Image registration has been a hot research spot in the computer vision technology and image processing. Image registration is one of the key technologies in image mosaic. In order to improve the accuracy of matching feature points, this paper put forward the least square optimization in image mosaic based on the algorithm of matching similarity of matrices. The correlation coefficient method of matrix is used for matching the module points in the overlap region of images and calculating the error between matrices. The error of feature points can be further minimized by using the method of least square optimization. Finally, image mosaic can be achieved by the two pair of feature points with minimized residual sum of squares. The experimental results demonstrate that the least square optimization in image mosaic can mosaic images with overlap region and improve the accuracy of matching feature points.
LED module board is the basic composition unit of LED panel, and the quality of module board is the key and premised
for panel to obtain a display of good quality. In this paper, based on the practice of project, use median filtering to filter
the pulse and salt-pepper noises, which are produced in the process of image acquisition, and use the adaptive OTSU to
segment images, adjust the angle between standard position image and the image caused by table vibration with
Fomier-Mellin method, and process results adjusted with bilinear interpolation method. Results show that, using the
image segmentation method can accurately determine the threshold image segmentation, results meet factory detection
requirements, the method can be used in the industrial field of application of real-time measurement system with a higher
promotional value.
An active vision detection technology based on laser target is proposed in this paper for measuring the dimensions of thermal train wheels in workshop. A mapping transorm of histogram is used to restrain thermal background and extrude the laser target, therefore, it is necessary to search the transform threshold value. The color weights of the image background are analysed. A contrast of the laser targe stripe and a recognized error are pursued to a best threshold for image mapping transform. The experiments prove that the useful information of the laser target image is extruded and the recognized errors caused by the mapping transorm are less than 0.04 pixel. A theoretical foundation is set up for the laser target pick-up correctly and other image processing expediently.
Dimension and form of a train wheel tread contour are the key controlled parameters in manufacturing and running process. Projecting laser light line to the tread contour, the left image and the right one of the light line in the measured countour are caught by using two CCD cameras. After calibrating the two images and other processing, the two images are pieced together to form a free-form curve. Measuring and data processing are completed in two steps as using "Bi-measurement Evaluation Test", the first step is modeling and the second is testing. Comparing the real coordinate values of Testing points with their theoretical ones reconstructed from the form model, the problem whether the model expresses the contour features enough can be resolved. If the answer is yes, the number and position distribution of sampling points are rational, then we can estimate the standard deviation (σ) of noise in the measuring sequence made up of coordinate values of sampling points. The fact that the standard deviation (σ) of noise in the real measuring sequence is about 0.1600mm is estimated by real measuring and data analysis.
Camera calibration is an important step in machine vision for dimensional measurement. Based on analyzing the photogrammetric calibration and self-calibration methods, a new planar way is proposed in this paper for calibrating the camera for the 2D objects. Induced some non-linear distortion factors, a fast algorithm is adopted to solve the complicated non-linear equations in calibration model. With this algorithm, a concatenation technique is used to reconstruct a 3D object from two 2D planar photos. In the second part of this paper, a calibration method using only one plane, which can be moved on some simple equipment, is deduced for 3D object dimensional measurement. Mathematic model and its transformation process are discussed in detail. This method can be used especially for profile inspection of machine parts in industrial working-field. An application to inspect the profile of train wheel is given in this paper. Experimental results are given to show the parameters of camera system and the measuring accuracy.
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.