WLWei-Yang Lin

Wei-Yang Lin

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wei-Yang Lin has a total of 56 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Wavelet-Transformed Frequency Linked Attention with Selective Hierarchy for Abdominal Organ Segmentation

    by Chung-Ming Lo, Kai-Chun Huang, Chuan-Hsien Chen, Peng-Hsiang Hung, Wei-Yang Lin

    The clinical use of computed tomography (CT) scans has been steadily rising due to their ability to provide detailed three-dimensional (3D) representations of organs, along with advantages such as speed and high resolution. With CT, physicians can identify potential diseased organs and plan appropriate treatments. However, accurate quantitative evaluation is time-consuming, and precise automatic segmentation can significantly enhance the effectiveness of CT scans. Frequency linked attention with selective hierarchy (FLASH) was introduced as a novel deep learning architecture for multi-organ segmentation in abdominal CT scans. FLASH incorporated the 3D discrete wavelet transform into Transformer blocks as the backbone of the encoder. By distinguishing 3D frequency bands, the network addressed the challenge of unclear organ boundaries in abdominal CT scans caused by low contrast. Two-directional skip connections were introduced to link the multi-scale frequency features into the bottleneck and to assign adaptive weights to frequency components using attention mechanisms. By training from scratch on the organ dataset with five-fold validation, FLASH achieved the highest dice similarity coefficient = 0.826, normalized surface distance = 0.698 with the lowest standard deviation of dice similarity coefficient = 0.034, standard deviation of normalized surface distance = 0.046 compared to other networks in the experiments. With better segmentation results, FLASH had fewer parameters (96.86 M vs. 139.45 M) and computation time (36.3 h vs. 50.4 h) compared to Swin UNETR, which is more suitable in clinical use with limited resources and waiting time. Our code can be found at https://github.com/jorden0721/FLASH-UNETR.git

  • Development of a Smartphone-Based Inventory Management System for Emergency Carts

    by Chia-Hui Liu, Nian-Yin Wu, Che-Chia Liu, Wen-Yin Kuo, Tzu-Chia Lin, Wei-Yang Lin

    Inventory management for emergency carts is one of the routine tasks in hospitals. It is highly desirable to simplify the workflow of the inventory task since healthcare staffs always work under high pressure and heavy workload. In this study, we exploit computer vision technology to develop an automated inventory management system for emergency carts. We have conducted a user study evaluate our proposed system. The subjects are 37 nurses from the internal medicine department and the pediatrics department of Chia-Yi Christian Hospital. The time spending on the inventory task before and after using our proposed system are compared. We also evaluate several state-of-the-art object detection algorithms (YOLOv4, YOLOv5, YOLOv7, and YOLOv5-OBB) for the task of automatic drug counting. We collect 500 images to train these object detection models and evaluate their accuracy. After using the proposed system, the time spent on the inventory task is reduced from 9.59 min to 5.32 min in average. The user study also indicates that the average workload score of the nurses is reduced from 3.81 to 2.70. For the evaluation of automatic drug counting, our proposed hybrid approach, which combines YOLOv5-OBB and YOLOv7, yields the highest accuracy. The resulting over detection rate and missed detection rate are 1.29% and 3.27%, respectively. In this study, we demonstrate that smartphone-based inventory management system using computer vision technology, specifically YOLO series object detectors, can effectively streamline inventory workflow and reduce the workload for healthcare personnel.

  • Open Access

    Entropy-Boosted Adversarial Patch for Concealing Pedestrians in YOLO Models

    by Chih-Yang Lin, Tun-Yu Huang, Hui-Fuang Ng, Wei-Yang Lin, Isack Farady

    In recent years, rapid advancements in hardware and deep learning technologies have paved the way for the extensive integration of image recognition and object detection into daily applications. As reliance on deep learning grows, so do concerns about the vulnerabilities of deep neural networks, emphasizing the need to address potential security issues. This research unveils the Entropy-boosted Loss, a novel loss function tailored to generate adversarial patches resembling potted plants. Specifically designed for the YOLOV2, YOLOV3, and YOLOV4 object detectors, these patches obscure the detectors’ ability to identify individuals. By enhancing the uncertainty in class probability, a person wearing an adversarial patch crafted using our proposed loss function becomes less identifiable by YOLO detectors, achieving the desired adversarial effect. This underscores the significance of comprehending the vulnerabilities of YOLO models to adversarial attacks, particularly for individuals aiming to obscure their presence from camera detection. Our experiments, conducted using the INRIA person dataset and under real-time network camera conditions, confirm the effectiveness of our method. Moreover, our technique demonstrates substantial success in virtual try-on environments.


  • Open Access

    Moving Object Detection for Complex Scenes by Merging BG Modeling and Deep Learning Method

    by Chih-Yang Lin, Han-Yi Huang, Wei-Yang Lin, Hui-Fuang Ng, Kahlil Muchtar, Nadhila Nurdin

    In recent years, many studies have attempted to use deep learning for moving object detection. Some research also combines object detection methods with traditional background modeling. However, this approach may run into some problems with parameter settings and weight imbalances. In order to solve the aforementioned problems, this paper proposes a new way to combine ViBe and Faster-RCNN for moving object detection. To be more specific, our approach is to confine the candidate boxes to only retain the area containing moving objects through traditional background modeling. Furthermore, in order to make the detection able to more accurately filter out the static object, the probability of each region proposal then being retained. In this paper, we compare four famous methods, namely GMM and ViBe for the traditional methods, and DeepBS and SFEN for the deep learning-based methods. The result of the experiment shows that the proposed method has the best overall performance score among all methods. The proposed method is also robust to the dynamic background and environmental changes and is able to separate stationary objects from moving objects. Especially the overall F-measure with the CDNET 2014 dataset (like in the dynamic background and intermittent object motion cases) was 0,8572.


