• The Journal of Korean Institute of Information Technology
• /
• v.17 no.5
• /
• pp.13-20
• /
• 2019

Recently, object detection technology based on CNN has been actively studied. Object detection technology is used as an important technology in autonomous vehicles, intelligent image analysis, and so on. In this paper, we propose a rotation change robust object detection system by applying MI-FL (Moment Invariant-Feature Layer) to SSD (Single Shot Multibox Detector) which is one of CNN-based object detectors. First, the features of the input image are extracted based on the VGG network. Then, a total of six feature layers are applied to generate bounding boxes by predicting the location and type of object. We then use the NMS algorithm to get the bounding box that is the most likely object. Once an object bounding box has been determined, the invariant moment feature of the corresponding region is extracted using MI-FL, and stored and learned in advance. In the detection process, it is possible to detect the rotated image more robust than the conventional method by using the previously stored moment invariant feature information. The performance improvement of about 4 ~ 5% was confirmed by comparing SSD with existing SSD and MI-FL.

• Journal of the Microelectronics and Packaging Society
• /
• v.30 no.4
• /
• pp.69-78
• /
• 2023

With the rapid growth of artificial intelligence, the demand for semiconductors is enormously increasing everywhere. To ensure the manufacturing quality and quantity simultaneously, the importance of automatic defect detection during the packaging process has been re-visited by adapting various deep learning-based methodologies into automatic packaging defect inspection. Deep learning (DL) models require a large amount of data for training, but due to the nature of the semiconductor industry where security is important, sharing and labeling of relevant data is challenging, making it difficult for model training. In this study, we propose a new framework for securing sufficient data for DL models with fewer computing resources through a divide-and-conquer approach. The proposed method divides high-resolution images into pre-defined sub-regions and assigns conditional labels to each region, then trains individual sub-regions and boundaries with boundary loss inducing the globally coherent and seamless images. Afterwards, full-size image is reconstructed by combining divided sub-regions. The experimental results show that the images obtained through this research have high efficiency, consistency, quality, and generality.

• Tunnel and Underground Space
• /
• v.31 no.5
• /
• pp.374-384
• /
• 2021

In this study, we propose a new approach for automatic fracture detection in CT scan images of rock specimens. This approach is built on top of two-stage object detection deep learning algorithm called Faster R-CNN with a major modification of using rotated bounding box. The use of rotated bounding box plays a key role in the future work to overcome several inherent difficulties of fracture segmentation relating to the heterogeneity of uninterested background (i.e., minerals) and the variation in size and shape of fracture. Comparing to the commonly used bounding box (i.e., axis-align bounding box), rotated bounding box shows a greater adaptability to fit with the elongated shape of fracture, such that minimizing the ratio of background within the bounding box. Besides, an additional benefit of rotated bounding box is that it can provide relative information on the orientation and length of fracture without the further segmentation and measurement step. To validate the applicability of the proposed approach, we train and test our approach with a number of CT image sets of fractured granite specimens with highly heterogeneous background and other rocks such as sandstone and shale. The result demonstrates that our approach can lead to the encouraging results on fracture detection with the mean average precision (mAP) up to 0.89 and also outperform the conventional approach in terms of background-to-object ratio within the bounding box.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.3
• /
• pp.65-72
• /
• 2020

The Internet of Things(IoT) is to build a hyper-connected society through interconnection, and on this basis, to improve the quality of life and productivity, including solving social problems, and to become the next growth engine for the nation. The open common eco-system pursued by the IoT can start with the under- standing of the word 'open'. The IoT can achieve the expected effect of lowering the barriers to entry of technology development, and in these changes, OSSW and OSHW play a very important role in accelerating IoT eco-system maturity and breaking the boundaries between industries to promote convergence. Recently, it has developed into an intelligent IoT that combines artificial intelligence (AI) with the connectivity of the IoT. Here, I will analyze the direction of development of the IoT through understanding and analysis of open source.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.6
• /
• pp.673-681
• /
• 2005

As it is the most important to make sure security and reliability for nuclear Power Plant, it's considered the most crucial issues to develop a fault detective and diagnostic system in spite of multiple hardware redundancy in itself. To develop an algorithm for a fault diagnosis in the nuclear PWR steam generator, this paper proposes a method based on ART2(adaptive resonance theory 2) neural network that senses and classifies troubles occurred in the system. The fault diagnosis system consists of fault detective part to sense occurred troubles, parameter estimation part to identify changed system parameters and fault classification part to understand types of troubles occurred. The fault classification part Is composed of a fault classifier that uses ART2 neural network. The Performance of the proposed fault diagnosis a18orithm was corroborated by applying in the steam generator.

