Surface quality inspection is a crucial step in industrial manufacturing. However, it is challenging to collect an adequate quantity of abnormal samples in practice. Supervised methods require sample annotation, which is costly, so unsupervised methods that are high-speed and low-cost are more suitable for industrial applications. Among the current unsupervised methods, embedding-similarity methods haven shown excellent performance, but most of them do not preprocess the images and directly use convolutional neural networks to extract image features. While in actual scenarios, image can have some degree of offset or rotation due to machine variations. Therefore, this paper proposes a new patch distribution framework for anomaly detection, specifically a novel image alignment module is proposed to enhance the utility of the model. Image alignment reduces the dense distance between pixels during training, enabling more precise learning of the feature distribution of normal samples and reduce false positives during testing. In addition, in the feature extraction stage, the middle layer of the network is selected to extract features and establish embedding connections. This not only enhances the model’s precision but also reduces its memory requirements. Experiments on the publicly available datasets MVTec AD and BeanTech AD show that our proposed new framework achieves better performance than other baseline models.
At present, the surface defect detection task of mobile phone lens still suffers from low detection accuracy and slow detection speed. To solve these problems, this paper proposes a real-time and effective algorithm based on YOLOv4. Firstly, we combine the cross stage partial block of YOLOv4 and convolutional block attention module, introducing channel attention and spatial attention to learn discriminative features of defects. Secondly, due to the limited differential characteristics of small defects, a novel feature fusion network is designed to further integrate the shallow details with deep semantics. Finally, in order to further boost the detection speed without reducing in accuracy, the proposed model is refined by using the structure tailoring strategies. Compared with YOLOv4 algorithm, our algorithm improves average precision (AP) of linear defect by 2.11%, reduces model size by 13.3% and parameters by 14.14%. Besides, our algorithm improves frames per second (FPS) by 50% and achieves the real-time performance for industrial production. Compared with other algorithms, our algorithm has superior performance in both AP and FPS.
In order to realize the accurate and quick positioning of pulmonary nodules in hundreds of two-dimensional CT chest images and reduce the burden of radiologist, the paper proposes a modified faster R-CNN method to improve the performance of the pulmonary nodule detection. Firstly, data enhancement technology is adopted to expand the dataset. Secondly, the image is fed into VGG-16 with de-convolution to extract the shared convolution features. Then, the shared convolution feature is sent to the region proposal network (RPN) to output candidate lung nodule region. Finally, the candidate lung nodule region and the previous shared convolution features are input into ROI pooling layer at the same time, and the characteristics of the corresponding candidate area are extracted. Through the connection layer, a multi task classifier is used to position the regression of the candidate region. According to the features of complex chest image background, large detecting object range and relatively small size of pulmonary nodule compared with natural objects, we design a smaller anchor box to accommodate changes in lung nodule size. In order to get the more accurate description of the characteristics of pulmonary nodules, we add a de-convolution layer with 4, 4, 2 and 512 for nuclear size, step size, filling size and number of nuclei respectively after the last layer of VGG-16 network conv5_3 , resulting in a higher de-convolution feature resolution. Finer granularity can be restored compared with the original feature map. The experimental results show that the average detection accuracy is up by 6.9 percentage points compared with the original model. This model can well detect solitary pulmonary nodules and pulmonary nodules and small nodules, showing certain clinical significance for early screening of lung cancer.
Lung cancer is the leading cause of cancer-related deaths among men. In this paper, we propose a pulmonary nodule detection method for early screening of lung cancer based on the improved AlexNet model. In order to maintain the same image quality as the existing B/S architecture PACS system, we convert the original CT image into JPEG format image by analyzing the DICOM file firstly. Secondly, in view of the large size and complex background of CT chest images, we design the convolution neural network on basis of AlexNet model and sparse convolution structure. At last we train our models on the software named DIGITS which is provided by NVIDIA. The main contribution of this paper is to apply the convolutional neural network for the early screening of lung cancer and improve the screening accuracy by combining the AlexNet model with the sparse convolution structure. We make a series of experiments on the chest CT images using the proposed method, of which the sensitivity and specificity indicates that the method presented in this paper can effectively improve the accuracy of early screening of lung cancer and it has certain clinical significance at the same time.
In order to repair the boundary depressions caused by juxtapleural nodules and improve the lung segmentation accuracy, we propose a new boundary correction method for lung parenchyma. Firstly, the top-hat filter is used to enhance the image contrast; Secondly, we employ the Ostu algorithm for image binarization; Thirdly, the connected component labeling algorithm is utilized to remove the main trachea; Fourthly, the initial mask image is obtained by morphological region filling algorithm; Fifthly, the boundary tracing algorithm is applied to extract the initial lung contour; Afterwards, we design a sudden change degree algorithm to modify the initial lung contour; Finally, the complete lung parenchyma image is obtained. The novelty is that sudden change degree algorithm can detect the inflection points more accurately than other methods, which contributes to repairing lung contour efficiently. The experimental results show that the proposed method can incorporate the juxtapleural nodules into the lung parenchyma effectively, and the precision is increased by 6.46% and 2.72% respectively compared with the other two methods, providing favorable conditions for the accurate detection of pulmonary nodules and having important clinical value.
The de-noising effect of many methods depends on the accuracy of the noise variance estimation. In this paper, we propose an effective algorithm for the noise variance estimation in shearlet domain. Firstly, the noisy image is decomposed into the low-frequency sub-band coefficients and multi-directional high-frequency sub-band coefficients based on the shearlet transform. Secondly, based on the high-frequency sub-band coefficients, the value of the noise variance is estimated using the Median Absolute Deviation (MAD) method. Thirdly, we choose some variance candidates in the neighborhood of the estimated value, and calculate the Residual Autocorrelation Power (RAP) of every variance candidate based on the Bayesian maximum a posteriori estimation (MAP) method. Finally, the accuracy of the noise variance estimation is improved using the residual autocorrelation power. A range of experiments demonstrate that the proposed method outperforms the traditional MAD method. The accuracy of the noise variance estimation has increased by 91.2% compared with the MAD method.
Low-dose CT (LDCT) scanning is a potential way to reduce the radiation exposure of X-ray in the population. It is necessary to improve the quality of low-dose CT images. In this paper, we propose an effective algorithm for quantum noise removal in LDCT images using shearlet transform. Because the quantum noise can be simulated by Poisson process, we first transform the quantum noise by using anscombe variance stabilizing transform (VST), producing an approximately Gaussian noise with unitary variance. Second, the non-noise shearlet coefficients are obtained by adaptive hard-threshold processing in shearlet domain. Third, we reconstruct the de-noised image using the inverse shearlet transform. Finally, an anscombe inverse transform is applied to the de-noised image, which can produce the improved image. The main contribution is to combine the anscombe VST with the shearlet transform. By this way, edge coefficients and noise coefficients can be separated from high frequency sub-bands effectively. A number of experiments are performed over some LDCT images by using the proposed method. Both quantitative and visual results show that the proposed method can effectively reduce the quantum noise while enhancing the subtle details. It has certain value in clinical application.
In this paper, a curvelet-based noise suppression bilinear interpolation method for low-dose CT images is proposed. Curvelets provide a multidirectional and multiscale decomposition that has been mathematically shown to represent distributed discontinuities such as edges better than traditional wavelets. Because the traditional linear interpolation results in boundary fuzziness in interpolated images, combined with the advantages of curvelet transform, here we propose a curvelet-based modified bilinear interpolation to improve the accuracy of interpolation. Extensive experiments indicate that the proposed method can effectively improve the quality of the obtained target image based on low-dose CT images and the produced slice image is similar to original slice image.
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.