• Journal of the Semiconductor & Display Technology
• /
• v.19 no.2
• /
• pp.100-104
• /
• 2020

Over the past several years, deep learning has been widely used for feature extraction in image and video for various applications such as object classification and facial recognition. This paper introduces an implantation of embedded Linux system for embossed digits recognition using CNN based deep learning methods. For this purpose, we implemented a coin recognition system based on deep learning with the Keras open source library on Raspberry PI. The performance evaluation has been made with the success rate of coin classification using the images captured with ultra-wide angle camera on Raspberry PI. The simulation result shows 98% of the success rate on average.

• Annual Conference of KIPS
• /
• 2006.11a
• /
• pp.121-124
• /
• 2006

이동물체 추출은 일반적으로 색상 분석을 통한 차 영상을 획득하여 추출하는 과정을 거치게 되는데, 이는 조명에 큰 영향을 받는 단점을 가지고 있으며, 배경영상과 이동물체의 색이 비슷할 경우 정확한 추출이 불가능한 문제점이 있다. 따라서 본 논문에서는 균일한 조도를 획득하여 생성된 배경영상과 입력영상간의 조도 차이로 생기는 문제점을 최소화 하도록 처리 하였고 침식연산과 팽창연산의 마스크의 차이와 반복횟수의 차이를 이용하여 잡음을 제거하고 수직-수평 방향으로 채움 연산을 통하여 추출된 이동물체의 정확한 영역을 추출하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.184-185
• /
• 2022

인터넷 환경의 변화에 따라 텍스트 기반의 정보 전달에서 멀티미디어 기반의 스트리밍 방식으로 바뀌어가고 있다. 또한 대용량의 동영상 데이터뿐 아니라 Shorts, Clip Reels 또는 등 다양한 방식의 동영상 형태로 배포되고 있으며 서비스 플랫폼에서는 손쉽게 편집할 수 있도록 기능을 제공하고 있다. 대용량 콘텐츠, TV, Youtue 콘텐츠를 포함하여 소용량 동영상 편집에 필요한 영상 제작 기술에서 가장 인력과 시간이 많이 소요되는 부분은 편집 단계로 딥러닝 기반 인공지능 기술을 활용하여 자동화하고 있으며 영상편집에서 가장 기본이 되는 단위인 씬검출 기법을 개발하였다. 키프레임 검출 기법과 유사도 기법을 이용하여 씬을 추출하였으며 블록 Cost Function을 이용하여 최적화하여 0.5214의 정확도를 도출하였다.

• Journal of Broadcast Engineering
• /
• v.17 no.4
• /
• pp.670-675
• /
• 2012

If the region of interest (ROI) is set within the picture of image and video and the high quality is provided in ROI compared to Non ROI, then overall subjective picture quality can be increased. ROI extracted by the color camera only increases the calculation complexity and reduces the extraction accuracy. In this paper, we use depth camera to set the ROI and calculate the object distance from camera, then propose a method that the different picture quality is controlled by depending on the distance of an object. That is, we apply a high quantization step size to the far object, but relatively a low quantization step size to the close object, so better picture quality can be provided. Simulation results show that applying the differential quantization step size to the distance of objects by the proposed method can improve the subjective picture quality.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.9
• /
• pp.453-459
• /
• 2024

Recent advances in generative AI technologies using natural language processing have critically impacted text, image, and video production. Despite these innovations, we still need to improve the consistency and reusability of AI-generated outputs. These issues are critical in cartoon creation, where the inability to consistently replicate characters and specific objects can degrade the work's quality. We propose an integrated adaption of language analysis-based requirement engineering and cartoon engineering to solve this. The proposed method applies the linguistic frameworks of Chomsky and Fillmore to analyze natural language and utilizes UML sequence models for generating consistent 3D representations of object interactions. It systematically interprets the creator's intentions from textual inputs, ensuring that each character or object, once conceptualized, is accurately replicated across various panels and episodes to preserve visual and contextual integrity. This technique enhances the accuracy and consistency of character portrayals in animated contexts, aligning closely with the initial specifications. Consequently, this method holds potential applicability in other domains requiring the translation of complex textual descriptions into visual representations.

