• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.530-533
• /
• 2009

This paper proposes a method of recognizing that a person doesn't put on a safety cap using image processing method in DSP(Digital Signal Processor). It processes inputted images by image input devices that equipped in a industrial settings. If the method recognizes a person that doesn't put on a safety cap, a system transfers relevant recognition result to a supervisor and takes proper measures. If an accident happens and someone doesn't put on a safety cap, additional casualities could be. Proposed method can nip additional casualties in the bud. To recognize that a person don't put on a safety cap, images are processed by object abstraction, removal of noise, decision of a thing or a person, abstraction of a head part in a image, recognizing whether a man puts on a safety cap using HSV color space or not, and so on. Image input and image process are processed by DSP. And C language-based codes are optimized by an eignefunction(Intrinsics) for speed improvement of algorithms.

• Korea Science and Art Forum
• /
• v.37 no.3
• /
• pp.113-123
• /
• 2019

In line with policy support and demand, mobile videos about science and technology have growth potential. For activation of domestic mobile video contents about science and technology, this article aims to analysis current global leading contents and draw implications for benchmarking. Therefore, this paper attempted to analyzed types and storytelling strategy of Science and technology channels on YouTube, which has the most influence among the mobile video media. The results are as follows. Fist, the YouTube contents about science technology are categorized into three types, activity-, explain-, review-centered type. Second, activity type channels are classified into 4 sub-types. Third, The core storytelling strategy of activity type channels is a combination of familiarity and unfamiliarity to deal with everyday material through specialized scientific and technological methods. Based on the results of this research, we expect to plan and produce global killer contents.

• Clinical and Experimental Pediatrics
• /
• v.52 no.3
• /
• pp.289-294
• /
• 2009

Purpose : To assess the usefulness of magnetic resonance imaging (MRI), karyotyping, brainstem auditory evoked potential (BAEP), electroencephalogram (EEG), tandem mass screening test, and newborn metabolic screening test in children with language delay for diagnosing underlying diseases. Methods : From January 2000 to June 2007, a retrospective chart review was performed for 122 children with language delay who visited the Child Neurology Clinic at Yeungnam University Hospital and who underwent neuropsychologic tests and other diagnostic evaluations for underlying diseases. They were grouped into phenomenological diagnostic categories, and test results were analyzed according to the underlying diseases. Results : Of 122 patients, 47 (38.5%) had mental retardation, 40 (32.8%) had developmental language disorders, 23 (18.9 %) had borderline IQ, and 12 (9.8%) had autism spectrum disorder. In 26 (21.3%) cases, the causes or relevant clinical findings to explain language delay were found. Eight (10.4%) of 77 MRIs, 6 (8.0%) of 75 EEGs, and 4 (5%) of 80 BAEPs showed abnormal results. Results directly attributed to diagnosing underlying diseases were 2 hearing defects in BAEPs and 1 bilateral perisylvian cortical dysplasia in MRIs. No abnormal results were found in karyotyping, tandem mass screening tests, and new-born screening tests. Conclusion : Commonly used tests to diagnose the cause of language delay are not very effective and should only be used selectively, according to patient characteristics. However, despite the low diagnostic yields from these tests, because many patients show abnormal results, these tests are useful when conducted in complete evaluation.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.3
• /
• pp.45-55
• /
• 2000

In this paper, we proposed the hardware architecture of wavelet transform digital filter for an image processing. Filter bank pyramid algorithm is used for wavelet transform and each fillet is implemented by the FIR filter. For DWT computation, because the memory controller is implemented by hardware, we can efficiently process the multisolution decomposition of the image data only input the parameter. As a result of the image Processing in this paper, 33㏈ PSNR has been obtained on 512$\times$512 B/W image due to 11-bit mantissa processing in FPGA Implementation. And because of using QMF( Quadrature Mirror Filter) properties, it reduces half number of the multiplier needed DWT(Discrete Wavelet Transform) computation so the hardware size is reduced largely. The proposed scheme can increase the efficiency of an image Processing as well as hardware size reduced. The hardware design proposed of DWT fillet bank is synthesized by VHDL coding and then the test board is manufactured, the operating Program and the application Program are implemented using MFC++ and C++ language each other.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.131-133
• /
• 2021

Recently, the average cost of education per child has increased compared to the annual birthrate, which has been decreasing, and the quality of education has also changed. In this paper, we aim to provide more efficient delivery for language learning using Unity's Buforia techniques. Using an application using a smartphone's camera based on Unity, it provides effective language development by inducing interest to learners through sound along with three-dimensional pictures. By providing such education, parents can gain satisfaction in providing high-quality education to their children. For children learning, smartphones have the effect of becoming educational elements, not just watching videos or playing games. Finally, by improving the quality of education, it gives satisfaction to parents and gives children who learn a language as well as the perception that smartphones serve as educational devices.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.141-147
• /
• 2024

