• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.6
• /
• pp.1449-1457
• /
• 2007

A panorama image is constructed by merging several overlapped images to a big one. There are two kinds of methods, feature based and direct method, in the construction. Feature based one has a merit of processing speed faster than direct one. But, it is difficult to be implemented under slower processing environments such as mobile device. This paper proposed high speed construction method of a panorama image. The algorithm extremely improved matching speed by reducing the number of matching parameters using scene shot guider, and additionally adapted local matching technique to reduce matching error caused by the fewer matching parameters. In the experiments, it was shown that the proposed method required about 0.078 second in processing time, about 17 times shorter than the feature based one, for 24-bit color images of $320{\times}240$ size.

• The Journal of the Society of Korean Medicine Diagnostics
• /
• v.16 no.1
• /
• pp.9-18
• /
• 2012

Objectives The aim of this study is to propose an optimized tongue colour interpolation method to achieve accurate tongue image rendering. Methods We selected 60 colour chips in the chips of DIC color guide selector, and then divided randomly the colour chips into two groups. The colour chips of a group (Gr I) were used for finding the optimized colour correction factor of error and those of the other group (Gr II) were used for verifying the correction factor. We measured colour value of the Gr I colour chips with spectrophotometer, and took the colour chips image with a digital tongue image system (DTIS). We adjusted colour correction factor of error to equal the chip colour from each method. Through that process, we obtained the optimized colour correction factor. To verify the correction factor, we measured colour value of the Gr II colour chips with a spectrophotometer, and took the colour chips image with the DTIS in the two types of colour interpolation mode (auto white balance mode and optimized colour correction factor mode). And then we calculated the CIE-$L^*ab$ colour difference (${\Delta}E$) between colour values measured with the spectrophotometer and those from images taken with the DTIS. Results In auto white balance mode, The mean ${\Delta}E$ between colour values measured with the spectrophotometer and those from images taken with the DTIS was 13.95. On the other hand, in optimized colour correction factor mode, The mean ${\Delta}E$ was 9.55. The correction rate was over 30%. Conclusions In case of interpolating colour of images taken with the DTIS, we suggest that procedure to search the optimized colour correction factor of error should be done first.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.10
• /
• pp.1334-1339
• /
• 2018

Viola & Jones's face detection algorithm is a typical face detection algorithm and shows excellent face detection performance. However, the Viola & Jones's algorithm in images including many faces generates undetected faces and wrong detected faces, such as false faces and duplicate detected faces, due to face diversity. This paper proposes an improved face detection algorithm using a face verification algorithm that eliminates the false detected faces generated from the Viola & Jones's algorithm. The proposed face verification algorithm verifies whether the detected face is valid by evaluating its size, its skin color in the designated area, its edges generated from eyes and mouth, and its duplicate detection. In the face verification experiment of 658 face images detected by the Viola & Jones's algorithm, the proposed face verification algorithm shows that all the face images created in the real person are verified.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.7 no.1
• /
• pp.1-8
• /
• 2004

It's a very meaningful experimental study to image restoration of ancient villages vanished at the real life spatial world. Focused on Cheung-Pyung Lake around where most part were flooded by the Chung-Ju large dam founded in early 1980s, we used remote sensing technique in this study in order to restore topographical features before the flood with 3 dimensional effects. It was gathered comparatively good satellite photos and remotely sensed digital images, then its made a new color image from these and the topographical map which had been made before filled water. This task was putting together two kinds of different timed images. And then, we generated DEM(digital elevation model) including the outskirts of that area as harmonizing current contour lines with the map. That could be a perfect 3D image of Cheung-Pyung around before when it had been flood by making perspective images from all directions, north, south, east and west, for showing there in three dimensions. Also, flying simulation we made for close visiting can bring us to experience their real space at that time.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.11-20
• /
• 2006

