When inspecting industrial parts, the measurement results are displayed as labels to enable the operators to better understand and judge the measurement results. The use of industrial software for the automatic layout of measurement points labeling is a good way considering the layout efficiency. When there are numerous labels, the layout is prone to be unreasonable and with a decrease in layout efficiency, since it often encounters issues of labels overlapping and hence requiring manual adjustments. This paper proposes an automatic label placement method based on the circular pre-placement and an EFR (enhanced Fruchterman-Reingold) algorithm, which utilizes the balance of attraction and repulsion between labels for the automatic location adjustment. Case studies are given to verify the effectiveness of the proposed method on automatic layout and preventing label region overlapping, which greatly saves the layout time from traditional manual adjustments.
In the process of using machine vision technology to detect the edges of circular holes and rectangular slots on furniture panel, the uneven stripes on the panel and the uneven distribution of details in the holes and slots will produce a lot of graphic noise, which will interfere with the edge information of holes and slots and affect the accuracy and stability of the detection results. This article proposes a method based on HSV color space segmentation, which can effectively eliminate unevenly distributed texture and detail noise and deepen edge information, and improve the reliability and accuracy of machine vision edge information. Firstly, the RGB raw image is converted to HSV color space image, and obtain the grayscale image with Hue, Saturation and Value channels. Then the hue channel grayscale image with obvious edge boundary between the hole, slot and the panel is selected, and the appropriate Gaussian kernel is selected for the image to perform Gaussian filtering. Finally, the edge of the filtered image is extracted by adjusting the appropriate upper and lower thresholds and using the Canny operator. The experimental results show that this method can effectively remove the texture of furniture panel and the noise of uneven details in the holes and slots, but also can almost retain the edge of the holes and the whole edge of the panel.
Machine vision detection relies on high-quality image extraction features obtained by the camera, and multi-exposure
image fusion technology is a crucial method to acquire images with high dynamic range and rich details. In order to better
obtain high dynamic range detail information of the entire scene to extract more image features, this paper proposes a
detail enhancement multi-exposure image fusion algorithm based on the exposure function and the homomorphic filtering
function to determine the weight. First, image sequences with different exposures are acquired by the camera and corrected,
then the exposure function and homomorphic filtering are used to determine the weight map of each image, and finally the
final fusion image is obtained by the multi-scale method. Compared with the current four advanced methods, the
experimental results show that the algorithm can obtain better imaging quality and more image detail information, and
obtain satisfactory visual effects. It provides a solution for the subsequent machine vision to extract richer features of the
image.
The machine vision system has already become the optical mechanical electrical integration products or components of
products in modern equipment manufacturing industry. The new LED is more excellent than the halogen tungsten lamp,
laser and other traditional light source. It is used in machine vision system more and more.
From the analysis of the functional characteristics, this article pointed out the difference between machine vision LED
lighting system and traditional optical instrument lighting system. By the interactive methods which integrate with
synthesis design analysis and Simulation, this paper import the element of field flattening theory into traditional lighting
design, making it a kind of the new flat field lighting system. The effect when it was applied to high power LED lighting
system is good.
With the new design concept, through the interactive design method and the new image quality evaluation system, we
have a contrast experiment on a kind of LED single lamp lighting system. The results show that the field flat lighting
system is superior to the traditional one. The most distinctive feature of the new light system is that, it can improve the
performance of critical illumination system in certain procedures -- poor illumination uniformity performance. This new
lighting optical structure and the new lighting quality evaluation system have broad prospects.
A second parallel CCD (CMOS) imaging system for an telescope objective with the fixed D/f' is
proposed in detail. As a direct imaging system that the CCD target surface coincides with the
imaging surface of the telescope objective, it shows the outstanding performance of more than
doubled resolution compared with the ordinary telescope objective under the same D/f'. Based on
the discussions about the second parallel optical path telescope system, three design examples are
compared and analyzed. The relation between the optical properties of image field and the optical
elements of the second parallel path is clarified, which provides an operable method for readers.
This practice has proved the outstanding performance of the new telescope objective
photoelectronic imaging system which indicates potential applications in broad scientific and
industrial prospects.
The strong lateral polarization component of radially polarized beam focused by high numerical aperture objective
shows totally axis-symmetrical property, which gives rise to its widely applications in many optical devices. The
equations of vectorial three dimensional(3D) electric field of radially polarized beam focused by high numerical
aperture objective are given based on the vectorial Debye theory. The finite difference time domain(FDTD) method is
applied to simulate the focusing of radially polarized beam. The electric field of radially polarized focal beam in a
defocus plan calculated by Debye theory is induced as input source using the total/scatter field approach. We simulated
the focusing processes in single dielectric medium and through the interface of two dielectric media, respectively. The
distribution of electric field of the focus obtained from the FDTD results coincides with that directly calculated by
Debye theory, which proves the facility of FDTD method for simulating the focusing optical field. Additionally, we
simulate the focusing of radially polarized beam through dielectric half ball shaped nano-holes with different sizes. The
focus shift effect caused by the different sizes of nano-holes provides the mechanism for changing the longitudinal
position and the lateral resolution of the focus in subwavelength scale. At last, the surface plasmons excited by the
radially polarized focus are shown at the surface of the metallic film and form a smaller focus. The simulation results of
this paper will give contribution to the super-resolution focusing for nano-lithography.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.