• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.2
• /
• pp.28-34
• /
• 2012

Various feature extraction algorithms are widely applied to real-time image processing applications for extracting significant features from images. Feature extraction algorithms are mostly combined with image processing algorithms mostly for image tracking and recognition. Feature extraction function is used to supply feature information to the other image processing algorithms and it is mainly implemented in a preprocessing stage. Nowadays, image processing applications are faced with embedded system implementation for a real-time processing. In order to satisfy this requirement, it is necessary to reduce execution time so as to improve the performance. Reducing the time for executing a feature extraction function dose not only extend the execution time for the other image processing algorithms, but it also helps satisfy a real-time requirement. This paper explains FAST (Feature from Accelerated Segment Test algorithm) of E. Rosten and presents FPGA-based embedded hardware accelerator architecture. The proposed acceleration scheme can be implemented by using approximately 2,217 Flip Flops, 5,034 LUTs, 2,833 Slices, and 18 Block RAMs in the Xilinx Vertex IV FPGA. In the Modelsim - based simulation result, the proposed hardware accelerator takes 3.06 ms to extract 954 features from a image with $640{\times}480$ pixels and this result shows the cost effectiveness of the propose scheme.

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.397-403
• /
• 2017

In the modern society, psychological diseases and impulsive crimes due to stress are occurring. In order to reduce the stress, the existing treatment methods consisted of continuous visit counseling to determine the psychological state and prescribe medication or psychotherapy. Although this face-to-face counseling method is effective, it takes much time to determine the state of the patient, and there is a problem of treatment efficiency that is difficult to be continuously managed depending on the individual situation. In this paper, we propose an artificial intelligence emotion management system that emotions of user monitor in real time and induced to a table state. The system measures multiple bio-signals based on the PPG and the GSR sensors, preprocesses the data into appropriate data types, and classifies four typical emotional states such as pleasure, relax, sadness, and horror through the SVM algorithm. We verify that the emotion of the user is guided to a stable state by providing a real-time emotion management service when the classification result is judged to be a negative state such as sadness or fear through experiments.

• Journal of Korea Multimedia Society
• /
• v.14 no.4
• /
• pp.494-503
• /
• 2011

In this paper, we propose a recognition application of facial expression for laughter theraphy on smartphone. It detects face region by using AdaBoost face detection algorithm from the front camera image of a smartphone. After detecting the face image, it detects the lip region from the detected face image. From the next frame, it doesn't detect the face image but tracks the lip region which were detected in the previous frame by using the three step block matching algorithm. The size of the detected lip image varies according to the distance between camera and user. So, it scales the detected lip image with a fixed size. After that, it minimizes the effect of illumination variation by applying the bilateral symmetry and histogram matching illumination normalization. After that, it computes lip eigen vector by using PCA(Principal Component Analysis) and recognizes laughter expression by using a multilayer perceptron artificial network. The experiment results show that the proposed method could deal with 16.7 frame/s and the proposed illumination normalization method could reduce the variations of illumination better than the existing methods for better recognition performance.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.6
• /
• pp.49-55
• /
• 2021

Recently, a small tracking radar requires the development of a small millimeter wave tracking radar having a high range resolution that can acquire and track a target in various environments and disable the target system with a single blow. Small millimeter wave tracking radar with high range resolution needs to implement a signal processor that can process wide bandwidth signals in real time and meet the requirements of small tracking radar. In this paper, we designed a signal processor that can perform the role and function of a signal processor for a small millimeter wave tracking radar. The signal processor for the small millimeter wave tracking radar requires the real-time processing of input signal of OOOMHz center frequency and OOOMHz bandwidth from 8 channels. In order to satisfy the requirements of the signal processor, the signal processor was designed by applying the high-performance FPGA (Field Programmable Gate Array) and ADC (Analog-to-digital converter) for pre-processing operations, such as DDC (Digital Down Converter) and FFT (Fast Fourier Transform). Finally, the signal processor of the small millimeter wave tracking radar was verified via performance test.

• Fire Science and Engineering
• /
• v.32 no.6
• /
• pp.84-90
• /
• 2018

Chemical accidents occur in various forms, such as explosions, leaks, spills, and fires. In particular, chemical accidents caused by fires seriously affect the surrounding air environment due to soot, causing anxiety to the residents. Therefore, it is important to identify the causative substances quickly and examine the influence of air quality in the surrounding area. In this paper, proton transfer reaction-time of flight mass spectrometry(PTR-ToFMS) was used to identify the causative material in a fire and monitor the air quality in real time. This analyzer is capable of real-time analysis with a rapid response time without sample collection and pretreatment. In addition, it is suitable for quantitative and qualitative analysis of most volatile organic compounds with high hydrogen affinity, to identify the cause of fire and examine the influence of ambient air. In April 2018, when a local fire occurred, methanol, acetone, and methyl ethyl ketone were the main causative agents in PTR-ToFMS.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.3
• /
• pp.134-139
• /
• 2023