  • Open Access

    Invisible Adversarial Attacks on Deep Learning-Based Face Recognition Models

    by Chih-Yang Lin, Feng-Jie Chen, Hui-Fuang Ng, Wei-Yang Lin

    Deep learning technology has grown rapidly in recent years and achieved tremendous success in the field of computer vision. At present, many deep learning technologies have been applied in daily life, such as face recognition systems. However, as human life increasingly relies on deep neural networks, the potential harms of neural networks are being revealed, particularly in terms of deep neural network security. More and more studies have shown that existing deep learning-based face recognition models are vulnerable to attacks by adversarial samples, resulting in misjudgments that could have serious consequences. However, existing adversarial face images are rather easy to identify with the naked eye, so it is difficult for attackers to carry out attacks on face recognition systems in practice. This paper proposes a method for generating adversarial face images that are indistinguishable from the source images based on facial landmark detection and superpixel segmentation. First, the eyebrows, eyes, nose, and mouth regions are extracted from the face image using a facial landmark detection algorithm. Next, the superpixel segmentation algorithm is used to include the pixels neighboring the extracted facial landmarks with similar pixel values. Lastly, the segmented regions are used as masks to guide existing attack methods to insert adversarial noise within the masked areas. Experimental results show that our method can generate adversarial samples with high Structural Similarity Index Measure (SSIM) values at the cost of a small percentage of attack success rate. In addition, to simulate real-time physical attacks, printouts of the adversarial images generated by the proposed method are presented to the face recognition system via a camera and are still able to fool the face recognition model. Experimental results indicated that the proposed method can successfully perform adversarial attacks on face recognition systems in real-world scenarios.


  • Open Access

    A Novel Computer-Aided-Diagnosis System for Breast Ultrasound Images Based on BI-RADS Categories

    by Yi-Wei Chang, Yun-Ru Chen, Chien-Chuan Ko, Wei-Yang Lin, Keng-Pei Lin

    The breast ultrasound is not only one of major devices for breast tissue imaging, but also one of important methods in breast tumor screening. It is non-radiative, non-invasive, harmless, simple, and low cost screening. The American College of Radiology (ACR) proposed the Breast Imaging Reporting and Data System (BI-RADS) to evaluate far more breast lesion severities compared to traditional diagnoses according to five-criterion categories of masses composition described as follows: shape, orientation, margin, echo pattern, and posterior features. However, there exist some problems, such as intensity differences and different resolutions in image acquisition among different types of ultrasound imaging modalities so that clinicians cannot always identify accurately the BI-RADS categories or disease severities. To this end, this article adopted three different brands of ultrasound scanners to fetch breast images for our experimental samples. The breast lesion was detected on the original image using preprocessing, image segmentation, etc. The breast tumor’s severity was evaluated on the features of the breast lesion via our proposed classifiers according to the BI-RADS standard rather than traditional assessment on the severity; i.e., merely using benign or malignant. In this work, we mainly focused on the BI-RADS categories 2–5 after the stage of segmentation as a result of the clinical practice. Moreover, several features related to lesion severities based on the selected BI-RADS categories were introduced into three machine learning classifiers, including a Support Vector Machine (SVM), Random Forest (RF), and Convolution Neural Network (CNN) combined with feature selection to develop a multi-class assessment of breast tumor severity based on BI-RADS. Experimental results show that the proposed CAD system based on BI-RADS can obtain the identification accuracies with SVM, RF, and CNN reaching 80.00%, 77.78%, and 85.42%, respectively. We also validated the performance and adaptability of the classification using different ultrasound scanners. Results also indicate that the evaluations of F-score based on CNN can obtain measures higher than 75% (i.e., prominent adaptability) when samples were tested on various BI-RADS categories.


  • Moving Object Detection Through Image Bit-Planes Representation Without Thresholding

    by Chih-Yang Lin, Kahlil Muchtar, Wei-Yang Lin, Zhi-Yao Jian

    Background subtraction is an example of a moving object detection technique that uses machine vision systems. Conventional moving object detection methods need complicated thresholds for background modeling to address changes in illumination. This paper proposes a novel background modeling approach without thresholding based on a bit-planes method, which fully utilizes color characteristics through spatial and temporal-based improvement. The proposed idea is effective and efficiently solving for shadow disturbance and brightness changes. We evaluate our proposed method using several challenging indoor and outdoor sequences from the CDNET 2014 dataset. The experiments show that the proposed idea typically achieves a higher rate of detection accuracy than those of the current state-of-the-art approaches.


  • Temporally Coherent Illumination Normalization for Indocyanine Green Video Angiography

    by Wei-Yang Lin, Shu-Fu Chou, Chia-Ling Tsai, Shih-Jen Chen

    Indocyanine green (ICG) angiography is an imaging method for doctors to observe choroidal abnormalities in human eyes. The ICG angiograms typically exhibit inhomogeneous illumination, which poses serious difficulties for the development of computer-aided diagnostic tools. In this paper, we propose a novel illumination normalization method to alleviate the inhomogeneous illumination in ICG video angiograms. In particular, we first align the viewpoint of the input ICG video angiogram using an image registration method. Then, we acquire temporal information using time-dependent intrinsic image and compute the corresponding illumination image. Finally, we correct inhomogeneous illumination from the illumination image by estimating contrast and luminosity distortion. We have conducted extensive evaluation using ICG video angiograms of 60 patients. Two video quality assessment methods are utilized to evaluate the performance of our proposed illumination normalization method. The results show that our proposed method can help improve the visual quality of ICG video angiogram. Visual evaluation by a human expert also confirms that our method yields better illumination normalization results.