This paper describes the technique which utilizes a fuzzy neural network to sketch feature extraction in digital images. We configure an artificial neural network and make it learn fuzzy membership functions to decide a local threshold applying to sketch feature extraction. To do this. we put the learning data which is membership functions generated based on optimal feature map of a few standard images into the artificial neural network. The proposed technique extracts sketch features in an images very effectively and rapidly because the input fuzzy variable have some desirable characteristics for feature extraction such as dependency of local intensity and excellent performance and the proposed fuzzy neural network is learned from their membership functions, We show that the fuzzy neural network has a good performance in extracting sketch features without human intervention.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.5
• /
• pp.77-84
• /
• 2008

This paper proposes a new approach to eliminate the reflectance component for the localization of text in natural scene images. Natural scene images normally have an illumination component as well as a reflectance component. It is well known that a reflectance component usually obstructs the task of detecting and recognizing objects like texts in the scene, since it blurs out an overall image. We have developed an approach that efficiently removes reflectance components while Preserving illumination components. We decided whether an input image hits Normal or Polarized for determining the light environment, using the histogram which consisted of a red component. In the normal image, we acquired the text region without additional processing. Otherwise we removed light reflecting from the object using homomorphic filtering in the polarized image. And then this decided the each text region based on the color merging technique and the Saliency Map. Finally, we localized text region on these two candidate regions.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.12
• /
• pp.65-73
• /
• 2013

As the advent of the digital age, documents are often scanned to be archived or to be transmitted over the network. The largest proportion of documents is texts and the next is seal images indicating the author of the documents. While a lot of research has been conducted to recognize texts in scanned documents and commercialized text recognizing products are developed as highlighted the importance of the scanned document, information about seal images is discarded. In this paper, we study how to extract the seal image area from the color or black and white document containing the seal image and how to save the seal image. We propose a preprocessing step to remove other components except for the candidate outlines of the seal imprint from scanned documents and a method to select the final region of interest from these candidates by using the feature of seal images. Also in case of a seal imprint overlapped with texts, the most similar image among those stored in the database is selected through the template matching process. We verify the implemented system for a various type of documents produced in schools and analyze the results.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.123-131
• /
• 2019

In this study, we modified CT images of femoral head in consideration of anatomically meaningful structure, proposing the method to augment the training data of convolution Neural network for segmentation of femur mesh model. First, the femur mesh model is obtained from the CT image. Then divide the mesh model into meaningful parts by using cluster analysis on geometric characteristic of mesh surface. Finally, transform the segments by using an appropriate mesh deformation algorithm, then create new CT images by warping CT images accordingly. Deep learning models using the data enhancement methods of this study show better image division performance compared to data augmentation methods which have been commonly used, such as geometric conversion or color conversion.

• The Journal of the Korea Contents Association
• /
• v.19 no.7
• /
• pp.130-137
• /
• 2019

With the advent of smart media, short and fast-paced video content appeared, and conditions for viewing changed to viewing in environments where the perception is dispersed due to distracting and complicated external situations in a short period of time. Accordingly, smart media videos are quickly delivering meaning while keeping the eyes of viewers who lack patience. Our eyes and brain have a hard time accepting image information that flows through the constraints of a small screen. Our visual perception is limited in terms of acceptable visual information and, in particular, less cognition in moving images, so the production of smart media images should be directed in a way that enhances perceptual understanding. To be able to effectively communicate what you want to talk about while reducing the visual burden, intuitive image comprehension is needed by applying intuitiveness and behavioral induction to the moving images. Close-up shot, stable structure such as frontality and three-division structure, and color have such 'visual affordance' Therefore we need to use that device appropriately.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.901-906
• /
• 2018

Due to the development of display technologies for images, the resolution and quality of images are increasing day by day. In accordance with the development of the display technology, researches have been actively conducted on technologies for converting and displaying existing images to higher resolution and quality. Since the results of theses studies are included in the image signal processor, hardware implementation is indispensable. In this paper, we propose a real-time HDR(High Dynamic Range) conversion hardware implementation of LDR(Low Dynamic Range) image using luminance distribution. The proposed method extracts the features of the image using the histogram of the luminance distribution, and extends the luminance and color based on the extracted features. In addition, when the proposed method is designed by hardware IP(Intellectual Property) and its performance is verified, 4K DCI(Digital Cinema Image) can be handled at a rate of 30fps at 265.46MHz.