• The Transactions of the Korea Information Processing Society
• /
• v.7 no.11
• /
• pp.3333-3340
• /
• 2000

Recently, Requnremeni for video data have been increased rapidly by high progress of both hardware and cornpression technique. Because digital video data are unformed and mass capacity, it needs various retrieval techniquesjust as contednt-based rehieval Superimposed-caption ina digital video can help us to analyze the video story easier and be used as indexing information for many retrieval techniques In this research we propose a new method that segments the caption as analyzing texture eature of caption regions in each video frame, and that extracts the accurate scope of superimposed-caption frame and its key regions and color by measunng cominuity of caption regions between frames

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.368-373
• /
• 2007

In recent year s there have been increasing interests in real-time object tracking with image information. This dissertation presents a real-time object tracking method through the object recognition based on neural networks that have robust characteristics under various illuminations. This dissertation proposes a global search and a local search method to track the object in real-time. The global search recognizes a target object among the candidate objects through the entire image search, and the local search recognizes and track only the target object through the block search. This dissertation uses the object color and feature information to achieve fast object recognition. The experiment result shows the usefulness of the proposed method is verified.

• Journal of IKEEE
• /
• v.16 no.4
• /
• pp.356-363
• /
• 2012

Information technology improves convenience, safety, and performance of automobiles. Recently, a lot of algorithms are studied to provide safety and environment information for driving, and traffic sign recognition is one of them. It can provide important information for safety driving. In this paper, we propose a method for traffic sign detection and identification concentrating on reducing the computation time. First, potential traffic signs are segmented by color threshold, and a polygon approximation algorithm is used to detect appropriate polygons. The potential signs are compared with the template signs in the database using SURF and ORB feature matching method.

• Annual Conference of KIPS
• /
• 2020.11a
• /
• pp.889-892
• /
• 2020

현재 식품의약품안전처에서 공공데이터 포털에 제공하는 정보에 의하면 국내에는 20,000종 이상의 약이 유통되고 있다. 식약처와 여러 제약회사에서 기본적인 약 정보를 제공하고는 있지만 정확한 처방전이나 설명서가 없는 경우에 무분별한 약 복용의 위험성을 안고 있다. 일부 약 검색을 지원하는 사이트가 있으나 세부 사항을 사용자가 일일이 선택하고 입력해야 정확한 정보를 얻을 수 있다. 본 논문에서는 사용자의 스마트폰을 이용하여 알약을 촬영하면 해당 약을 인식하고 상세 정보를 알려주는 딥러닝 모델을 설계하였다. CNN 신경망을 사용하여 약의 모양, 색상, 마크, 분할선 등을 기준으로 분류하고 인식된 약의 세부 정보는 공공데이터로부터 받아온다.

• Korean journal of food and cookery science
• /
• v.17 no.3
• /
• pp.195-203
• /
• 2001

The purpose of study was to improve the storage time of breads with spices. The quality of breads with garlic, ginger and cinnamon powder containing 1 % concentration were investigated using sensory and mechanical evaluation. For 14 days, total microbial count and chemical properties were analyzed at 18$^{\circ}C$. The result of sensory evaluation was not significantly different between control and breads with spices powder. But breads with spices powder were significantly higher than control in texture and acceptability. Especially, bread with cinnamon powder was most favorable in acceptability. The result of total microbial count showed that breads with spices powder were reduced with storing time passed and bread with cinnamon powder was most reduced in breads with spices powder. ks storing time passed, moisture contents and pH range were decreased and L, a and b value were decreased in all breads. Hardness, gumminess and brittleness of torture analysis were increased as storing time passed, but springiness and cohesiveness were decreased. A negative correlation was observed between the sensory and mechanical properties in general. Sensory Properties of springiness and swelling were positively correlated with the acceptability. In the analysis of correlation between the chemical and mechanical properties showed that lightness of mechanical properties had positive correlation with pH range and moisture contents. Moisture contents of chemical properties had negative correlation with hardness, but had positive correlation with cohesiveness of mechanical properties.

