• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.71-77
• /
• 2014

In this paper, we propose an improved numeric character recognition method which can recognize numeric characters well under low-illuminated and shade-illuminated environment. The LN(Local Normalization) preprocessing method is used in order to enhance low-illuminated and shade-illuminated image quality. The reading area is detected using line segment information extracted from the illumination-normalized meter images, and then the three-phase procedures are performed for segmentation of numeric characters in the reading area. Finally, an efficient hybrid classifier is used to classify the segmented numeric characters. The proposed numeric character classifier is a combination of multi-layered feedforward neural network and template matching module. Robust heuristic rules are applied to classify the numeric characters. Experiments using meter image database were conducted. Meter image database was made using various kinds of meters under low-illuminated and shade-illuminated environment. The experimental results indicates the superiority of the proposed numeric character recognition method.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.3
• /
• pp.97-106
• /
• 2015

In this paper, the development of infrared threat surrogate system is described and it can be used to verify the performance of DIRCM system. In this research, threat surrogates are manufactured using same F# and reflective optics used in 1st- and 2nd-Gen. real seeker so that the threat surrogate system can be used to develop code-based jamming techniques. Also the threat surrogate system can analyze the saturation jamming effect for image seeker using FPA detector. The result shows that 1st- and 2nd-generation threat surrogates have relatively precise tracking performance and jamming effect.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2011.08a
• /
• pp.308-308
• /
• 2011

6.48 ${\AA}$의 격자 상수를 갖는 InSb 물질은 0.17 eV의 낮은 에너지 밴드갭과 78,000 cm2/Vs의 전자 이동도를 갖는 물질로서 고속의 자성 센서소자, 장파장의 광 검출기 그리고 고속 전자소자 등의 분야에서 많은 주목을 받고 있다. 그러나, 전기적 특성이 우수한 InSb 물질을 소자로 구현하는데 있어서 큰 어려움이 있다. InSb와 격자 크기가 잘 맞으면서 절연이 우수한 기판의 부재가 가장 큰 문제가 되는 부분이다. 즉, 격자 부정합을 최소화하며 동시에 절연기판을 사용함으로써 소자의 특성을 잘 살려야 하는 것이다. 이러한 이유로 인하여 InSb 기반의 소자가 널리 사용되지 못하고 있는 것이다. 현재 범용으로 사용하고 있는 기판은 격자 부정합이 14%인 GaAs, 11%의 InP 그리고 18%의 Si 등이 있다. 이번 발표에서는 GaAs 기판 위에 격자 부정합을 최소화하여 InSb 박막을 최적화 시켜 성장하는 방법에 대해서 소개하고자 한다. InSb 박막 성장하는데 있어 논문으로 보고된 여러 가지 방법들이 있다. 기판과의 격자 부정합을 줄이기 위하여 저온-고온 (L-T)의 의한 메타몰픽(metamorphic) buffer 층을 성장 후 InSb 박막을 성장하는 방법[1] 그리고 단계별 buffer를 성장하는 방법[2] 등을 통해서 많은 진보가 있었다. 하지만, 우리는 GaAs 기판 위에 AlSb 박막을 성장 하면서 동시에 In과 Al의 양을 서서히 변화시키는 grading 기술을 사용하였다. 즉, 물질 각각의 격자상수를 고려하여 GaAs (기판)-AlSb-InAlSb-InSb로 변화를 주어 격자 부정합이 최소가 되도록 하여 만들어진 buffer 위에 InSb 층이 만들어 지도록 하여 GaAs 기판 위에 InSb 박막을 성장 할 수 있었다. grading 기술을 이용하여 만들어진 buffer 위에 성장된 0.3 um의 InSb 박막 층은 상온에서 전자 이동도가 약 38,000 cm2/Vs에 이르는 것을 확인하였다. InSb 박막의 두께가 약 1 um 되어야 30,000 cm2/Vs 이상의 전자 이동도를 얻을 수 있다고 많은 논문을 통해서 보고 되고 있으나 우리는 단지 0.3 um의 InSb 박막두께에서 이와 같은 전기적인 특성을 확인하였기에 이상과 같이 보고 하고자 한다.