Rehabilitators perform outpatient treatment and daily rehabilitation exercises to recover physical function with the aim of quickly returning to society after surgical treatment. Unlike performing exercises in a hospital with the help of a professional therapist, there are many difficulties in performing rehabilitation exercises by the patient on a daily basis. In this paper, we propose a CNN-LSTM-based upper limb rehabilitation real-time monitoring system so that patients can perform rehabilitation efficiently and with correct posture on a daily basis. The proposed system measures biological signals through shoulder-mounted hardware equipped with EMG and IMU, performs preprocessing and normalization for learning, and uses them as a learning dataset. The implemented model consists of three polling layers of three synthetic stacks for feature detection and two LSTM layers for classification, and we were able to confirm a learning result of 97.44% on the validation data. After that, we conducted a comparative evaluation with the Teachable machine, and as a result of the comparative evaluation, we confirmed that the model was implemented at 93.6% and the Teachable machine at 94.4%, and both models showed similar classification performance.

• Proceedings of the Korean Society of Postharvest Science and Technology of Agricultural Products Conference
• /
• 2003.10a
• /
• pp.153-153
• /
• 2003

우리나라와 일본에서 특유의 향미로 인해 오래 전부턴 조미식품으로 애용되었던 참기름은 최근 토코페롤과 세사몰류 항산화 성분의 인체 기능성으로 인해 유지시장에 서 더욱 증가일로에 있다. 지금까지 좋은 향미와 품질을 지닌 참기름을 얻기 위해 참깨의 roasting조건에 대한 많은 연구가 이루어져 왔으나, 가공 전처리인 이물질 제거를 위한 수세 작업 및 탈수 작업에 관한 연구는 아직까지 없었다. 따라서, 본 연구에서는 이물질을 제거하는 수세 작업을 한 후 수분의 제거 정도 즉, 참깨가 roasting 과정으로 들어가기 직전의 수분 함량이 참기름의 제조와 품질에 미치는 영향을 알아보고자 하였다. 시료 350g을 수세 후 24 hr, 48 hr, 120 hr 실온에서 송풍 건조를 시켜 참깨 자체의 수분 함량을 각각 17.14%, 11.78%, 6.08%로 조절하여 착유하였다. 수분함량이 다른 세 군 시료를 각기 24$0^{\circ}C$, 26$0^{\circ}C$, 28$0^{\circ}C$에서 20분간 roasting하여 착유된 참기름에 대해 이화학적 품질 특성을 알기 위해 seed와 oil의 색도, 산가, 과산화물가, TBA가, 점도와 굴절률을 측정하였다. 또한, sample single test(5점 척도)를 이용한 관능검사를 행하여 benny, nutty, burnt flavor 및 전체적 만족도와 향의 강도 항목을 조사한 후 상관분석을 실시하였다. roasted sesame seed와 oil에 대해 색도를 측정하고 분산 분석을 실시한 결과, 참깨의 색도 중 L＊가 R-suare=1로서 전체 자료가 모형을 잘 설명해줌을 의미하는데, 고수분 시료일수록 whiteness가 높게 나왔고(60이상), 고온일수록 미미한 감소가 나타났다. 이것은 수분함량이 시료의 건화속도에 요인자로 작용함을 말해준다. oil의 L＊도 마찬가지 경향을 보이나 고수분 시료구의 경우(40 이상), 타 시료구(20이하)에 비해 백색도가 높은 것을 볼 수 있어 볶음에 더 많은 시간을 투자해야 함을 보여주었다. 그러나 a＊와b＊는 시료구간 뚜렷한 차이는 보이지 않았다. 참기름에 대하여 화학적 품질 평가로 산가는 수분함량 시료구별로 1.204, 3.28, 1.862가 측정되었고, 과산화물가는 0.493, 0.169, 0.315가 기록되었고, TBA가 또한 13.45, 10.27, 11.73로서 시료의 수분 함량과 상관없이 초기 산패 경향은 거의 없는 것으로 나타났다. 참기름의 물리적 품질요소로서 점도는 평균 85.57 cS, 굴절률은 평균 1.471로서 시험구간 이화학적 차이는 없는 것으로 드러났다. 관능검사결과의 상관분석에서는 beany와 burnt flavor간에 -0.9975(p＜0.05)의 음상관을, nutty flavor와 전체favor간에 0.99662의 양상관(p$\leq$0.05)을 보였고, burnt와 향의 strength, 전체 favor와 nutty flavor간에도 상관성이 높았다. strength와 nutty 항목간에도 0.982의 높은 상관을 보였으나 전체 favor와 burnt 항목간에는 높은 음상관(-0.9862)을 보였다. 고수분 함량의 시료는 28$0^{\circ}C$의 고온 처리시 외에는 향미가 좋지 못한 것으로 나타났고, 수분량이 적은 실험구는 고온일수록 향과 고소함은 강해지나 수분 보유량이 적어 타 실험구에 비해 탄내가 많이 발생하였다. 향미 만족도는 중간 수분량, 26$0^{\circ}C$ 볶음 처리구가 가장 컸다. 결론적으로 수분함량을 10~12%로 조절한 시료로 26$0^{\circ}C$~28$0^{\circ}C$에서 20분 이내로 roasting할 때가 좋은 참기름을 얻을 수 있을 것으로 사료된다.

