Automatic detection, localization and segmentation of nano-particles with deep learning in microscopy images
تشخیص خودکار ، بومی سازی و تقسیم نانو ذرات با یادگیری عمیق در تصاویر میکروسکوپی-2019
With the growing amount of high resolution microscopy images automatic nano-particle detection, shape analysis and size determination have gained importance for providing quantitative support that gives important information for the evaluation of the material. In this paper, we present a new method for detection of nanoparticles and determination of their shapes and sizes simultaneously with deep learning. The proposed method employs multiple output convolutional neural networks (MO-CNN) and has two outputs: first is the detection output that gives the locations of the particles and the other one is the segmentation output for providing the boundaries of the nano-particles. The final sizes of particles are determined with the modified Hough algorithm that runs on the segmentation output. The proposed method is tested and evaluated on a dataset containing 17 TEM images of Fe3O4 and silica coated nano-particles. Also, we compared these results with U-net algorithm which is a popular deep learning method. The experiments showed that the proposed method has 98.23% accuracy for detection and 96.59% accuracy for segmentation of nano-particles.
Keywords: Nano-particle | Deep learning | Object detection | MO-CNN | Hough transform
Quasi-autonomous bolt-loosening detection method using vision-based deep learning and image processing
روش تشخیص شل شدن شبه مستقل با استفاده از یادگیری عمیق مبتنی بر بینایی و پردازش تصویر-2019
In this study, a quasi-autonomous vision-based method is newly proposed for detecting loosened bolts in critical connections. The main idea of the approach is to estimate the rotational angles of bolts from the connection images by integrating deep learning technology with image processing techniques. Firstly, a regional convolutional neural network (RCNN)-based deep learning algorithm is developed to automatically detect and crop plausible bolts in the connection image. Also, the Hough line transform (HLT)-based image processing algorithm is designed to automatically estimate the bolt angles from the cropped bolt images. Secondly, the proposed vision-based approach is validated for bolt-loosening detection in a lab-scale girder connection using images captured by a smartphone camera. The accuracy of the RCNN-based bolt detector and the HLT-based bolt angle estimator are examined under different levels of perspective distortion and shooting distance. Finally, the practicality of the proposed vision-based method is verified on a real-scale girder bridge connection containing numerous bolts. The images of the connection are captured by an unmanned aerial vehicle and transferred to a computer where a quasi-autonomous bolt-loosening detection process is performed via the proposed algorithm. The experimental results demonstrate potentials of the proposed approach for quasi real-time bolt-loosening monitoring of large bolted connections. The results show that the perspective angle should not go beyond 40 degrees to ensure the accuracy of the detection results.
Keywords: Bolted connection | Bolt-loosening | Deep learning | CNN | Hough transform | Canny line detector | Bolt detection | Bolt rotation estimation