• IEMEK Journal of Embedded Systems and Applications
• /
• v.12 no.6
• /
• pp.395-403
• /
• 2017

Image processing for object detection and identification has been studied for supply chain management application with various approaches. Among them, feature pointed detection algorithm is used to track an object or to recognize a position in automated supply chain systems and a depth image based feature point detection is recently highlighted in the application. The result of feature point detection is easily influenced by image noise. Also, the depth image has noise itself and it also affects to the accuracy of the detection results. In order to solve these problems, we propose a novel hybrid filtering mechanism for depth image based feature point detection, it shows better performance compared with conventional hybrid filtering mechanism.

• International Journal of Precision Engineering and Manufacturing
• /
• v.8 no.1
• /
• pp.52-58
• /
• 2007

We propose a new contact detection algorithm for fine pitch wire bonding. Fast and stable contact detection of the z-axis in wire bonding is extremely important to maintain the quality of fine pitch gold wire bonding processes, which use a small pad less than $70{\mu}m$ in diameter. A small perturbation in the contact detection time causes a large difference in the size of the formed squashed ball. The new detection method is based on a statistical approach and designed for a discrete Kalman filter. It is faster and has smaller detection time variations than conventional detection methods. Experimental results are presented to demonstrate the advantages of the proposed algorithm.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.277-278
• /
• 2021

최근 손동작 인식에 대한 연구들이 활발하다. 하지만 대부분 Depth 정보를 포함한3D 정보를 필요로 한다. 이는 기존 연구들이 Depth 카메라 없이는 동작하지 않는다는 한계점이 있다는 것을 의미한다. 본 프로젝트는 Depth 카메라를 사용하지 않고 2D 이미지에서 Hand Keypoint Detection을 통해 손동작 인식을 하는 방법론을 제안한다. 학습 데이터 셋으로 Facebook에서 제공하는 InterHand2.6M 데이터셋[1]을 사용한다. 제안 방법은 크게 두 단계로 진행된다. 첫째로, Object Detection으로 Hand Detection을 수행한다. 데이터 셋이 어두운 배경에서 촬영되어 실 사용 환경에서 Detection 성능이 나오지 않는 점을 해결하기 위한 이미지 합성 Augmentation 기법을 제안한다. 둘째로, Keypoint Detection으로 21개의 Hand Keypoint들을 얻는다. 실험을 통해 유의미한 벡터들을 생성한 뒤 Annoy (Approximate nearest neighbors Oh Yeah) Tree를 생성한다. 생성된 Annoy Tree들로 후처리 작업을 거친 뒤 최종 Pose Estimation을 완료한다. Annoy Tree를 사용한 Pose Estimation에서는 NN(Neural Network)을 사용한 것보다 빠르며 동등한 성능을 냈다.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.367-369
• /
• 2005

In this paper, we present a new method for the detection of spiculation on digital mammograms. Traditional methods have defects; sensitive to noise, fixed size processing, and long processing time, however, the proposed method has merits; not sensitive to noise, adaptive size processing, and fast processing time. Experimental results show that the spiculation detection performance of the proposed method is improved much compared to the other methods.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.4
• /
• pp.284-290
• /
• 2013

Feature detection is very important to image processing area. In this paper we compare and analyze some characteristics of image processing algorithms for corner and blob feature detection. We also analyze the simulation results through image matching process. We show that how these algorithms work and how fast they execute. The simulation results are shown for helping us to select an algorithm or several algorithms extracting corner and blob feature.

• Journal of KIISE:Software and Applications
• /
• v.27 no.3
• /
• pp.241-247
• /
• 2000

In this paper, a fast change detection is proposed for sequence image. The proposed method enhances the quality of the change detection mask and the speed of the change detection by combining block based method and pixel based method. Firstly, change regions are detected for 16 ${\times}$ 16 blocks in image. And 16 ${\times}$ 16 contour block of change detection mask is divided into 4 subblocks. Finally, for divided 8 ${\times}$ 8 blocks, contour blocks are extracted and then, the pixel-based change regions are detected for them. As this makes use of the block based method, this not only enhances the speed of the change detection, but also reduces effects of noise in change detection mask. Experimental results show not only the improvement of the separated change/non-change region, but also the improvement of the speed.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.4
• /
• pp.9-16
• /
• 2014

This paper proposes a linear scratch detection and restoration algorithm using pixel data comparison in a single frame or consecutive frames. There exists a high parallelism in that a scratch detection and restoration algorithm needs a large amount of comparison operations. The proposed scratch detection and restoration algorithm is designed with a GPU for fast computation. We test the proposed algorithm in sequential and parallel processing with the set of digital videos in National Archive of Korea. In the experiments, the scratch detection rate of consecutive frames is as fast as about 20% for that of a single frame. The detection and restoration rates of a GPU-based algorithm are similar to those of a CPU-based algorithm, but the parallel implementation speeds up to about 50 times.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.8A
• /
• pp.639-647
• /
• 2012

Vision-based on-road vehicle detection is one of the key techniques in automotive driver assistance systems. However, due to the huge within-class variability in vehicle appearance and environmental changes, it remains a challenging task to develop an accurate and reliable detection system. In general, a vehicle detection system consists of two steps. The candidate locations of vehicles are found in the Hypothesis Generation (HG) step, and the detected locations in the HG step are verified in the Hypothesis Verification (HV) step. Since the final decision is made in the HV step, the HV step is crucial for accurate detection. In this paper, we propose using a reduced multivariate polynomial pattern classifier (RM) for the HV step. Our experimental results show that the RM classifier outperforms the well-known Support Vector Machine (SVM) classifier, particularly in terms of the fast decision speed, which is suitable for real-time implementation.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.2
• /
• pp.68-71
• /
• 2006

Active thermography has been used for several years in the field of remote non-destructive testing. It provides thermal images for remote detection and imaging of damages. Also, it is based on propagation and reflection of thermal waves which are launched from the surface into the inspected component by absorption of modulated radiation. For energy deposition, it use external heat sources (e.g., halogen lamp or convective heating) or internal heat generation (e.g., microwaves, eddy current, or elastic wave). Among the external heat sources, the ultrasound is generally used for energy deposition because of defect selective heating up. The heat source generating a thermal wave is provided by the defect itself due to the attenuation of amplitude modulated ultrasound. A defect causes locally enhanced losses and consequently selective heating up. Therefore amplitude modulation of the injected ultrasonic wave turns a defect into a thermal wave transmitter whose signal is detected at the surface by thermal infrared camera. This way ultrasound thermography(UT) allows for selective defect detection which enhances the probability of defect detection in the presence of complicated intact structures. In this paper the applicability of UT for fast defect detection is described. Examples are presented showing the detection of defects in PCB material. Measurements are performed on various kinds of typical defects in PCB materials (both Cu metal and non-metal epoxy). The obtained thermal image reveals area of defect in row of thick epoxy material and PCB.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.7
• /
• pp.1200-1207
• /
• 2008

In this paper, a novel fault detection method is proposed when the neutral-point-clamped inverter has a open-circuit fault in the switching device. This proposed method is configured with simple circuit and is achieved by a simple algorithm using the inherent characteristic of the continuous Pulse Width Modulation. Also, this method has the fast fault detection ability and is much simpler to embody, in comparison with conventional fault detection methods. This ability to detect fault minimizes harmful effect which are such as DC-link voltage unbalance and overstress to other switching devices. Therefore, this proposed fault detection method can improve reliability of NPC inverter system. Experimental results are presented to verify the validity of proposed fault detection method.