• FLOWER RESEARCH JOURNAL
• /
• v.18 no.3
• /
• pp.171-178
• /
• 2010

This work is for selecting superior media which is similar to Peat Moss that is in general use as media of Gymnocalycium mihanovichii for Export such as 'Hwang wall' but lower price. The result on growth of 7 kinds of media (Peat Moss, BM6 Culture Medium, Coco Peat, Hydro Cray, Hydro Ball, Hugato, Vermiculite) which are applied watering (overhead irrigation, sub irrigation) based on bichemical analysis including chemical, physical analysis are following. The result of bi-chemical analysis shows that Coco Peat was stabilized planting after 90 days and Hydro Ball has high water holding capacity. The experimental result of growth in grafted cactus 'Hwangwall' shows Coco Peat is similar to Peat Moss on organic matter and in case of inorganic media, Hugato, Vermiculite, Hydro Cray made satisfactory results. But, the weight of inorganic media is too light to be tied. Consequently, Coco Peat and sphagnum moss as organic media has lower price and the condition of growth is analogous to Peat Moss. On the other hands, Hydro Ball was chosen as a substitute of Peat Moss in inorganic media.

• Journal of the Korea Convergence Society
• /
• v.12 no.12
• /
• pp.31-37
• /
• 2021

In this paper proposed a feature fusion and spatial attention-based modified YOLOv4S for small and occluded detection. Conventional YOLOv4S is a lightweight network and lacks feature extraction capability compared to the method of the deep network. The proposed method first combines feature maps of different scales with feature fusion to enhance semantic and low-level information. In addition expanding the receptive field with dilated convolution, the detection accuracy for small and occluded objects was improved. Second by improving the conventional spatial information with spatial attention, the detection accuracy of objects classified and occluded between objects was improved. PASCAL VOC and COCO datasets were used for quantitative evaluation of the proposed method. The proposed method improved mAP by 2.7% in the PASCAL VOC dataset and 1.8% in the COCO dataset compared to the Conventional YOLOv4S.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.111-118
• /
• 2022

In computer vision research, the two-dimensional human pose is a very extensive research direction, especially in pose tracking and behavior recognition, which has very important research significance. The acquisition of human pose targets, which is essentially the study of how to accurately identify human targets from pictures, is of great research significance and has been a hot research topic of great interest in recent years. Human pose recognition is used in artificial intelligence on the one hand and in daily life on the other. The excellent effect of pose recognition is mainly determined by the success rate and the accuracy of the recognition process, so it reflects the importance of human pose recognition in terms of recognition rate. In this human body gesture recognition, the human body is divided into 17 key points for labeling. Not only that but also the key points are segmented to ensure the accuracy of the labeling information. In the recognition design, use the comprehensive data set MS COCO for deep learning to design a neural network model to train a large number of samples, from simple step-by-step to efficient training, so that a good accuracy rate can be obtained.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.3
• /
• pp.343-350
• /
• 2019

As an important visual element, color in animated films can not only depicts the reality, but also conveys emotion and meanings, which play an important role in shaping the space of animated films. As one of the most outstanding animated films, Coco uses bold and unique color language to shape the film space. It uses the national color to blend the Mexican culture into the story space making it full of Mexican regional and cultural connotation, uses color contrast to shape the physical space, highlighting the three-dimensional and deep sense of the physical space. And also uses color association to create the psychological space, leading audience into the spiritual world of the film. Based on the analysis of the Coco, we an see that when shape the film space of animation, the film maker should give full play to the characteristics and function of color, and apply different color language to shape different space according to the role of the film space, so as to expand and deepen the connotation and expressiveness of film space.