• The KIPS Transactions:PartB
• /
• v.12B no.1 s.97
• /
• pp.47-56
• /
• 2005

A moving object has a various features that its spatial location, shape, and size are changed as time goes. In addition, the moving object has both temporal feature and spatial feature. It is one of the highly interested feature information in video data. In this paper, we propose an efficient content-based multimedia information retrieval system, so tailed ECoMOT which enables user to retrieve video data by using a trajectory information of moving objects in video data. The ECoMOT includes several novel techniques to achieve content-based retrieval using moving objects' trajectories : (1) Muitiple trajectory modeling technique to model the multiple trajectories composed of several moving objects; (2) Multiple similar trajectory retrieval technique to retrieve more similar trajectories by measuring similarity between a given two trajectories composed of several moving objects; (3) Superimposed signature-based trajectory indexing technique to effectively search corresponding trajectories from a large trajectory databases; (4) convenient trajectory extraction, query generation, and retrieval interface based on graphic user interface

• Journal of Broadcast Engineering
• /
• v.16 no.1
• /
• pp.33-43
• /
• 2011

Recently, 3D displays are supplied in the 3D markets so that the demand for 3D stereoscopic contents increases. In general, a simple method is to use a stereoscopic camera. As well, the production of 3D from 2D materials is regarded as an important technology. Such conversion works have gained much interest in the field of 3D converting. However, the stereoscopic image generation from a single 2D image is limited to simple 2D to 3D conversion so that the better realistic perception is difficult to deliver to the users. This paper presents a new stereoscopic content production method where foreground objects undergo alive action events. Further stereoscopic animation is viewed on 3D displays. Given a 2D image, the production is composed of background image generation, foreground object extraction, object/background depth maps and stereoscopic image generation The alive objects are made using the geometric transformation (e.g., translation, rotation, scaling, etc). The proposed method is performed on a Korean traditional painting, Danopungjung as well as Pixar's Up. The animated video showed that through the utilization of simple object transformations, more realistic perception can be delivered to the viewers.

• Journal of The Korean Association of Information Education
• /
• v.7 no.2
• /
• pp.199-206
• /
• 2003

XML is becoming a new developing tool of web technology because of its ability of data management and flexibility in data presentation. So it's well researched that the reusability and integration with learning objects such as text, image, sound, video and plug-in programs of web contents in computer education. But the research for storing, extracting and integrating metadata about learning object was needed prior to implementing online learning system to integrate and manage it. Therefore this study propose a new method of using web service of DBMS for extracting learning object's metadata in database server which located in 3-tier system. To evaluate the efficiency of proposed method, The test server and two DBMSs(MS SQL Server 2000 and Oracle 9i) which have 30 metadata was implemented and the response time of it was measured. The response time of it was short, but in order to using this method the additional programming with SAX/DOM was necessary.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.29-35
• /
• 2023

CCTV is used for various purposes such as crime prevention, public safety reinforcement, and traffic management. However, as the range and resolution of the camera improve, there is a risk of exposing personal information in the video. Therefore, there is a need for new technologies that can identify individuals while protecting personal information in images. In this paper, we propose histogram-based singular value decomposition for object identification and tracking. The proposed method distinguishes different objects present in the image using color information of the object. For object recognition, YOLO and DeepSORT are used to detect and extract people present in the image. Color values are extracted with a black-and-white histogram using location information of the detected person. Singular value decomposition is used to extract and use only meaningful information among the extracted color values. When using singular value decomposition, the accuracy of object color extraction is increased by using the average of the upper singular value in the result. Color information extracted using singular value decomposition is compared with colors present in other images, and the same person present in different images is detected. Euclidean distance is used for color information comparison, and Top-N is used for accuracy evaluation. As a result of the evaluation, when detecting the same person using a black-and-white histogram and singular value decomposition, it recorded a maximum of 100% to a minimum of 74%.

• Smart Media Journal
• /
• v.4 no.1
• /
• pp.9-15
• /
• 2015

Nonverbal communications such as eye gazing, posture, and gestures send forceful messages. In regard to nonverbal communication, eye gazing is one of the most strong forms that an individual can use. However, lack of mutual gazing occurs when we use video conferencing system. The displacement between locations of the eyes and a camera gets in the way of eye contact. The lack of eye gazing can give unapproachable and unpleasant feeling. In this paper, we propose an eye gazing correction for video conferencing. We use two cameras installed at the top and the bottom of the television. The captured two images are rendered with 2D warping at virtual position. We implement view morphing to the detected face, and synthesize the face and the warped image. The result shows that eye gazing is corrected and correctly preserved and the image was synthesized seamlessly.