Jung-Jin Lee

Learn More
—Detecting text regions in natural scenes is an important part of computer vision. We propose a novel text detection algorithm that extracts six different classes features of text, and uses Modest AdaBoost with multi-scale sequential search. Experiments show that our algorithm can detect text regions with a f = 0.70, from the ICDAR 2003 datasets which(More)
As the abnormal proliferation of vascular smooth muscle cells (VSMCs) plays a critical role in the development of atherosclerosis and vascular restenosis, a candidate drug with antiproliferative properties is needed. We investigated the antiproliferative action and underlying mechanism of a newly synthesized naphthoquinone derivative,(More)
BACKGROUND Soshiho-tang (SST) is a traditional medicine widely used for the treatment of chronic hepatitis. SST has been shown to confer a variety of pharmacological activities, including prevention of hepatotoxicity, promotion of liver regeneration, and modulation of liver fibrosis. In this study, we investigated the antiproliferative activity of native(More)
BACKGROUND Soshiho-tang (SH; Chinese name, Xiao-Chai-Hu-Tang; Japanese name, Shosaiko-to) is a traditional Korean, Chinese, and Japanese medicine, which has been used to treat various conditions, including hepatitis, liver cirrhosis, and chronic and acute liver disease. SH consists of seven herbal components, of which Scutellaria baicalensis Georgi and(More)
The aim of this study was to investigate whether a novel formulation of an herbal extract, KBH-1, has an inhibitory effect on obesity. To determine its anti-obesity effects and its underlying mechanism, we performed anti-obesity-related experiments in vitro and in vivo. 3T3-L1 preadipocytes were analyzed for lipid accumulation as well as the protein and(More)
PURPOSE This study was performed to evaluate shear bond strength (SBS) between three dual-cured resin cements and silica coated zirconia, before and after thermocycling treatment. MATERIALS AND METHODS Sixty specimens were cut in 15 × 2.75 mm discs using zirconia. After air blasting of 50 µm alumina, samples were prepared by tribochemical silica coating(More)
Contextual advertising seeks to place relevant ads to generic web pages based on their contents. Recently, it has been observed that classifying web pages into a well-organized taxonomy of topics is promising for matching topically relevant ads to web pages. Following the observation, in this paper we propose two methods to increase classification accuracy(More)
We discuss the construction of probabilistic user models that can analyze and predict user behavior. Currently, the lack of foundations and formal theories in the field makes it difficult to assess the feasibility and applicability of user models. Much work to date has resulted in ad-hoc approaches such as simply capturing user preferences at a shallow(More)