• Journal of Korea Multimedia Society
• /
• v.7 no.2
• /
• pp.173-186
• /
• 2004

This paper proposed the content-based retrieval system as a method for performing image retrieval through the effective feature extraction of the object of significant meaning based on the characteristics of man's visual system. To allow the object region of interest to be primarily detected, the region, being comparatively large size, greatly different from the background color and located in the middle of the image, was judged as the major object with a meaning. To get the original features of the image, the cumulative sum of tile declination difference vector the segment of the object contour had and the signature of the bipartite object were extracted and used in the form of being applied to the rotation of the object and the change of the size after partition of the total length of the object contour of the image into the normalized segment. Starting with this form feature, it was possible to make a retrieval robust to any change in translation, rotation and scaling by combining information on the texture sample, color and eccentricity and measuring the degree of similarity. It responded less sensitively to the phenomenon of distortion of the object feature due to the partial change or damage of the region. Also, the method of imposing a different weight of similarity on the image feature based on the relationship of complexity between measured objects using the fractal dimension by the Boxing-Counting Dimension minimized the wrong retrieval and showed more efficient retrieval rate.

• Proceedings of the Korean Society of Postharvest Science and Technology of Agricultural Products Conference
• /
• 2003.04a
• /
• pp.123-123
• /
• 2003

야채 soup mix의 제조조건이 야채죽의 물리적 및 관능적 특성에 대한 영향을 조사하였다. Soup mix의 제조조건인 주입액의 양 (쌀 무게에 대한 물의 체적 비), 버섯, 당근 그리고 대파의 첨가량(쌀 무게에 대한 잣의 무게 비)에 따른 물리적 특성과 관능적 특성의 변화를 모니터링 하고자 반응 표면분석법 (response surface methodology, RSM)을 사용하였으며, 이때 실험계획은 중심합성계획법을 적용하였다. 요인변수(Xn)를 중심합성계획에 따라 17실험구로 구분하여 조리실험을 실시하였고, 이들 요인변수에 의해 영향을 받는 반응변수(Yn)는 야채죽의 물리적 특성으로 하여 회귀분석에 사용하였다. 회귀분석에 의한 모델식의 예측에는 SAS (statistical analysis system) program을 사용하였으며, 야채죽의 조리조건이 물리적 및 관능적 특성에 미치는 영향은 SAS program을 이용한 3차원 반응표면분석법으로 해석하였다. 야채의 배합비를 달리한 야채죽의 물리적 특성인 색도 L, a 및 b값에 대한 F-value는 자각 1.50, 11.75 및 5.58이고,유의수준이 각각 0.3044, 0.0019와 0.0169로서 a값과 b값의 유의성이 1% 수준에서 인정되어 이들 제조조건이 a값과 b값에 큰 영향을 미치는 것으로 나타났다. 점도와 퍼짐성에 대한 유의수준은 각각 0.6920과 0.7528이고, 반응표면회귀식의 $R^2$은 각각 0.4766과 0.4436으로 유의성이 인정되지 않았다. 고형분에 대한 유의수준은 0.2026이고 회귀식의 $R^2$는 0.7107으로서 버섯, 당근 및 대파 첨가량이 고형분의 변화에 영향을 미치지 않은 것을 알 수 있었다. 관능적 특성인 색상에 대하여 soup mix의 제조조건이 야채죽에 미치는 영향은 F-value는 6.23이고, 유의수준이 0.0124으로서 1%수준에서 유의성이 인정되었으며, 회귀식의 $R^2$은 0.8890이다. 향에 대한 유의확률은 0.4555이고 0.05이상이므로 유의성이 인정되지 않아 설정된 범위내에서 야채죽의 향에 대하여 크게 영향을 미치지 않는 것으로 나타났다. 점성에 대한 반응표면회귀식의 $R^2$은 0.8134로서 그 유의성이 5%수준에서 인정되었다. 맛과 전반적 기호도에 대하여 야채의 배합비에 따른 반응표면회귀식의 $R^2$은 각각 0.7374와 0.8651이며, 유의화률은 0.1578과 0.0228으로 나타나 전반적인 기호도에 대한 영향은 10% 유의수준에서 영향을 주었다. 결론적으로, 물리적 특성인 색도, 점성, 퍼짐성과 고형분의 함량은 관능적 특성인 색과 비교적 높은 정(正)의 상관을 나타내었으며, 관능적 특성인 향과의 상관은 유의성이 인정되지 않았다. 야채죽 제조를 위한 soup mix의 제조조건에 있어서 야채의 배합비는 색과 점성에 영향을 미치는 가장 주요한 조건이라고 생각된다.

