Electrocardiogram signal analysis is based on detecting a fiducial point consisting of the onset, offset, and peak of each waveform. The accurate diagnosis of arrhythmias depends on the accuracy of fiducial point detection. Detecting the onset and offset fiducial points is ambiguous because the feature values are similar to those of the surrounding sample. To improve the accuracy of this paper’s fiducial point detection, the signal is represented by a small number of vertices through a curvature-based vertex selection technique using polygonal approximation. The proposed method minimizes the number of candidate samples for fiducial point detection and emphasizes these sample’s feature values to enable reliable detection. It is also sensitive to the morphological changes of various QRS complexes by generating an accumulated signal of the amplitude change rate between vertices as an auxiliary signal. To verify the superiority of the proposed algorithm, error distribution is measured through comparison with the QT-DB annotation provided by Physionet. The mean and standard deviation of the onset and the offset were stable as −4.02±7.99 ms and −5.45±8.04 ms, respectively. The results show that proposed method using small number of vertices is acceptable in practical applications. We also confirmed that the proposed method is effective through the clustering of the QRS complex. Experiments on the arrhythmia data of MIT-BIH ADB confirmed reliable fiducial point detection results for various types of QRS complexes.
This paper uses a Directional Filter Bank (DFB) and adaptive multilevel thresholding for TFT-LCD panel inspection. Line-scan and area-scan cameras are used to acquire images of TFT-LCD panels with different resolutions. Thereafter, a DFB is used to find line defects in low-resolution images, while adaptive multilevel thresholding is employed to detect line defects on the LCD panels. LCD panel defects can be defined as the pixels that have a non-uniform bright region compared to the background region. However, the intensities of LCD panels are inherently non-uniform, the pattern-variation different even within the same model, and defects usually faint and hard to discern, making the detection problem all the more difficult. Accordingly, the present study detects line-type defects by using a DFB and multilevel threshold to extract features. In a low-resolution image, a DFB that can find directional information is used to identify a line-shape abnormal region. Meanwhile, in a high-resolution image, a multilevel thresholding technique based on statistical approach is employed to detect abnormal line defects that are brighter or darker than the surrounding pixels. The effectiveness of the proposed DFB and multilevel thresholding technique is tested through the experiments using real LCD panels.
In the manufacturing process of a LCM(Liquid Crystal Display Module), many spot-type defects can be occurred on the surface of LCM due to various physical factors. The existence and pattern of such defects are very important in determining whether the LCM is normal or not. To enhance the accuracy and reproducibility of LCD inspection, this paper introduces an automated inspection method using a computer vision technique. The LCM defects are classified into macro-defects and micro-defects. One is detected by using a macro-view area camera and the other by using six micro-view line cameras. An adaptive multilevel thresholding method using statistical characteristics of local block is proposed for a macro-view image while the detection method for a micro-view images composed of R, G, B sub-cells involves a pattern elimination technique using the pixel difference and adaptive multilevel thresholding. The proposed inspection system is tested using many real LCMs having different defects, and the resulting performance confirms the effectiveness of the proposed algorithm.
Recently, there have been many studies on the automatic extraction of facial information using machine learning. Age estimation from front face images is becoming important, with various applications. Our proposed work is based on the binary classifier, which only determines whether two input images are clustered in a similar class, and trains the convolutional neural networks (CNNs) model using the deep metric learning method based on the Siamese network. To converge the results of the training Siamese network, two classes, for which age differences are below a certain level of distance, are considered as the same class, so the ratio of positive database images is increased. The deep metric learning method trains the CNN model to measure similarity based on only age data, but we found that the accumulated gender data can also be used to compare ages. From this experimental fact, we adopted a multi-task learning approach to consider the gender data for more accurate age estimation. In the experiment, we evaluated our approach using MORPH and MegaAge-Asian datasets, and compared gender classification accuracy only using age data from the training images. In addition, from the gender classification, we found that our proposed architecture, which is trained with only age data, performs age comparison by using the self-generated gender feature. The accuracy enhancement by multi-task learning, for the simultaneous consideration of age and gender data, is discussed. Our approach results in the best accuracy among the methods based on deep metric learning on MORPH dataset. Additionally, our method is also the best results compared with the results of the state of art in terms of age estimation on MegaAge Asian and MORPH datasets.
This paper presents a pan-tilt-zoom (PTZ) camera-based displacement measurement system, specially based on the perspective distortion correction technique for the early detection of building destruction. The proposed PTZ-based vision system rotates the camera to monitor the specific targets from various distances and controls the zoom level of the lens for a constant field of view (FOV). The proposed approach adopts perspective distortion correction to expand the measurable range in monitoring the displacement of the target structure. The implemented system successfully obtains the displacement information in structures, which is not easily accessible on the remote site. We manually measured the displacement acquired from markers which is attached on a sample of structures covering a wide geographic region. Our approach using a PTZ-based camera reduces the perspective distortion, so that the improved system could overcome limitations of previous works related to displacement measurement. Evaluation results show that a PTZ-based displacement sensor system with the proposed distortion correction unit is possibly a cost effective and easy-to-install solution for commercialization.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.