude of watch shell workpiece
A machine vision and watch technology, applied in the interpretation of photos, etc., can solve the problems of mechanical structure affecting service life and maintenance costs, easy fatigue, and increased recognition error rate.
Inactive Publication Date: 2020-10-30
TONGJI UNIV
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Although the task of identifying the front and back of a watch case is very simple and can be easily completed manually, due to the large number of cases on the production line of watch case processing and manufacturing, the human eye is prone to fatigue after a long time of recognition, and the recognition error rate will increase with the increase of working hours
From an economic point of view, on the basis of mass production, the cost of using manual identification is higher than the cost of mechanical identification
In addition, using a purely mechanical structure to distinguish the front and back of the watch case also has its own limitations.
On the one hand, the mechanical structure is relatively complex, and the design and manufacturing costs are high; on the other hand, the complexity of the mechanical structure directly affects its service life and maintenance costs
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0046] The schematic diagram of the machine vision hardware system built in this project is as follows: figure 1 . in figure 1 (a) in the figure shows the illumination schematic diagram of the light source system. It can be seen from the figure that the visual hardware system is mainly composed of a black box, a camera, a light source and the workpiece to be photographed. The image taken by the designed system is the top view of the workpiece. The distance between the light source and the camera and the workpiece should be adjustable. figure 1 (b) is a sectional view of the specific 3D model of the built vision system. In order to facilitate the display of the internal structure, the top cover of the black box has been hidden in the figure. In order to reduce the impact of the external environment on the image acquisition process, a black box is designed in this project. The workpiece enters the black box to be photographed, so as to isolate the workpiece from the external...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to a monocular machine vision method for normal or reversed position determination of a wristwatch case workpiece. A photographing angle of the vision system in the invention isa top view of a workpiece. Meanwhile, an OpenCV based library function is used to determine a normal position or a reversed position of the wristwatch case. The monocular machine vision method has a high anti-interference performance, a low requirement for hardware device and high determination accuracy. When the vision system is used for an assembly line having a task of determining whether the wristwatch case is at the normal position or the reversed position, the work efficiency will be greatly improved, and the production automation is realized by replacing human-eye identification with machine identification.
Description
technical field [0001] The invention relates to a monocular machine vision method for judging the positive and negative postures of watch shell workpieces. Background technique [0002] Paul Hough proposed the Hough transform in the machine analysis of bubble chamber photos in 1959, and obtained a US patent in 1962, named Method and Means for Recognizing Complex Patterns. In this patent, the parametric equation of the straight line adopts the slope-intercept formula, but since the slope may be infinite, this may lead to an infinite transformation space. [0003] The Hough transform used in this patent was invented by Richard Duda and Peter Hart in 1972. It is called "Generalized Hough Transform [GHT]", and its invention patent name is "Use of the Hough Transformation to Detect Lines and Curves in Pictures , 1972". Then in 1981, an article called Generalizing the Hough transform to detect arbitrary shapes appeared in the computer vision community, and the Hough transform te...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G01C11/04
CPCG01C11/04
Inventor 李梦如吴轩全陈哲卜王辉陈茂林奚鹰
Owner TONGJI UNIV