scholarly journals Statistics Based Neural Networks Method for Industrial Image Inspection

2021 ◽  
Author(s):  
Yi Zhu
Keyword(s):  
Neural Networks ◽  
Image Registration ◽  
The Other ◽  
Inspection System ◽  
Tolerance Zone ◽  
Registration Method ◽  
Image Inspection ◽  
Feature Based ◽  
Two Indices ◽  
Defect Simulation

Automated industrial image inspection system has attracted a great deal of interest in recent years. In this thesis, a new method is presented by combining a statistics method with a neural networks method, which could reduce the interference of machine dynamics and improve the inspection accuracy. Different from the pixel-based or feature-based methods, the proposed method is based on two indices of an image, which are the variances of the rows and columns of the image. For image inspection, first neural networks are trained using these two indices from a set of good images in order to establish a tolerance zone. Then, the two indices of each inspection image are computed through trained neural networks and compared with the tolerance zone. A defective item is detected if either index falls out of the tolerance zone. The other contributions, such as two-point based image registration method and defect simulation algorithms, also help to improve the performance of inspection. Experimental results demonstrate that the proposed approach has a better performance in comparison with traditional statistics approach.

scholarly journals Statistics Based Neural Networks Method for Industrial Image Inspection

2021 ◽  
Author(s):  
Yi Zhu
Keyword(s):  
Neural Networks ◽  
Image Registration ◽  
The Other ◽  
Inspection System ◽  
Tolerance Zone ◽  
Registration Method ◽  
Image Inspection ◽  
Feature Based ◽  
Two Indices ◽  
Defect Simulation

Automated industrial image inspection system has attracted a great deal of interest in recent years. In this thesis, a new method is presented by combining a statistics method with a neural networks method, which could reduce the interference of machine dynamics and improve the inspection accuracy. Different from the pixel-based or feature-based methods, the proposed method is based on two indices of an image, which are the variances of the rows and columns of the image. For image inspection, first neural networks are trained using these two indices from a set of good images in order to establish a tolerance zone. Then, the two indices of each inspection image are computed through trained neural networks and compared with the tolerance zone. A defective item is detected if either index falls out of the tolerance zone. The other contributions, such as two-point based image registration method and defect simulation algorithms, also help to improve the performance of inspection. Experimental results demonstrate that the proposed approach has a better performance in comparison with traditional statistics approach.

scholarly journals An Image Registration Method Using Deep Residual Network Features for Multisource High-Resolution Remote Sensing Images

2021 ◽  
Vol 13 (17) ◽  
pp. 3425
Author(s):  
Xin Zhao ◽  
Hui Li ◽  
Ping Wang ◽  
Linhai Jing
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Image Registration ◽  
Feature Descriptor ◽  
Remote Sensing Images ◽  
Residual Network ◽  
Scale Invariant ◽  
Registration Method ◽  
Sensing Applications ◽  
Feature Based

Accurate registration for multisource high-resolution remote sensing images is an essential step for various remote sensing applications. Due to the complexity of the feature and texture information of high-resolution remote sensing images, especially for images covering earthquake disasters, feature-based image registration methods need a more helpful feature descriptor to improve the accuracy. However, traditional image registration methods that only use local features at low levels have difficulty representing the features of the matching points. To improve the accuracy of matching features for multisource high-resolution remote sensing images, an image registration method based on a deep residual network (ResNet) and scale-invariant feature transform (SIFT) was proposed. It used the fusion of SIFT features and ResNet features on the basis of the traditional algorithm to achieve image registration. The proposed method consists of two parts: model construction and training and image registration using a combination of SIFT and ResNet34 features. First, a registration sample set constructed from high-resolution satellite remote sensing images was used to fine-tune the network to obtain the ResNet model. Then, for the image to be registered, the Shi_Tomas algorithm and the combination of SIFT and ResNet features were used for feature extraction to complete the image registration. Considering the difference in image sizes and scenes, five pairs of images were used to conduct experiments to verify the effectiveness of the method in different practical applications. The experimental results showed that the proposed method can achieve higher accuracies and more tie points than traditional feature-based methods.

Flaw Detection Using Image Registration and Fusion Techniques

2008 ◽  
Author(s):  
Yiqiang Zhou ◽  
L. L. Hoberock
Keyword(s):  
Image Registration ◽  
Flaw Detection ◽  
Inspection System ◽  
Specular Reflections ◽  
Lighting Conditions ◽  
Image Registration Algorithm ◽  
Surface Flaws ◽  
Feature Based ◽  
New Feature ◽  
Polished Metal

