• Journal of the Korea Computer Graphics Society
• /
• v.12 no.4
• /
• pp.23-32
• /
• 2006

In recent years, since the digital camera has been popularized, so users can easily collect hundreds of photos in a single usage. Thus the managing of hundreds of digital photos is not a simple job comparing to the keeping paper photos. We know that managing and classifying a number of digital photo files are burdensome and annoying sometimes. So people hope to use an automated system for managing digital photos especially for their own purposes. The previous studies, e.g. content-based image retrieval, were focused on the clustering of general images, which it is not to be applied on digital photo clustering and classification. Recently, some specialized clustering algorithms for images clustering digital camera images were proposed. These algorithms exploit mainly the statistics of time gap between sequent photos. Though they showed a quite good result in image clustering for digital cameras, still lots of improvements are remained and unsolved. For example the current tools ignore completely the image transformation with the different focal lengths. In this paper, we present a photo considering focal length information recorded in EXIF. We propose an algorithms based on MVA(Matching Vector Analysis) for classification of digital images taken in the every day activity. Our experiment shows that our algorithm gives more than 95% success rates, which is competitive among all available methods in terms of sensitivity, specificity and flexibility.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.340-343
• /
• 2016

현재 사용 되어지고 있는 대부분의 영상 합성 알고리즘들은 영상의 크기가 클수록 계산량이 많아지는 특징이 있다. 따라서 UHD 영상을 대상으로 영상 합성을 할 때 속도가 기존의 HD 영상에 비해 크게 느리다는 점과 특수 카메라 사용 혹은 카메라 위치 고정 등의 제한이 필요하다는 점의 단점들이 있다. 이에 본 논문에서는 스마트폰에서 콘텐츠를 촬영한 영상들을 이용하여 영상 분류, Map 생성, Rendering 의 과정을 통해 현재 사용 되어지고 있는 영상 합성 알고리즘과 비교하여 보다 빠르게 영상 합성을 할 수 있는 알고리즘을 제안한다. 촬영 시 EXIF 에 저장되는 GPS 정보를 이용하여 그룹화를 진행한 후 영상의 특징점 매칭을 통해 Map 을 생성하는 것이 본 논문에서 제안하는 알고리즘이다. 이를 위해 본 논문에서는 FAST 특징점 알고리즘과 FREAK 기술자 알고리즘을 사용하였으며 Rendering 을 통하여 해당 알고리즘을 검증 하였다.

• Journal of Advanced Navigation Technology
• /
• v.15 no.5
• /
• pp.742-748
• /
• 2011

G-File on the position of the photo shoot pictures with built-in picture file to the user, the location and orientation of the image files using the data refers to the [1]. G-File is to store photo files, photo files and receiving means for receiving input, and picture files, photos and location information extracted by separating the subject's location information with location information and location analysis by means of the corresponding coordinates on the map including the location indicated in the guide means is characterized in that. In this paper, the G-File on the location information stored in the algorithm that can be managed is proposed. G-File on the algorithm used to manage the information to the user, G-File management is to provide convenience.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.5
• /
• pp.616-620
• /
• 2010

Generally, most people use the photo management method which clusters lots of photos into each folders according to photo shooting time and date. However, since the number of photos to manage is getting more increasing, it takes much time and burdensome work. This paper describes PHOTOLAND, a system that visualizes hundreds of photos on a 2D grid space to help users manage their photos. It closely places similar photos in the grid based on temporal and spatial information. Most photograph management systems use a scrollable view based on a sequential grid layout that arranges the thumbnails of photos in some default order on the screen. Our system decreases drag and drop mouse interaction when they classify their photos into small groups comparing to the sequential grid layout. We conducted experiments to evaluate temporal coherence and space efficiency.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.293-302
• /
• 2023

This study examines and proposes standardization approaches to address the heterogeneous issues of metadata in drone imagery within the agricultural sector. Image metadata comes in various formats depending on different camera manufacturers, with most utilizing EXIF and XMP. The metadata of cameras used in fixed-wing and rotary-wing platforms, along with the metadata requirements in image alignment software, were analyzed for sensors like DJI XT2, MicaSense RedEdge-M, and Sentera Double4K. In the agricultural domain, multispectral imagery is crucial for vegetation analysis, making the provision of such imagery essential. Based on Pix4D SW, a comparative analysis of metadata attributes was performed, and necessary elements were compiled and presented as a proposed standardization (draft) in the form of tag information.

• Journal of Advanced Navigation Technology
• /
• v.14 no.3
• /
• pp.336-342
• /
• 2010

GPIR(GPS Position Information Revision) system is a new concept of GPS system which utilizes database containing the location of taking a picture by the existing GPS, an angle between a camera and a subject and the location information of buildings and minimizes the GPS's own margin of error and there by provides the services, such as location-guiding via GPS and way-guiding via navigation in an exact and precision way more than before. GPIR system comprehends the location of taking photos via GPS information saved in G-files, searches database in the direction of taking a photo at a photo-taking position via location information and the photo-taking directional angle. And GPIR system corrects the GPS information searched to the location of a subject, again saves such information in a G-file and is ready for receiving more detailed location of the subject. This study explores into the design and development of a receiver which a GPIR user is able to utilize its system as well as the design of the receiver's prototypes.

• Journal of the Institute of Convergence Signal Processing
• /
• v.15 no.2
• /
• pp.30-36
• /
• 2014

Quality and resolution of camera in mobile device is improved significantly. In this paper, we propose block-based information hide techniques without image distortion for mobile device to solve image degradation in conventional watermarking methods. Information of image is composed with text such as camera maker, model, date, time, etc. Each text is converted to $8{\times}8$ pixel blocks and is added to the bottom of image. Generally image including block based information for image authentication are compressed using JPEG in mobile device. The vertical line value in JPEG header is modified by original size of image sensor. This technique can hide the block based authentication information using general decoder. In the experimental results, JPEG file size is slightly increased within 0.1% for the proposed block based authentication information encoding. Finally proposed methods can be adopted for various embedded systems using medical image, smart phone and DSLR camera.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.2
• /
• pp.323-330
• /
• 2019

Recently, as the growth of the Internet has led to a rapid increase in the consumption of multimedia such as photographs and moving images, the importance of metadata has been emphasized. In the case of existing metadata, only limited information such as GPS value or focal length according to the format is stored. However, with the development of mobile devices and multimedia acquisition devices, various sensors can be used in the devices. Therefore, this paper describes a method that can store not only the existing metadata format information at the time of multimedia acquisition but also another existing format of metadata such as information of various sensors which is the gyroscope and acceleration sensor of the device. We propose an application program that provides moving location information. The proposed method is expected to provide various applications such as image matching and effective image classification.