• Journal of the Korean Society of Food Culture
• /
• v.20 no.6
• /
• pp.738-743
• /
• 2005

This study was performed to investigate the quality characteristics of pine mushroom yanggaeng prepared with different additions and different preparations of pine mushroom. Yanggaeng was prepared with three concentration of pine mushroom after different preparations of pine mushroom, A hot wind drying 0.1%, 0.3%, 0.5%, Frozen pine mushroom grinding 0.1%, 0.3%, 0.5%, Freezed drying 0.1%, 0.3%, 0.5%, to which was added cooked red bean, agar, oligosaccharide, salt and water. Proximate composition, hunter's color, texture profile analysis and sensory evaluation of yanggaeng were examined. Lightness of pine mushroom yangaeng increased with increasing pine mushroom content and frozen pine mushroom grinding products were higher than those of the preparation products. In the texture profile analysis, hardness of pine mushroom yangaeng increased with increasing pine mushroom content and cohesiveness, springiness of Frozen pine mushroom grinding 0.1% were the highest. In sensory evaluation, the taste and viscosity scores of Freezed drying 0.1% higher than those of the other products. Also the overall acceptability of freezed drying 0.1% pine mushroom yanggaeng was the highest of the all products.

• Journal of Korean Society of Forest Science
• /
• v.108 no.4
• /
• pp.531-539
• /
• 2019

This study assessed the vitality of Carpinus laxiflora seeds stored for more than 15 years in order to discover optimal pre-treatment conditions for removingthe causes of seed dormancy and improving revitalization rate. Seeds were collected in October 2000 and stored at -18℃ for 16 years. Experiments to assess the revitalization ability of the seeds were performed under the following conditions: a controlled environment; in warm stratification (30 days at 23℃); in cold stratification (30 days at 4℃ andfor 30, 45, 60, and 120 days); gibberellin (GA₃) treatment (24 hours per day in GA₃ solutions of 100, 500, 1000, 2000, and 3000 mg·L^-1); and both cold stratification and GA₃ treatment (30 days at 4℃, then in a GA₃ solution of 100, 500, and 1000 mg·L^-1 for 2 hours). The average germination percentage(GP) of untreated seeds was 2%, and the average GP of warm-stratification seeds was 10%. Cold-stratification seeds had the highest GP at 81% for the 45-day process, while the 120-day cold-stratification seeds had the lowest GP at 67.3%. The average GP of seeds treated with GA₃ ranged from 77% (100 mg·L^-1) to 99% (1000 mg·L^-1), indicatingsignificant differences between the treatment concentrations. The treatment effect of GA₃ was highest at 500 mg·L^-1 and 1000 mg·L^-1, and lowest at 100 mg·L^-1. The average GP of seeds treated with GA₃ following cold stratification was 68%, which was lower than the cold stratification-only (73.2%) and GA₃-only (88.4%) treatments. A comprehensive comparison of the seed germination characteristics according to the four treatments determined that a GA₃ 500 mg·L^-1 pre-treatment, with the highest average GP, was ideally suited to the revitalization of long-term stored C. laxiflora seeds. Consequently, C. laxiflora stored at -18℃ for 16 years indicated strong vitality and could be regenerated by proper pre-treatment.

• Korean Journal of Plant Resources
• /
• v.27 no.1
• /
• pp.102-109
• /
• 2014

This study was carried out to investigate the effects of diffused light materials on marketable yield and quality of sunlight dried red pepper in plastic film house. The after ripening methods were composed of 3 treatments; using electric bulk dryer (Bulk), sealing house (House), and PE sealing. The diffused light materials were control, tent, shading 35% (Shading net), white polypropylene (PP (white)), and black polypropylene (PP (Black)). The marketable yield was high in order of Bulk as 300 g, House as 275 g, and PE sealing as 112 g. The redness of PE sealing was the highest as 17.85 and that of Bulk was the lowest as 10.65. There was significant difference in redness among the treatments. The moisture content of red pepper was the most rapidly reduced in control, and was the most slowly reduced in Shading net treatment. The marketable yield index was the higher in PP (white) as 114% than control. The redness had a significant difference in PP (Black) and tent compared to the other treatments. The capsaicin content showed the highest as $160mg{\cdot}100g^{-1}$ in PP (white) treatment. Conclusively, the most effective method for sunlight drying red pepper was House with PP (White) treatment. It delayed drying for 2 days but increased marketable yield at 114% than control when sunlight dried red pepper in plastic house. Our results also provided an optimized method for improvement of drying red pepper with sunlight, and will be useful for further drying red pepper research.