• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.4
• /
• pp.95-105
• /
• 2021

Road surface damage detection is essential for a comfortable driving environment and the prevention of safety accidents. Road management institutes are using automated technology-based inspection equipment and systems. As one of these automation technologies, a sensor to detect road surface damage plays an important role. For this purpose, several studies on sensors using deep learning have been conducted in recent years. Road images and label images are needed to develop such deep learning algorithms. On the other hand, considerable time and labor will be needed to secure label images. In this paper, the adversarial learning method, one of the semi-supervised learning techniques, was proposed to solve this problem. For its implementation, a lightweight deep neural network model was trained using 5,327 road images and 1,327 label images. After experimenting with 400 road images, a model with a mean intersection over a union of 80.54% and an F1 score of 77.85% was developed. Through this, a technology that can improve recognition performance by adding only road images was developed to learning without label images and is expected to be used as a technology for road surface management in the future.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.77-84
• /
• 2022

In this paper, we propose a Label Reassignment Strategy to improve the performance of an object detection algorithm. Our approach involves two stages: an inference stage and an assignment stage. In the inference stage, we perform multi-scale inference with predefined scale sizes on a trained model and re-infer masked images to obtain robust classification results. In the assignment stage, we calculate the IoU between bounding boxes to remove duplicates. We also check box and class occurrence between the detection result and annotation label to re-assign the dominant class type. We trained the YOLOX-L model with the re-annotated dataset to validate our strategy. The model achieved a 3.9% improvement in mAP and 3x better performance on AP_S compared to the model trained with the original dataset. Our results demonstrate that the proposed Label Reassignment Strategy can effectively improve the performance of an object detection model.

• Imaging Science in Dentistry
• /
• v.52 no.4
• /
• pp.383-391
• /
• 2022

Purpose: Periodontitis, the most prevalent chronic inflammatory condition affecting teeth-supporting tissues, is diagnosed and classified through clinical and radiographic examinations. The staging of periodontitis using panoramic radiographs provides information for designing computer-assisted diagnostic systems. Performing image segmentation in periodontitis is required for image processing in diagnostic applications. This study evaluated image segmentation for periodontitis staging based on deep learning approaches. Materials and Methods: Multi-Label U-Net and Mask R-CNN models were compared for image segmentation to detect periodontitis using 100 digital panoramic radiographs. Normal conditions and 4 stages of periodontitis were annotated on these panoramic radiographs. A total of 1100 original and augmented images were then randomly divided into a training (75%) dataset to produce segmentation models and a testing (25%) dataset to determine the evaluation metrics of the segmentation models. Results: The performance of the segmentation models against the radiographic diagnosis of periodontitis conducted by a dentist was described by evaluation metrics(i.e., dice coefficient and intersection-over-union [IoU] score). MultiLabel U-Net achieved a dice coefficient of 0.96 and an IoU score of 0.97. Meanwhile, Mask R-CNN attained a dice coefficient of 0.87 and an IoU score of 0.74. U-Net showed the characteristic of semantic segmentation, and Mask R-CNN performed instance segmentation with accuracy, precision, recall, and F1-score values of 95%, 85.6%, 88.2%, and 86.6%, respectively. Conclusion: Multi-Label U-Net produced superior image segmentation to that of Mask R-CNN. The authors recommend integrating it with other techniques to develop hybrid models for automatic periodontitis detection.

• Food Science of Animal Resources
• /
• v.43 no.2
• /
• pp.232-244
• /
• 2023

We investigated the effects of different phosphate replacements on the quality of ground pork products cured with sodium nitrite or radish powder to determine their potential for achieving clean-label pork products. The experimental design was a 2×5 factorial design. For this purpose, the ground meat mixture was assigned into two groups, depending on nitrite source. Each group was mixed with 0.01% sodium nitrite or 0.4% radish powder together with 0.04% starter culture, and then processed depending on phosphate replacement [with or without 0.5% sodium tripolyphosphate; STPP (+), STPP (-), 0.5% oyster shell calcium (OSC), 0.5% citrus fiber (CF), or 0.5% dried plum powder (DPP)]. All samples were cooked, cooled, and stored until analysis within two days. The nitrite source had no effect on all dependent variables of ground pork products. However, in phosphate replacement treatments, the STPP (+) and OSC treatments had a higher cooking yield than the STPP (-), CF, or DPP treatments. OSC treatment was more effective for lowering total fluid separation compared to STPP (-), CF, or DPP treatments, but had a higher percentage than STPP (+). The STPP (+) treatment did not differ from the OSC or CF treatments for CIE L^* and CIE a^*. Moreover, no differences were observed in nitrosyl hemochrome content, lipid oxidation, hardness, gumminess, and chewiness between the OSC and STPP (+) treatments. In conclusion, among the phosphate replacements, OSC addition was the most suitable to provide clean-label pork products cured with radish powder as a synthetic nitrite replacer.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.83-88
• /
• 2024

