• The KIPS Transactions:PartB
• /
• v.18B no.2
• /
• pp.51-56
• /
• 2011

Algorithms for intrinsic images reduce color differences in RGB images caused by the temperature of black-body radiators. Based on the reference light and detecting single invariant direction, these algorithms are weak in real images which can have multiple invariant directions when the scene illuminant is a colored illuminant. To solve these problems, this paper proposes a method of acquiring an intrinsic image by omnidirectional projection of an ROI and a translation of white patch in the ${\chi}$-chromaticity space. Because it is not easy to analyze an image in the three-dimensional RGB space, the ${\chi}$-chromaticity is also employed without the brightness factor in this paper. After the effect of the colored illuminant is decreased by a translation of white patch, an invariant direction is detected by omnidirectional projection of an ROI in this chromaticity space. In case the RGB image has multiple invariant directions, only one ROI is selected with the bin, which has the highest frequency in 3D histogram. And then the two operations, projection and inverse transformation, make intrinsic image acquired. In the experiments, test images were four datasets presented by Ebner and evaluation methods was the follows: standard deviation of the invariant direction, the constancy measure, the color space measure and the color constancy measure. The experimental results showed that the proposed method had lower standard deviation than the entropy, that its performance was two times higher than the compared algorithm.

• Korean Journal of Remote Sensing
• /
• v.27 no.2
• /
• pp.75-87
• /
• 2011

This paper presents a method for region-based building extraction from high resolution satellite images(HRSI) using integrated information of spectral and color invariant features without user intervention such as selecting training data sets. The purpose of this study is also to evaluate the effectiveness of the proposed method by applying to IKONOS and QuickBird images. Firstly, the image is segmented by the MSRG method. The vegetation and shadow regions are automatically detected and masked to facilitate the building extraction. Secondly, the region merging is performed for the masked image, which the integrated information of the spectral and color invariant features is used. Finally, the building regions are extracted using the shape feature for the merged regions. The boundaries of the extracted buildings are simplified using the generalization techniques to improve the completeness of the building extraction. The experimental results showed more than 80% accuracy for two study areas and the visually satisfactory results obtained. In conclusion, the proposed method has shown great potential for the building extraction from HRSI.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.112-119
• /
• 2019

In this paper, we propose a deep learning structure suitable for embedded system. The flame detection process of the proposed deep learning structure consists of four steps : flame area detection using flame color model, flame image classification using deep learning structure for flame color specialization, $N{\times}N$ cell separation in detected flame area, flame image classification using deep learning structure for flame shape specialization. First, only the color of the flame is extracted from the input image and then labeled to detect the flame area. Second, area of flame detected is the input of a deep learning structure specialized in flame color and is classified as flame image only if the probability of flame class at the output is greater than 75%. Third, divide the detected flame region of the images classified as flame images less than 75% in the preceding section into $N{\times}N$ units. Fourthly, small cells divided into $N{\times}N$ units are inserted into the input of a deep learning structure specialized to the shape of the flame and each cell is judged to be flame proof and classified as flame images if more than 50% of cells are classified as flame images. To verify the effectiveness of the proposed deep learning structure, we experimented with a flame database of ImageNet. Experimental results show that the proposed deep learning structure has an average resource occupancy rate of 29.86% and an 8 second fast flame detection time. The flame detection rate averaged 0.95% lower compared to the existing deep learning structure, but this was the result of light construction of the deep learning structure for application to embedded systems. Therefore, the deep learning structure for flame detection proposed in this paper has been proved suitable for the application of embedded system.

• Journal of Biomedical Engineering Research
• /
• v.30 no.1
• /
• pp.34-40
• /
• 2009

Transforms including translation and rotation are required for registering two or more images. In medical applications, different registration methods have been applied depending on the structures: for rigid bodies such as bone structures, affine transformation was widely used. In most previous research, a single transform was used for registering the whole images, which resulted in low registration accuracy especially when the degree of deformation was high between two images. In this paper, a novel registration method is introduced which is based image sub-division and bilinear interpolation of transformations. The proposed method enhanced the registration accuracy by 40% comparing with Trimmed ICP for registering color and MRI images.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.407-410
• /
• 2005

We used a series of Landsat images acquired from 1984 to 2001 to observe decadal changes of the research forest of Kangwon National University. Tree NDVI images of November in 1984, 1986 and 2001 were displayed in RGB color composite. This image enabled us to identify historical change of conifer types and their approximate ages. Conifers were classified into 'old conifer aged more than 25 years', 'young conifer aged 20-25 years' 'very young conifer aged less than 20 years', and recently deforested areas. The results coincide with in situ data very well. Archives of higher resolution images should be used to monitor the change of area for various tree types.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.870-874
• /
• 2009

Genetic algorithms can be effectively used when generating abstract images in an automatic way. However, managing huge number of automatically generated images has been problematic without sufficient managing mechanisms. This paper presents effective classification scheme for the abstract Affine images using form, emotion and color facets, and implements image databases.

• KSBB Journal
• /
• v.26 no.1
• /
• pp.87-91
• /
• 2011

Automatic counting of yeast cells in baker's yeast culture was tried using a conventional light microscope equipped with a pc camera. Relatively good binary image was obtained by using white LED as microscope light source, but uneven brightness distribution in original image hindered counting accuracy. A block binarization method using local thresholds proportional to local brightnesses was used to get improved binary images. The brightnesses of the blocks were expressed as the value component in HSV color model. Good quality binary images were obtained by binarization on $8{\times}6$ blocks of original images and connected-component labelling of the binarized images produced reliable counting results in the concentration range $1.4{\times}10^5/mL{\sim}1.4{\times}10^7\;cells/mL$.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.971-972
• /
• 2008

In this paper, we present a novel method for classifying pornography images using adaptive skin detection. From an input image, we detect initial skin regions and construct an adaptive skin probability density model using color information for the detected skin regions. From the skin probability density model, we extract feature vectors and train the images using Support Vector Machine to classify pornography images.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.33A no.5
• /
• pp.203-211
• /
• 1996

This paper describes CAD tools for the construction of image database in IC chip analysis CAD system. For IC chip analysis by high-resolution microscopy, the image database is essential to manage more than several thousand images. But manual database construction is error-prone and time-consuming. In order to solve this problem, we develop a set of CAD toos that include image grabber to capture chip images, image editor to make the whole chip image database from the grabbed images, and image divider to reconstruct the database that consists of evenly overlapped images for efficient region search. we also develop an interactive pattern matching method for user-friendly image editing, and a heuristic region search method for fast image division. The tools are developed with a high-performance graphic hardware with JPEG image comparession chip to process the huge color image data. The tools are under the field test and experimental resutls show that the database construction time can be redcued in 1/3 compared to manual database construction.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.164-169
• /
• 2009

As one of the most interesting scenes, landmarks constitute a large percentage of the vast amount of scene images available on the web. On the other hand, a specific "landmark" usually has some characteristics that distinguish it from surrounding scenes and other landmarks. These two observations make the task of accurately estimating geographic information from a landmark image necessary and feasible. In this paper, we propose a method to identify landmark location by means of landmark recognition in view of significant viewpoint, illumination and temporal variations. We use GPS-based clustering to form groups for different landmarks in the image dataset. The images in each group rather fully express the possible views of the corresponding landmark. We then use a combination of edge and color histogram to match query to database images. Initial experiments with Zubud database and our collected landmark images show that is feasible.