The Research of the PCB Location Based on Three Layers of MARK Point

2011 ◽  
Vol 317-319 ◽  
pp. 869-876 ◽  
Author(s):  
Hao Wu ◽  
Xian Min Zhang ◽  
Yong Cong Kuang
Keyword(s):  
Position Error ◽  
Field Of View ◽  
Uneven Surface ◽  
Position Accuracy ◽  
Loading Process ◽  
Optical Inspection ◽  
Automated Optical Inspection

In order to reduce the position error produced by single board assembly and partial uneven surface in automated optical inspection, a new position method based on three layers of MARK point is developed. the first layer is the whole board alignment which compensate the position error of the PCB loading process, the second layer is the single board alignment which compensate the position error of the single board assembly, the last layer is the partial FOV(field of view) alignment which compensate the position error of the partial uneven surface. The experiment result proved the proposed position method improved the position accuracy obviously.

scholarly journals Ceramic Cracks Segmentation with Deep Learning

2021 ◽  
Vol 11 (13) ◽  
pp. 6017
Author(s):  
Gerivan Santos Junior ◽  
Janderson Ferreira ◽  
Cristian Millán-Arias ◽  
Ramiro Daniel ◽  
Alberto Casado Junior ◽  
...  
Keyword(s):  
Deep Learning ◽  
Ceramic Plate ◽  
Ceramic Tiles ◽  
Entire Area ◽  
Manual Inspection ◽  
Optical Inspection ◽  
Proposed Model ◽  
Processing Step ◽  
Long Time ◽  
Automated Optical Inspection

Cracks are pathologies whose appearance in ceramic tiles can cause various damages due to the coating system losing water tightness and impermeability functions. Besides, the detachment of a ceramic plate, exposing the building structure, can still reach people who move around the building. Manual inspection is the most common method for addressing this problem. However, it depends on the knowledge and experience of those who perform the analysis and demands a long time and a high cost to map the entire area. This work focuses on automated optical inspection to find faults in ceramic tiles performing the segmentation of cracks in ceramic images using deep learning to segment these defects. We propose an architecture for segmenting cracks in facades with Deep Learning that includes an image pre-processing step. We also propose the Ceramic Crack Database, a set of images to segment defects in ceramic tiles. The proposed model can adequately identify the crack even when it is close to or within the grout.

Improving position accuracy for telescopes with small aperture and wide field of view utilizing point spread function modelling

2020 ◽  
Vol 497 (3) ◽  
pp. 4000-4008
Author(s):  
Rongyu Sun ◽  
Shengxian Yu ◽  
Peng Jia ◽  
Changyin Zhao
Keyword(s):  
Point Spread Function ◽  
Large Scale ◽  
Field Of View ◽  
Wide Field ◽  
Position Measurement ◽  
Small Aperture ◽  
Position Accuracy ◽  
Point Spread ◽  
Wide Field Of View ◽  
Spread Function

ABSTRACT Telescopes with a small aperture and a wide field of view are widely used and play a significant role in large-scale state-of-the-art sky survey applications, such as transient detection and near-Earth object observations. However, owing to the specific defects caused by optical aberrations, the image quality and efficiency of source detection are affected. To achieve high-accuracy position measurements, an innovative technique is proposed. First, a large number of raw images are analysed using principal component analysis. Then, the effective point spread function is reconstructed, which reflects the state of the telescope and reveals the characteristics of the imaging process. Finally, based on the point spread function model, the centroids of star images are estimated iteratively. To test the efficiency and reliability of our algorithm, a large number of simulated images are produced, and a telescope with small aperture and wide field of view is utilized to acquire the raw images. The position measurement of sources is performed using our novel method and two other common methods on these data. Based on a comparison of the results, the improvement is investigated, and it is demonstrated that our proposed technique outperforms the others on position accuracy. We explore the limitations and potential gains that may be achieved by applying this technique to custom systems designed specifically for wide-field astronomical applications.

Synthesizing images using parameterized models for automated optical inspection (AOI)

2015 ◽  
Vol 82 (5) ◽  
Author(s):  
Max-Gerd Retzlaff ◽  
Josua Stabenow ◽  
Jürgen Beyerer ◽  
Carsten Dachsbacher
Keyword(s):  
Physical Simulation ◽  
Rigid Bodies ◽  
Systematic Evaluation ◽  
Virtual Objects ◽  
Optical Inspection ◽  
Physically Based ◽  
Automated Optical Inspection ◽  
Real Objects ◽  
Physically Based Rendering ◽  
Test Objects

AbstractWhen designing or improving systems for automated optical inspection (AOI), systematic evaluation is an important but costly necessity to achieve and ensure high quality. Computer graphics methods can be used to quickly create large virtual sets of samples of test objects and to simulate image acquisition setups. We use procedural modeling techniques to generate virtual objects with varying appearance and properties, mimicking real objects and sample sets. Physical simulation of rigid bodies is deployed to simulate the placement of virtual objects, and using physically-based rendering techniques we create synthetic images. These are used as input to an AOI system instead of physically acquired images. This enables the development, optimization, and evaluation of the image processing and classification steps of an AOI system independently of a physical realization. We demonstrate this approach for shards of glass, as sorting glass is one challenging practical application for AOI.

Dimensional Optimization for Minimally Invasive Surgery Robot Based on Double Space and Kinematic Accuracy Reliability Index

2020 ◽  
Vol 3 (2) ◽  
Author(s):  
Yang Jing ◽  
Jin Lingyan ◽  
Shi Xinge ◽  
Zhao Deming ◽  
Hu Ming
Keyword(s):  
Reliability Index ◽  
Position Error ◽  
Optimal Size ◽  
Kinematic Accuracy ◽  
Position Accuracy ◽  
Adjustment Mechanism ◽  
Error Space ◽  
Double Space ◽  
Kinematic Performance ◽  
Dimensional Optimization

Abstract To improve the kinematic performance of the remote center mechanism for surgical robot, a double space index and kinematic accuracy reliability index are proposed to optimize the dimensional sizes of mechanism. First, the influence of the angular error on the position error and the operability of the remote center in the workspace are analyzed. The position error space and operability space index are weighted to establish the double space index. Second, a kinematic accuracy reliability index is established based on the influence of joint clearance on output position accuracy. Finally, the dimensional sizes of remote center adjustment mechanism and double parallelogram mechanism are optimized based on proposed optimization indices. Multipopulation genetic algorithm is used to obtain the optimal size parameters under the corresponding index. The optimized double space index is 56.7%, which is 56.5% higher than before optimization. The optimized kinematic accuracy reliability is 0.91, which is 22.9% higher than before optimization. The kinematic performance of remote center mechanism has been significantly improved after optimization.

Sign in / Sign up

Export Citation Format

Share Document