In this research, we propose a Semi-Supervised learning based railroad surface defect detection method. The Resnet50 model, pretrained on ImageNet, was employed for the training. Data without labels are randomly selected, and then labeled to train the ResNet50 model. The trained model is used to predict the results of the remaining unlabeled training data. The predicted values exceeding a certain threshold are selected, sorted in descending order, and added to the training data. Pseudo-labeling is performed based on the class with the highest probability during this process. An experiment was conducted to assess the overall class classification performance based on the initial number of labeled data. The results showed an accuracy of 98% at best with less than 10% labeled training data compared to the overall training data.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.47-73
• /
• 2023

Management decision-making based on artificial intelligence(AI) plays an important role in helping decision-makers. Business decision-making centered on AI is evaluated as a driving force for corporate growth. AI-based on accurate analysis techniques could support decision-makers in making high-quality decisions. This study proposes an effective decision-making method with the application of multi-label feature selection. In this regard, We present a CFS-BR (Correlation-based Feature Selection based on Binary Relevance approach) that reduces data sets in high-dimensional space. As a result of analyzing sample data and empirical data, CFS-BR can support efficient decision-making by selecting the best combination of meaningful attributes based on the Best-First algorithm. In addition, compared to the previous multi-label feature selection method, CFS-BR is useful for increasing the effectiveness of decision-making, as its accuracy is higher.

• Fashion & Textile Research Journal
• /
• v.20 no.3
• /
• pp.331-342
• /
• 2018

This paper enables stakeholders involved in textile industry to gain an overview of standards used for care labelling and help establish a common standard that could be used as a universal standard. This study provides a comprehensive and detailed analytical study of care labelling standards adopted by common countries in the textile market. It was found that the development of a universal system for care labeling could enhance the trade of textile articles and assist consumers in caring for textile articles. Universal care label systems could be characterized by two main features of inclusiveness and comprehensiveness. The range of instructions and symbols presented were found different among standards. Insignificant differences in symbols' shapes were found between standards for bleaching, ironing and professional cleaning. The washing process had the widest variety of instructions; in addition, options were provided by stated standards. Different meanings were found for similar shapes in some tumble drying symbols. The study findings show the importance of enhancing text based standards or the development of an understandable format across as many cultures as possible. The unification of symbols and meanings may be needed to provide global consumers consistent guidance. The efficiency of a detailed standard that provides and covers a wide range of instructions is an important aspect. The visibility and practicality of offering variable options/symbols in one standard is an important aspect for developing a universal care label system.

• IE interfaces
• /
• v.15 no.2
• /
• pp.152-158
• /
• 2002

The explosive growth of the internet traffic in the last few years has imposed tremendous stress on today's routers, particularly in the core network. Recently, ATM LSRs(Label Switching Router) are potentially capable of providing the highest forwarding capacity in the backbone Internet network. VC merging is a mechanism in an ATM LSR that allows many IP routes to be mapped to the same VC label, and provides a scalable mapping method that can support thousands of destinations. VC merging requires reassembly buffers so that cells belonging to different packets intended for the same destination do not interleave with each other. In this study, we propose an architecture of the ATM LSR which supports VC merging. We propose traffic control scheme called APD(Active Packet Discard) algorithm so that predicts and controls the congestion of the Internet traffic effectively. We study the performance of this algorithm using simulation.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.5
• /
• pp.1053-1059
• /
• 2012

Barcode labels are being widely used for identifying products since they are cheap and easy to use. As the barcode labels are massively produced by seal printing, some labels have defects such as poor printing quality or data mismatch between barcode and the text. Barcode read errors and business errors caused by defected barcodes result in delay in logistics and increased processing costs. In this paper, we propose an on-line barcode verification system that uses image processing technique to verify the quality of labels at the production stage. The proposed system captures label images through the vision camera and then checks the print quality and verifies the combination of barcodes and texts in a label. If any defected label is found, the proposed system gives alarm signals and marks the defected labels so that they are removed at early stage of the production.

• Journal of the Korean Society of Industry Convergence
• /
• v.23 no.3
• /
• pp.481-489
• /
• 2020

Safety and security during the handling of hazardous materials is a great concern for anyone in the field. One driving point in the security field is the ability to detect the source of the danger and take action against it as quickly as possible. Via the usage of a fully convolutional network, it is possible to create the label map of an input image, indicating what object is occupying the specific area of the image. This research employs the usage of U-net, which was constructed in biomedical field segmentation to segment cells, instead of the original FCN. One of the challenges that this research faces is the availability of ground truth with precise labeling for the dataset. Testing the network after training resulted in some images where the network pronounces even better detail than the expected label map. With better detailed label map, the network might be able to produce better segmentation is something to be studied in further research.