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.388-396
• /
• 2017

Since there are many variables such as various poses, illuminations and occlusions in a face detection problem, a high performance detection system is required. Although CNN is excellent in image classification, CNN operatioin requires high-performance hardware resources. But low cost low power environments are essential for small and mobile systems. So in this paper, the CPU-FPGA integrated system is designed based on 3-stage cascade CNN architecture using small size FPGA. Adaptive Region of Interest (ROI) is applied to reduce the number of CNN operations using face information of the previous frame. We use a Field Programmable Gate Array(FPGA) to accelerate the CNN computations. The accelerator reads multiple featuremap at once on the FPGA and performs a Multiply-Accumulate (MAC) operation in parallel for convolution operation. The system is implemented on Altera Cyclone V FPGA in which ARM Cortex A-9 and on-chip SRAM are embedded. The system runs at 30FPS with HD resolution input images. The CPU-FPGA integrated system showed 8.5 times of the power efficiency compared to systems using CPU only.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.8
• /
• pp.385-392
• /
• 2016

Market analysis for a business plain is required for the success in the modern world. Most important part in this analysis is pedestrian traffic counting. A traditional way for this is counting it in person. However, it causes high labor costs and mistakes. This paper proposes an automatic algorithm to measure the pedestrian traffic count using images with webcam. The proposed algorithm is composed of two parts: pedestrian area detection and movement tracking. In pedestrian area detection, moving blobs are extracted and pedestrian areas are detected using HoG features and Adaboost algorithm. In movement tracking, multi-level matching and false positive removal are applied to track pedestrian areas and count the pedestrian traffic. Multi-level matching is composed of 3 steps: (1) the similarity calculation between HoG area, (2) the similarity calculation of the estimated position with Kalman filtering, and (3) the similarity calculation of moving blobs in the pedestrian area detection. False positive removal is to remove invalid pedestrian area. To analyze the performance of the proposed algorithm, a comparison is performed with the previous human area detection and tracking algorithm. The proposed algorithm achieves 83.6% accuracy in the pedestrian traffic counting, which is better than the previous algorithm over 11%.

• Journal of the Korean Geographical Society
• /
• v.39 no.4
• /
• pp.643-664
• /
• 2004

This study aims to review what geographers have contributed to GIS industries and national needs. To-be-geographers and geographers are expected to meet the gap between what we have teamed in school and what we have to do after graduation. The characteristics of GIS industry in the 1990 are summarized with approximate evaluation of the contribution of geographers in each stage. Author introduced the requirement for the licenses of geomatics and geospatial engineering experts and the other licenses, which are important to get a job in GIS industry from 2003 to 2004. A set of questionnaire on the user's requirements was given to GIS people in private companies and public GIS research centers and analyzed. Author found that they put an emphasis on hands-on experiences and programming skills. no advantages or geography such as capability or integration and inter-disciplinary collaboration were not appreciated. The prospects for the GIS tend to be positive but the reflectance of the prospect was not accompanied by at the same degree of preference for geography. Most government strategies for the next ten years' GIS focus on new-growth leading industries. SWOT(strength, weakness, opportunity, threat) analysis of geography for GIS industry will give some directions such as telematics, regional marketing strategies with web-based GIS technology, location based service. That means intra-disciplinary study in geography will evoke the potentiality of GIS, compared with interdisciplinary studies.

• Korean Journal of Food Science and Technology
• /
• v.45 no.2
• /
• pp.241-247
• /
• 2013

AOAC Mouse Bioassay Analysis (MBA) has been the gold standard for the analysis of paralytic shellfish poisoning toxin (PSP toxin) for more than 50 years. However, this method has inaccurate limit of quantification and cannot be used to determine toxic profiles. An HPLC method (PCOX) was optimized for Korean shellfish to establish an alternative or supplementary method for PSP analysis and was intended to be used for the official monitoring and regulation of food. The recovery rate of the PCOX method was 83.5-112.1% and the limit of quantification for total toxin was about $8.6{\mu}g$/100 g. A long-term comparison study showed a good correlation of the PCOX results with the AOAC MBA results: the correlation factors were 0.9534 and 0.9109 for oyster and mussel matrices, respectively. The PCOX method may be used as an alternative or supplementary method for AOAC MBA to monitor the occurrence of PSP and to analyze PSP toxin profile in oysters and mussels.