• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.12
• /
• pp.2270-2277
• /
• 2016

In modern society, creation and distribution of multimedia contents is being actively conducted. These multimedia information have come out the enormous amount daily, the amount of data is also large enough it can't be compared with past text information. Since it has been increased for a need of the method to efficiently store multimedia information and to easily search the information, various methods associated therewith have been actively studied. In particular, image search methods for finding what you want from the video database or multiple sequential images, have attracted attention as a new field of image processing. Image retrieval method to be implemented in this paper, utilizes the attribute of corner patches based on the corner points of the object, for providing a new method of efficient and robust image search. After detecting the edge of the object within the image, the straight lines using a Hough transformation is extracted. A corner patches is formed by defining the extracted intersection of the straight line as a corner point. After configuring the feature vectors with patches rearranged, the similarity between images in the database is measured. Finally, for an accurate comparison between the proposed algorithm and existing algorithms, the recall precision rate, which has been widely used in content-based image retrieval was used to measure the performance evaluation. For the image used in the experiment, it was confirmed that the image is detected more accurately in the proposed method than the conventional image retrieval methods.

• Journal of Advanced Navigation Technology
• /
• v.23 no.5
• /
• pp.400-407
• /
• 2019

In this paper, the shadow detection and reconstruction method are proposed using intrinsic image, which does not change the essential characteristics under the influence of various illuminance, and multi-scale gamma correction. The shadow detection was estimated by the pixel change information between a grayscale and an intrinsic image of the color image, and the brightness of the image were adjusted by gamma correction in the shadow restoration process. Multi-scale gamma correction is performed for each channel of a color image due to the fact that the saturation can be changed by nonlinear adjustment to individual pixel values. Multi-scale gamma values are estimated based on the information of the crossed edge between shadows and non-shadowed regions in the color image, as a result, the shadows are reconstructed by correcting different region features with multi-scale gamma values. Experimental results show that the proposed method effectively reconstructs shadows in a single natural image.

• The KIPS Transactions:PartB
• /
• v.17B no.6
• /
• pp.421-428
• /
• 2010

It takes a long time for the users to view a whole image from the image server under the low-bandwidth internet environments or in case of a big sized image. In this case, as there needs a technique that preferentially transfers a part of image, JPEG2000 offers a ROI(Region-of-Interest) coding. In ROI coding, the users see the thumbnail of image from the server and specifies some regions that they want to see first. And then if an information about the regions are informed to the server, the server preferentially transfers the regions of the image. The existing methods requested a huge time to compute the mask information, but this thesis approximately computes the regions and reduces the creating time of the ROI masks. If each code block is a mixed block which ROI and background are mixed, the proper boundary points should be acquired. Searching the edges of the block, getting the two points on the edge, to get the boundary point inside the code block, the method searches a mid point between the two edge points. The proposed method doesn't have a big difference compared to the existing methods in quality, but the processing time is more speedy than the ones.

• Korean Journal of Remote Sensing
• /
• v.36 no.3
• /
• pp.449-460
• /
• 2020

Super-resolution is a technique used to reconstruct an image with low-resolution into that of high-resolution. Recently, deep-learning based super resolution has become the mainstream, and applications of these methods are widely used in the remote sensing field. In this paper, we propose a super-resolution method based on the deep back-projection network model to improve the satellite image resolution by the factor of four. In the process, we customized the loss function with the edge loss to result in a more detailed feature of the boundary of each object and to improve the stability of the model training using generative adversarial network based on Wasserstein distance loss. Also, we have applied the detail preserving image down-scaling method to enhance the naturalness of the training output. Finally, by including the modified-residual learning with a panchromatic feature in the final step of the training process. Our proposed method is able to reconstruct fine features and high frequency information. Comparing the results of our method with that of the others, we propose that the super-resolution method improves the sharpness and the clarity of WorldView-3 and KOMPSAT-2 images.

• The Journal of the Korea Contents Association
• /
• v.13 no.12
• /
• pp.38-47
• /
• 2013

An image coding based on MRC model, a kind of multi-layer image model, first segments a screen image into foreground, mask, and background layers, and then compresses each layer using a codec that is suitable to the layer. The mask layer defines the position of foreground regions such as textual and graphical contents. The colour signal of the foreground (background) region is saved in the foreground (background) layer. The mask layer which contains the segmentation result of foreground and background regions is of importance since its accuracy directly affects the overall coding performance of the codec. This paper proposes a new layer segmentation algorithm for the MRC based image coding. The proposed method extracts text pixels from the background using morphological top hat filtering. The application of white or black top hat transformation to local blocks is controlled by the information of relative brightness of text compared to the background. In the proposed method, the boundary information of text that is extracted from the edge map of the block is used for the robust decision on the relative brightness of text. Simulation results show that the proposed method is superior to the conventional methods.