The inspection of polished metal contoured surfaces, such as silverware pieces, is much more difficult than for a flat surface, considering the complex curved surface, reflections, and shadows. It is hard to detect flaws when they overlap with shadows and specular reflections, which is typically the case. In this paper, this problem is solved using image registration and image fusion techniques. A continuous-inspection system is developed to take two images sequentially under different lighting conditions when the object is passing under the camera. Shadows and reflections shift, while the flaws do not. From the differences of these two images, flaws can be distinguished from shadows and reflections, and the lost information due to specular reflections can be made up. Fused images without specular reflections were obtained, and a new feature based image registration algorithm is developed to compare these two fused images to detect the surface flaws.

scholarly journals A Novel Coarse-to-Fine Scheme for Remote Sensing Image Registration Based on SIFT and Phase Correlation

2019 ◽  
Vol 11 (15) ◽  
pp. 1833 ◽  
Author(s):  
Han Yang ◽  
Xiaorun Li ◽  
Liaoying Zhao ◽  
Shuhan Chen
Keyword(s):  
Remote Sensing ◽  
Image Registration ◽  
Phase Correlation ◽  
Mean Square ◽  
Extended Phase ◽  
Registration Method ◽  
Coarse Registration ◽  
Feature Based ◽  
Coarse To Fine ◽  
Fine Registration

Automatic image registration has been wildly used in remote sensing applications. However, the feature-based registration method is sometimes inaccurate and unstable for images with large scale difference, grayscale and texture differences. In this manuscript, a coarse-to-fine registration scheme is proposed, which combines the advantage of feature-based registration and phase correlation-based registration. The scheme consists of four steps. First, feature-based registration method is adopted for coarse registration. A geometrical outlier removal method is applied to improve the accuracy of coarse registration, which uses geometric similarities of inliers. Then, the sensed image is modified through the coarse registration result under affine deformation model. After that, the modified sensed image is registered to the reference image by extended phase correlation. Lastly, the final registration results are calculated by the fusion of the coarse registration and the fine registration. High universality of feature-based registration and high accuracy of extended phase correlation-based registration are both preserved in the proposed method. Experimental results of several different remote sensing images, which come from several published image registration papers, demonstrate the high robustness and accuracy of the proposed method. The evaluation contains root mean square error (RMSE), Laplace mean square error (LMSE) and red–green image registration results.

HYBRID REGISTRATION OF CORRESPONDING MAMMOGRAM IMAGES FOR AUTOMATIC DETECTION OF BREAST CANCER

2007 ◽  
Vol 19 (06) ◽  
pp. 359-374 ◽  
Author(s):  
Yih-Chih Chiou ◽  
Chern-Sheng Lin ◽  
Cheng-Yu Lin
Keyword(s):  
Breast Cancer ◽  
Image Registration ◽  
Early Detection ◽  
Feature Matching ◽  
Automatic Detection ◽  
Spatial Transformation ◽  
Registration Method ◽  
Feature Based ◽  
Mammogram Images ◽  
Hybrid Registration

Mammogram registration is a critical step in automatic detection of breast cancer. Much research has been devoted to registering mammograms using either feature-matching or similarity measure. However, a few studies have been done on combining these two methods. In this research, a hybrid mammogram registration method for the early detection of breast cancer is developed by combining feature-based and intensity-based image registration techniques. Besides, internal and external features were used simultaneously during the registration to obtain a global spatial transformation. The experimental results indicates that the similarity between the two mammograms increases significantly after a proper registration using the proposed TPS-registration procedures.

scholarly journals Automatic Image Registration

10.29007/kqbg ◽  
2018 ◽  
Author(s):  
Mehfuza Holia ◽  
Zankhana Shah
Keyword(s):  
Image Registration ◽  
Linear Transformation ◽  
User Interaction ◽  
Scale Space ◽  
Consensus Algorithm ◽  
Registration Method ◽  
Harris Corner ◽  
Feature Based ◽  
Local Gradient ◽  
Maximal Suppression

The automatic construction of large, high-resolution multi view image registration is an active area of research in the fields of image processing. Multiview image registration can be used for many different applications. The most traditional application is the construction of large aerial and satellite photographs from collections of images, construction of virtual travel etc. This proposed Automatic feature based image registration method does not allow any user interaction and perform all registration steps automatically. Here the matching points are found automatically using local feature detector i.e. harris corner detector which find invariant features using feature descriptors as oriented patches. For estimating homography between detected features of images to be registered, Homography estimator i.e. modified RANSAC (RANdom SAmple Consensus) algorithm, and direct linear transformation algorithm is used. Here features are located at Harris corners (new improved) in discrete scale-space and oriented using a blurred local gradient. To have better spatial distribution of features, adaptive non- maximal suppression algorithm is used.Feature matching are achieved using RANSAC which also uses DLT (Direct Linear Transformation) and warping is applied to achieve final registered image. This proposed algorithm can be applied for the series of images that may or may not be in the same alignment as per desired output image, thus mainly scaling, rotation and image transformation must be applied to get proper registered image.

Sign in / Sign up

Export Citation Format

Share Document