• Journal of Digital Convergence
• /
• v.17 no.12
• /
• pp.451-459
• /
• 2019

This study is aims to examine how the skeleton character in Pixar's Animation is visualized for the narrative of the film and suggests the direction of attractive character development corresponding to the story. First of all, it was conducted the case studies on the narrative of animation, character design, character's emotion expression, and animations featuring skeleton character. Based on this study, it was derived the visual representation of the skeleton character featuring in and analyzed the role and function in the animation. As a result, the expressions by the skeleton's eyes, eyebrows, mouth, lips, and jaw played the most important role for the emotional expression and lines in , and the major characteristic for human facial expression was reflected in the design of the skeleton character. In addition, the various props were used to provide the detailed informations of the skeleton's character, and it was expressed the movement emphasizing its essential attribute. Finally, the skeleton's symbolic image was strengthened by composing and arranging the skeleton's image through Mise en scene. It is expected that this study will be used as a reference for the animation character related researchers and practitioners in the business and it helps develop attractive characters fir the narrative animation in the future.

• Proceedings of the Korea Contents Association Conference
• /
• 2018.05a
• /
• pp.473-474
• /
• 2018

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.82-84
• /
• 2017

본 논문에서는 한국어 이미지 캡션을 학습하기 위한 데이터를 작성하고 딥러닝을 통해 예측하는 모델을 제안한다. 한국어 데이터 생성을 위해 MS COCO 영어 캡션을 번역하여 한국어로 변환하고 수정하였다. 이미지 캡션 생성을 위한 모델은 CNN을 이용하여 이미지를 512차원의 자질로 인코딩한다. 인코딩된 자질을 LSTM의 입력으로 사용하여 캡션을 생성하였다. 생성된 한국어 MS COCO 데이터에 대해 어절 단위, 형태소 단위, 의미형태소 단위 실험을 진행하였고 그 중 가장 높은 성능을 보인 형태소 단위 모델을 영어 모델과 비교하여 영어 모델과 비슷한 성능을 얻음을 증명하였다.

• Journal of KIISE
• /
• v.43 no.8
• /
• pp.878-882
• /
• 2016

Automatic generation of captions for an image is a very difficult task, due to the necessity of computer vision and natural language processing technologies. However, this task has many important applications, such as early childhood education, image retrieval, and navigation for blind. In this paper, we describe a Recurrent Neural Network (RNN) model for generating image captions, which takes image features extracted from a Convolutional Neural Network (CNN). We demonstrate that our models produce state of the art results in image caption generation experiments on the Flickr 8K, Flickr 30K, and MS COCO datasets.

• International Journal of Advanced Culture Technology
• /
• v.9 no.3
• /
• pp.298-304
• /
• 2021

Currently, to prevent the spread of COVID-19 virus infection, gathering of more than 5 people in the same space is prohibited. The purpose of this paper is to measure the distance between objects using the Yolov5 model for processing real-time images with OpenCV in order to restrict the distance between several people in the same space. Also, Utilize Euclidean distance calculation method in DeepSORT and OpenCV to minimize occlusion. In this paper, to detect the distance between people, using the open-source COCO dataset is used for learning. The technique used here is using the YoloV5 model to measure the distance, utilizing DeepSORT and Euclidean techniques to minimize occlusion, and the method of expressing through visualization with OpenCV to measure the distance between objects is used. Because of this paper, the proposed distance measurement method showed good results for an image with perspective taken from a higher position than the object in order to calculate the distance between objects by calculating the y-axis of the image.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.57 no.4
• /
• pp.449-455
• /
• 2012

Greenhouse and laboratory experiments were conducted to determine the effects of shade treatment and substrate components on plant growth and physiological activity of Taraxacum officinale. Substrates combined with coco peat and perlite (ratio 70 : 30 and 50 : 50, v/v) showed higher growth and yield than their single substrates (p<0.05). Shade treatment also significantly reduced plant height, root length, root diameter, leaf area, chlorophyll content, and fresh weight (p<0.05), compared to no shade. Contents of total phenolics [mg chlorogenic acid equivalents (CAE) $kg^{-1}$ DW] and total flavonoids [mg naringin equivalents $kg^{-1}$ DW] showed higher amounts in shoot parts than root parts of T. officinale, with shade than no shade. The antioxidant potential of the methanol extracts from the plants dose-dependently increased. DPPH (1,1-diphenyl-2-picryl hydrazyl radical) free radical scavenging activity was higher in leaf parts than in root parts of the plants, and no shade than with shade.