• Korean Journal of Radiology
• /
• v.23 no.11
• /
• pp.1044-1054
• /
• 2022

Objective: This study aimed to investigate whether a deep learning reconstruction (DLR) method improves the image quality, stent evaluation, and visibility of the valve apparatus in coronary computed tomography angiography (CCTA) when compared with filtered back projection (FBP) and hybrid iterative reconstruction (IR) methods. Materials and Methods: CCTA images of 51 patients (mean age ± standard deviation [SD], 63.9 ± 9.8 years, 36 male) who underwent examination at a single institution were reconstructed using DLR, FBP, and hybrid IR methods and reviewed. CT attenuation, image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and stent evaluation, including 10%-90% edge rise slope (ERS) and 10%-90% edge rise distance (ERD), were measured. Quantitative data are summarized as the mean ± SD. The subjective visual scores (1 for worst -5 for best) of the images were obtained for the following: overall image quality, image noise, and appearance of stent, vessel, and aortic and tricuspid valve apparatus (annulus, leaflets, papillary muscles, and chordae tendineae). These parameters were compared between the DLR, FBP, and hybrid IR methods. Results: DLR provided higher Hounsfield unit (HU) values in the aorta and similar attenuation in the fat and muscle compared with FBP and hybrid IR. The image noise in HU was significantly lower in DLR (12.6 ± 2.2) than in hybrid IR (24.2 ± 3.0) and FBP (54.2 ± 9.5) (p < 0.001). The SNR and CNR were significantly higher in the DLR group than in the FBP and hybrid IR groups (p < 0.001). In the coronary stent, the mean value of ERS was significantly higher in DLR (1260.4 ± 242.5 HU/mm) than that of FBP (801.9 ± 170.7 HU/mm) and hybrid IR (641.9 ± 112.0 HU/mm). The mean value of ERD was measured as 0.8 ± 0.1 mm for DLR while it was 1.1 ± 0.2 mm for FBP and 1.1 ± 0.2 mm for hybrid IR. The subjective visual scores were higher in the DLR than in the images reconstructed with FBP and hybrid IR. Conclusion: DLR reconstruction provided better images than FBP and hybrid IR reconstruction.

• Journal of Oral Medicine and Pain
• /
• v.21 no.1
• /
• pp.37-54
• /
• 1996

In this thesis, a new superimposition scheme using a computer vision system was proposed with 7 pairs of skull and ante-mortem photographs, which were already identified through other tests and DNA fingerprints at the Korea National Institute of Scientific Investigation. At this computer vision system, an unidentified skull was caught by video-camcoder with the MPEG and a ante-mortem photograph was scanned by scanner. These two images were processed and superimposed using pixel processing. Recognition of the individual identification by anatomical references was performed on the two superimposed images. These results were as followings. 1. For the enhancement of skull and ante-mortem photographs, various image processing schemes, such as SMOOTH, SHARPEN, EMBOSS, MOSAIC, ENGRAVE, INVERT, NEON and COLOR TO MONO, were applied using 3*5 window processing. As an image processing result of these methods, the optimal techniques were NEON, INVERT and ENGRAVE for the edge detection of skull and ante-mortem photograph. 2. Using various superimposition image processing techniques (SRCOR, SRCAND, SRCINVERT, SRCERASE, DSTINVERT, MERGEPAINT) were compared for the enhancement of image recognition. 3. By means of the video camera, the skull image was inputed directly to a computer system : superimposing it on the ante-mortem photograph made the identification more precise and time-saving. As mentioned above, this image processing techniques for the superimposition of skull and ante-mortem photographs simply used the previous approach, In other wrods, taking skull photographs and developing it to the same size as the ante-mortem photographs. This system using various image processing techniques on computer screen, a more precise and time-saving superimposition technique could be able to be applied in the area of individual identification in forensic practice.

• Journal of Korea Multimedia Society
• /
• v.15 no.11
• /
• pp.1369-1376
• /
• 2012

In this paper, we propose 2D industrial image registration method for the detection of defects. Proposed method performs preprocessing to smooth the original image with the preservation of the edge for the robust registration against general noise. Then, x-direction gradient magnitude image and corresponding binary image are generated. Density analysis around neighborhood regions per pixel are performed to generate feature image for preventing mis-registration due to moire-like patterns, which frequently happen in industrial images. Finally, 2D image registration based on phase correlation between feature images is performed to calculate translational parameters to align two images rapidly and optimally. Experimental results showed that the registration accuracy of proposed method for the real industrial images was 100% and our method was about twenty times faster than the previous method. Our fast and accurate method could be used for the real industrial applications.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.463-466
• /
• 2008

With the development of Information Technology in recent years, the image has been an important means to store or express information. Generally, during the process of acquiring and storing images, the images can be corrupted by noise of which typical types are Impulse(Impulse Noise) and AWGN(Addiction White Gaussian Noise). Impulse noise shows irregularly in black and white over the length and breadth of the image by sharp and sudden disturbance of the image signal. In the Impulse noise environment, SM(Standard Median) filter would be used because of its good noise removal performance and simple algorithm. However, when SM filter removes noise, it also produces error at the edge of image and causes whole image quality deterioration. In this paper, we propose a method based on modified nonlinear filter operation scheme which enhances the features of noise removal and detail image preservation when restoring image in Impulse noise environment. And, we compared it with existing methods and the performances through simulation.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2000.11b
• /
• pp.318-324
• /
• 2000

Ultrasonic and magnetic resonance imaging systems are used to visualize the interior states of biological objects. These nondestructive methods have many advantages but too much expensive. And they do not give exact color information and may miss some details. If it is allowed to destruct some biological objects to get the interior and exterior information, constructing 3D image from the series of the sliced sectional images gives more useful information with relatively low cost. In this paper, PC based automatic 3D model generator was developed. The system was composed of three modules. One is the object handling and image acquisition module, which feeds and slices objects sequentially and maintains the paraffin cool to be in solid state and captures the sectional image consecutively. The second is the system control and interface module, which controls actuators for feeding, slicing, and image capturing. And the last is the image processing and visualization module, which processes a series of acquired sectional images and generates 3D graphic model. The handling module was composed of the gripper, which grasps and feeds the object and the cutting device, which cuts the object by moving cutting edge forward and backward. Sliced sectional images were acquired and saved in the form of bitmap file. The 3D model was generated to obtain the volumetric information using these 2D sectional image files after being segmented from the background paraffin. Once 3-D model was constructed on the computer, user could manipulate it with various transformation methods such as translation, rotation, scaling including arbitrary sectional view.