• Food Science and Preservation
• /
• v.18 no.2
• /
• pp.131-142
• /
• 2011

The primary objective of this study is to investigate the quality properties of noodles added with germinated non-waxy (Saesalbori) and waxy (Saechalbori) barley flours at concentrations of 10%, 20% and 30% to wheat flour. The quality characteristics of the samples were assessed for color, cooking characteristics (water absorption, volume increase of noodles and turbidity of cooking water), texture profile analysis (TPA) and sensory evaluation. Regarding the cooking properties of the noodles, adding waxy barley flour did not affect cooking yield and volume increase significantly(p<0.05), but noodles added with germinated Saesalbori at level of 10% had the lowest values of cooking yield and volume increase. Adding both types of flour increased the turbidity of the noodle soups. There was a common downward trend in $L^*$ and $b^*$ values and upward trend in $a^*$ value when increasing the level of barley used progressively. Adding germinated Saechalbori decreased the hardness, springiness and gumminess of noodles but did not cause any change in cohesiveness significantly while adding germinated Saesalbori decreased all the TPA parameters of the samples. Furthermore, the sensory analysis results showed that cooked noodles with 10% added germinated barley had no significantly different overall acceptance from the control sample. 20% substitution still resulted in acceptable sensory qualities. However treatment with both the substituted flours up to 30% was shown to cause unpleasant sensory qualities of noodles.

• KOREAN JOURNAL OF PACKAGING SCIENCE & TECHNOLOGY
• /
• v.24 no.2
• /
• pp.65-71
• /
• 2018

Paper packs, glass bottles, metal cans, and plastic materials are classified according to packaging material recycling groups that are Extended Producer Responsibility (EPR). In the case of waste paper pack, the compressed cartons are dissociated to separate polyethylene films and other foreign substance, and then these are washed, pulverized and dried to produce toilet paper. Glass bottle for recycling is provided to the bottle manufacturers after the process of collecting the waste glass bottle, removing the foreign substance, sorting by color, crushing, raw materializing process. Waste glass recycling technology of Korea is largely manual, except for removal of metal components and low specific gravity materials. Metal can is classified into iron and aluminum cans through an automatic sorting machine, compressed, and reproduced as iron and aluminum through a blast furnace. In the case of composite plastic material, the selected compressed product is crushed and then recycled through melt molding and refined products are produced through solid fuel manufacturing steps through emulsification and compression molding through pyrolysis. In the recycling process of paper packs, glass bottles, metal cans, and plastic materials, the influx of recycled materials and other substances interferes with the recycling process and increases the recycling cost and time. Therefore, the government needs to improve the legal system which is necessary to use materials and structure that are easy to recycle from the design stage of products or packaging materials.

• Korean Journal of Food Science and Technology
• /
• v.47 no.1
• /
• pp.1-5
• /
• 2015

This study aimed to simultaneously determine various carotenoids from different colored paprika using an ultra performance liquid chromatograph (UPLC) equipped with a HSS T3 column. Analysis was performed at 450 nm using gradient conditions with acetonitrile/methanol/methylene chloride (65/25/10) and distilled water. We improved the peak resolution and performed carotenoid analysis within 30 min. We qualitatively analyzed 11 carotenoids (neoxanthin, capsorubin, violaxanthin, capsanthin, zeaxanthin, lutein, ${\alpha}$-cryptoxanthin, ${\beta}$-cryptoxanthin, lycopene, ${\alpha}$-carotene, and ${\beta}$-carotene). For the validation of UPLC methods, we validated the precision and accuracy of capsanthin. Capsanthin showed good linearity ($R^2$=0.9998) in the concentration range of $1-200{\mu}g/mL$ with 2.4 and $7.2{\mu}g/mL$ of limit of detection (LOD) and limit of quantification (LOQ), respectively. The relative standard deviation (RSD) for intra- and inter-day precision was less than 3.83%. Recovery was in the range of 91.86-99.87%. We quantitatively analyzed carotenoid contents from 8 different colored paprika (red, orange, yellow, and green). The most abundant carotenoids were capsanthin in red paprika, and zeaxanthin in orange, yellow, and green paprika.