• Industry Promotion Research
• /
• v.8 no.4
• /
• pp.163-176
• /
• 2023

Through a literature review, this study examined the concept of slow learners and the lifelong learning characteristics of slow learners, and sought ways to achieve successful lifelong learning by utilizing grit and growth mindset among non-cognitive characteristics. Slow learners were experiencing difficulties in cognitive, academic, linguistic, social and emotional, and behavioral characteristics. For successful lifelong learning of slow learners, it was necessary to set long-term goals rather than short-term goals and to maintain effort and consistency of interest to achieve the goals. In addition, it was confirmed that in order to achieve long-term goals, it is necessary to believe that change can be achieved through effort and learning. In other words, the need for learning using grit and growth mindset was confirmed. Based on these previous research results, it was presented as a lifelong learning strategy for slow learners that applied grit and growth mindset, which are non-cognitive characteristics, rather than cognitive characteristics such as intelligence.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.3
• /
• pp.11-22
• /
• 2010

This paper is a study on implementation of intelligent image surveillance system using context information and supplements temporal-spatial constraint, the weak point in which it is hard to process it in real time. In this paper, we propose scene analysis algorithm which can be processed in real time in various environments at low resolution video(320*240) comprised of 30 frames per second. The proposed algorithm gets rid of background and meaningless frame among continuous frames. And, this paper uses wavelet transform and edge histogram to detect shot boundary. Next, representative key-frame in shot boundary is selected by key-frame selection parameter and edge histogram, mathematical morphology are used to detect only motion region. We define each four basic contexts in accordance with angles of feature points by applying vertical and horizontal ratio for the motion region of detected object. These are standing, laying, seating and walking. Finally, we carry out scene analysis by defining simple context model composed with general context and emergency context through estimating each context's connection status and configure a system in order to check real time processing possibility. The proposed system shows the performance of 92.5% in terms of recognition rate for a video of low resolution and processing speed is 0.74 second in average per frame, so that we can check real time processing is possible.

• Journal of Intelligence and Information Systems
• /
• v.15 no.3
• /
• pp.1-15
• /
• 2009

In a classification problem, data imbalance occurs when the number of instances in one class greatly outnumbers the number of instances in the other class. Such data sets often cause a default classifier to be built due to skewed boundary and thus the reduction in the classification accuracy of such a classifier. This paper proposes a Geometric Mean-based Boosting (GM-Boost) to resolve the problem of data imbalance. Since GM-Boost introduces the notion of geometric mean, it can perform learning process considering both majority and minority sides, and reinforce the learning on misclassified data. An empirical study with bankruptcy prediction on Korea companies shows that GM-Boost has the higher classification accuracy than previous methods including Under-sampling, Over-Sampling, and AdaBoost, used in imbalanced data and robust learning performance regardless of the degree of data imbalance.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.6
• /
• pp.1635-1645
• /
• 1999

In this paper, an intelligent resynthesis technique for timing optimization at the architecture-level has been studied. The proposed technique can remedy the problem which may occur in combinational timing optimization techniques applied to circuits which have the hierarchical subblock structure at the architectural-level. The approach first tries to maintain the original hierarchical subblock while minimizing the longest delay of whole circuit. This paper tries to find a new approach to timing optimization for circuits which have hierarchical structure at architectural-level, and has verified its effectiveness experimentally. We claim its usefulness from the fact that most designers design the circuits hierarchically due to the increase of design complexity.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.939-944
• /
• 2007

Edge is a significant element to represent boundary information between objects in images. There are various edge detection methods, which are based on differential operation, such as Sobel, Prewitt, Roberts, Canny, Laplacian, and etc. However the conventional methods have drawbacks as follow : (i) insensitivity to edges with gentle curve intensity, (ii) detection of double edges for edges with one pixel width. For the detection of edges, not only development of the effective operators but also that of appropriate thresholding methods are necessary. But it is very complicate problem to find an appropriate threshold. In this paper, we propose an edge detection method based on the region separateness between objects to overcome the drawbacks of the conventional methods, and a thresholding method for the proposed edge detection method. We show the effectiveness of the proposed method through experimental results obtained by applying the proposed and the conventional methods to well-known test images.