Recently, there has been growing interest in personalized services tailored to an individual's preferences. This has led to ongoing research aimed at recognizing and leveraging an individual's personality traits. Among various methods for personality assessment, the OCEAN model stands out as a prominent approach. In utilizing OCEAN for personality recognition, a multi modal artificial intelligence model that incorporates linguistic, paralinguistic, and non-linguistic information is often employed. This paper examines the impact of the margin value set for extracting facial areas from video data on the accuracy of a personality recognition model that uses facial expressions to determine OCEAN traits. The study employed personality recognition models based on 2D Patch Partition, R2plus1D, 3D Patch Partition, and Video Swin Transformer technologies. It was observed that setting the facial area extraction margin to 60 resulted in the highest 1-MAE performance, scoring at 0.9118. These findings indicate the importance of selecting an optimal margin value to maximize the efficiency of personality recognition models.

• Journal of the Korean Society of Radiology
• /
• v.8 no.4
• /
• pp.163-170
• /
• 2014

This study is to investigate neuro-anatomical correlation between neuropsychological results and cerebral cortex thickness of cognitive ability in the brain MRI targeting the patients with mild cognitive impairment. It was that 78 people who were diagnosed as first Parkinson's disease followed by neuropsychological screening battery(Parkinson's disease with mild cognitive impairment: 39 people; Parkinson's disease with normal cognition: 39 people) and 32 people of normal group were selected. Correlation between mild cognitive impairment and normal cognitive impairment and correlation between neuropsychological screening battery and cerebral cortex thickness in the brain MRI were performed by independent sample t-test or Pearson correlation coefficient and then level of significance of collected data was verified in p<0.05. As a result, cerebral cortex thickness of the Parkinson's disease with mild cognitive impairment in both side precuneas and right inferiortemporal lobe had statistically significant decrease. In addition, function of visuospatial ability, verbal and visual memory was reduced in neuropsychological screening battery for cognitive assessment. Especially, there was correlation between neuropsychological screening battery of verbal and visual memory anatomical left precuneus.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.11b
• /
• pp.751-754
• /
• 2002

학습자 중심이라는 큰 장점을 가지고 급속도로 발전해 가는 온라인 교육의 세계적인 흐름에서 어린이 영어 교육사이트에 있어 어린이들에게 흥미를 높여주고 동기를 유발시키며, 추상적인 언어를 살아있게 해 주며, 적은 용량으로 애니메이션을 표현할 수 있는 플래시 애니메이션 활용의 필요성을 알아보았고, 기존 영어교육사이트의 플래시 애니메이션을 분석해 본 결과. 작업이 제대로 이루어지지 않아 동영상으로 보여줄 수 있는 상황의 이해, 학습동기 유발, 집중력 향상 등의 학습효과를 기대하기 어렵다. 사용자에 대한 많은 연구와 플래시 애니메이션의 적극적인 활용과 개선을 통해 어린이를 위한 온라인 영어 교육이 충분히 제 역할을 다 할 수 있는 계기가 되리라 기대한다.

• Broadcasting and Media Magazine
• /
• v.22 no.1
• /
• pp.91-102
• /
• 2017

비디오 정보를 자동으로 학습하고 관련 문제를 해결하기 위해서는, 비디오의 기본 구성요소인 영상, 음성, 언어 정보의 학습을 기반으로 고차원의 추상적 개념을 파악하는 기술이 필수적이다. 최근 딥러닝이 실용적인 수준으로 이러한 기술을 가능하게 함에 따라, 보다 도전적인 비디오 스토리 분석과 이해 문제 해결을 시도할 수 있게 되었다. 본 고에서는 비디오의 요소별 분석에 적용 가능한 최신 딥러닝 기술을 소개하고, 딥러닝 기술을 핵심으로 한 TV 드라마의 스토리 분석 사례를 살펴본다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.833-836
• /
• 2004

본 연구에서는 장애인은 물론 일반 어린이들이 쉽고 재미있게 수화 언어를 배울 수 있게 도와주는 구연 동화 시스템을 구현하고자 한다. 본 시스템은 흥미를 유발할 수 있도록 이미지나 배경 소리와 같은 멀티미디어 자료와 동영상을 포함한다. 아울러, 본 시스템은 인터넷 상에서 누구나 쉽게 접근하여 배울 수 있고 단어별 수화 학습이 가능하도록 HTML 문서 형식을 가지며, 여기에 XML를 도입하여 사용자의 편리성과 단어에 대한 수화DB가 없는 경우를 고려하여 자동 지화가 생성되도록 구현한다.