• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.5
• /
• pp.55-61
• /
• 2007

In this paper, we propose a three-dimensional(3D) active shape models for medical image segmentation. In order to build a 3D shape model, we need to generate a point distribution model(PDM) and select corresponding landmarks in all the training shapes. The manual determination method, two-dimensional(2D) method, and limited 3D method of landmark correspondences are time-consuming, tedious, and error-prone. In this paper, we generate a 3D statistical shape model using the 3D model generation method of a distance transform and a tetrahedron method for landmarking. After generating the 3D model, we extend the shape model training and gray-level model training of 2D active shape models(ASMs) and we use the integrated modeling process with scale and gray-level models for the appearance profile to represent the local structure. Experimental results are comparable to those of region-based, contour-based methods, and 2D ASMs.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.1
• /
• pp.197-208
• /
• 2016

In this paper, we propose a method based on a convolutional neural network which is one of the deep neural network. So, we convert a malware code to malware image and train the convolutional neural network. In experiment with classify 9-families, the proposed method records a 96.2%, 98.7% of top-1, 2 error rate. And our model can classify 27 families with 82.9%, 89% of top-1,2 error rate.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.16 no.2
• /
• pp.45-59
• /
• 1998

Halftonig is a technique to create the appearance of intermideate tone levels by controlling the spatial distribution of the binary pixel values. Recently, many printing devices such as image setter, inkjet printer, laser printer and facsimile, generate image, they require the technique. Ordered dither is achieved comparing the gray scale image to periodic array. This method is fast, but it occurs periodic patterns. Conentional error diffusion generates a good image. But processing speed is very slow and appeares worm artifacts in middle tone scale. To improve it, Bns(Blue noise Screen) is developed based on Gaussian distribution. In this paper, we discribe methods to design BNS based human visual characteristics and to improve blue appearing at edge area of image by USM(using unsharp mask).

• Journal of Convergence for Information Technology
• /
• v.11 no.10
• /
• pp.20-26
• /
• 2021

In this paper, we studied the rotation angle estimation methods required for image alignment in an image recognition environment. In particular, a rotation angle estimation method applicable to a low specification embedded-based environment was proposed and compared with the existing method using complex moment. The proposed method estimates the rotation angle through similarity mathcing of the 1D projection profile along the radial axis after converting an image into polar coordinates. In addition, it is also possible to select a method of using vector sum of the projection profile, which more simplifies the calculation. Through experiments conducted on binary pattern images and gray-scale images, it was shown that the estimation error of the proposed method is not significantly different from that of complex moment-based method and requires less computation and system resources. For future expansion, a study on how to match the rotation center in gray-scale images will be needed.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.1 s.307
• /
• pp.17-26
• /
• 2006

The error diffusion method is one of the digital halftoning processes that transforms the continuous-tone image to the binary image and the method has the excellent reproduction ability. However the error diffusion method using the permanent threshold has difficulty in proper binarization, so the method has the periodic pattern and is unpleasant to the eye. In this paper, to reduce defects and to binarize properly, we propose the error diffusion method using the adaptive threshold. Depending on the intensity distribution of the input gray scale image, we decided on the adaptive threshold with the average of the intensities. The error diffusion method with the adaptive threshold has the better performance than the existing method and is evaluated with experiments and comparisons.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1130-1133
• /
• 2003

The goal of this research is developing advanced lane detecting algorithm for unmanned vehicle. Previous lane detecting method to bring on error become of the lane loss and noise. Therefore, new algorithm developed to get exact information of lane. This algorithm can be used to AGV(Autonomous Guide Vehicle) and LSWS(Lane Departure Warning System), ACC(Adapted Cruise Control). We used 1/10 scale RC car to embody developed algorithm. A CCD camera is installed on top of vehicle. Images are transmitted to a main computer though wireless video transmitter. A main computer finds information of lane in road image. And it calculates control value of vehicle and transmit these to vehicle. This algorithm can detect in input image marked by 256 gray levels to get exact information of lane. To find the driving direction of vehicle, it search line equation by curve fitting of detected pixel. Finally, author used median filtering method to removal of noise and used characteristic part of road image for advanced of processing time.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.8
• /
• pp.1127-1136
• /
• 1995

In this paper, a morphological shape decomposition method is proposed for the purpose of pattern recognition and image compression. In the method, a structuring element that geometrical characteristics is more similar to the shape function is preselected. The shape is decomposed into the primitive elements corresponding to the structuring element. A gray scale image also is transformed into 8 bit plane images for the hierarchical reconstruction required in image communication systems. The shape in each bitplane is decomposed to the proposed method. Through the experiment. it is proved that the description error is reduced and the coding efficiency is improved.

• Journal of Korea Multimedia Society
• /
• v.20 no.11
• /
• pp.1720-1728
• /
• 2017

Active shape model is widely used in the field of image processing especially on arbitrary meaningful shape extraction from single gray level image. Cootes et. al. showed efficient detection of variable shape from image by using covariance and mean shape from learning. There are two stages of learning and testing. Hahn applied enhanced shape alignment method rather than using Cootes's rotation and scale scheme. Hahn did not modified the profile itself. In this paper, the method using directional one dimensional profile is proposed to enhance Cootes's one dimensional profile and the shape alignment algorithm of Hahn is combined. The performance of the proposed method was superior to Cootes's and Hahn's. Average landmark estimation error for each image was 27.72 pixels and 39.46 for Cootes's and 33.73 for Hahn's each.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.5
• /
• pp.504-512
• /
• 2002

This paper presents a new subfield method that can alleviate the visual artifact called the dynamic false contour (DFC), which occurs on plasma display panels. Nothing that the DFC is caused by the difference of time intervals between the adjacent subfields, we propose a constant slope code, in which the differences are maintained to be constant. Also, we propose a subfield code that can minimize the mean absolute error, considering the trade-off between the peak magnitude of the error and its duration. We will show that the proposed subfield method maintains an adequate performance in the view point of the human visual system, since the bound of the errors increases with the gray scale.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.61 no.3
• /
• pp.55-65
• /
• 2019

Although crack on concrete exists from its early formation, crack requires attention as it affects stiffness of structure and can lead demolition of structure as it grows. Detecting cracks on concrete is needed to take action prior to performance degradation of structure, and deep learning can be utilized for it. In this study, transfer learning, one of the deep learning techniques, was used to detect the crack, as the amount of crack's image data was limited. Pre-trained Inception-v3 was applied as a base model for the transfer learning. Web scrapping was utilized to fetch images of concrete wall with or without crack from web. In the recognition of crack, image post-process including changing size or removing color were applied. In the visualization of crack, source images divided into 30px, 50px or 100px size were used as input data, and different numbers of input data per category were applied for each case. With the results of visualized crack image, false positive and false negative errors were examined. Highest accuracy for the recognizing crack was achieved when the source images were adjusted into 224px size under gray-scale. In visualization, the result using 50 data per category under 100px interval size showed the smallest error. With regard to the false positive error, the best result was obtained using 400 data per category, and regarding to the false negative error, the case using 50 data per category showed the best result.