• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.333-342
• /
• 2005

This paper proposes a method, which recognizes student's identification card by using image processing and recognition technology and can manage student information on the web. The presented scheme sets up an average brightness as a threshold, based on the brightest Pixel and the least bright one for the source image of the ID card. It is converting to binary image, applies a horizontal histogram, and extracts student number through its location. And, it removes the noise of the student number region by the mode smoothing with 3$\times$3 mask. After removing noise from the student number region, each number is extracted using vertical histogram and normalized. Using the enhanced ART1 algorithm recognized the extracted student number region. In this study, we propose the enhanced ART1 algorithm different from the conventional ART1 algorithm by the dynamical establishment of the vigilance parameter. which shows a tolerance limit of unbalance between voluntary and stored patterns for clustering. The Experiment results showed that the recognition rate of the proposed ART1 algorithm was improved much more than that of the conventional ART1 algorithm. So, we develop an educational matters administration system by using the proposed recognition method of the student's identification card.

• Journal of the Korea Computer Graphics Society
• /
• v.15 no.3
• /
• pp.11-18
• /
• 2009

In this paper, we introduce a novel method to extend the JPEG standard, which is the most widely used for lossy image compression, in order to improve compression ratio. To employ two of the most successful methodologies for the data compression: differential coding and quantization simultaneously, we propose a line-based approach. For each line in a block, we apply one-dimensional discrete cosine transformation to the increments instead of the pixel values. Those values are quantized and entropy-coded similarly to the JPEG standard. To further increase compression ratio, the proposed method is plugged into the JPEG standard to form a new compression method, in which the proposed method are applied to only selected JPEG blocks. In our experiment, we found that the proposed method outperform the JPEG standard when the qualities of the coded images are set to be high. We believe the proposed method can be simply plugged into the standard to improve its compression ratio for higher quality images.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.3 s.309
• /
• pp.84-91
• /
• 2006

In this paper, we present a new segmentation algorithm for color images based on mathematical morphology and a Gaussian mixture model(GMM). We use the morphological operations to determine the number of components in a mixture model and to detect their modes of each mixture component. Next, we have adopted the GMM to represent the probability distribution of color feature vectors and used the deterministic annealing expectation maximization (DAEM) algorithm to estimate the parameters of the GMM that represents the multi-colored objects statistically. Finally, we segment the color image by using posterior probability of each pixel computed from the GMM. The experimental results show that the morphological operation is efficient to determine a number of components and initial modes of each component in the mixture model. And also it shows that the proposed DAEM provides a global optimal solution for the parameter estimation in the mixture model and the natural color images are segmented efficiently by using the GMM with parameters estimated by morphological operations and the DAEM algorithm.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.47 no.2
• /
• pp.67-73
• /
• 2010

We have developed a millimeter-wave passive imaging system with reflector for detection of concealed objects. We have designed a millimeter-wave sensor, control device for reflector control, and a lens for focusing of millimeter-wave signal at center frequency of 94GHz. DC signal from millimeter-wave sensor output is filtered by low pass filter and amplified by video amplifier, and then converted into digital signal by using ADC/DAQ. This signal is image processed by computer, and it is possible to obtain millimeter-wave passive image with resolution of $18{\times}64$ pixel using the fabricated system. It is shown that we can obtain the image of men and concealed object with the system.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1366-1372
• /
• 2019

In this paper, we designed a revised neural network to remove the Monte Carlo Rendering noise contained in the ray tracing graphics. The Monte Carlo Rendering is the best way to enhance the graphic's realism, but because of the need to calculate more than thousands of light effects per pixel, rendering processing time has increased rapidly, causing a major problem with real-time processing. To improve this problem, the number of light used in pixels is reduced, where rendering noise occurs and various studies have been conducted to eliminate this noise. In this paper, a deep learning is used to remove rendering noise, especially by separating the rendering image into diffuse and specular light, so that the structure of the dual neural network is designed. As a result, the dual neural network improved by an average of 0.58 db for 64 test images based on PSNR, and 99.22% less light compared to reference image, enabling real-time race-tracing rendering.

• Spatial Information Research
• /
• v.7 no.1
• /
• pp.89-101
• /
• 1999

This paper represents methods to calculate heights of buildings by estimating their shadow lengths in a single and panchromatic image of the KVR-1000 camera system Shadows are identified Com brightness intensity of each pixel, and their lengths are measured. Two methods are implemented to estimate heights from shadows. One method is to use a ratio of shadow s lengths with respect to heights of reference buildings measured on site. The other method uses sun elevation angles calculated from various camera s parameters at the exposure time. The estimated heights of 20 buildings are compared with heights measured on site, and the RMS errors for each method are 1.70m and 1.75m, respectively. When a resampling method to enhance identification of shadows is used and their lengths are accordingly re-calculated, the estimated errors for each method are significantly reduced to 1.17m and 1.16m, respectively. Meanwhile, effects of land slope on shadows can be hardly obtained unless detailed DTM(digital terrain model) are available, and they introduce additional errors up to 25m.

• Journal of Broadcast Engineering
• /
• v.16 no.5
• /
• pp.801-810
• /
• 2011

This paper proposes a new lossless data embedding algorithm on spatial domain of digital images. A single key parameter is required to embed and extract data in the algorithm instead of embedding any additional information such as the location map. A $3{\times}3$ window slides over the cover image by one pixel unit, and one bit can be embedded at each position of the window. So, the ideal embedding capacity equals to the number of pixels in an image. For further increase of embedding capacity, new weight parameters for the estimation of embedding target pixels have been used. As a result, significant increase in embedding capacity and better quality of the message-embedded image in high capacity embedding have been achieved. This algorithm is verified with simulations.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.1
• /
• pp.13-18
• /
• 2017

With the advancement of internet technology, the importance of data protection is gaining more attention. As a possible data protection solution, we propose a novel video encryption method using complemented maximum-length cellular automata (C-MLCA). The first step for encryption is to use 90/150 CA rule to generate a transition matrix T of a C-MLCA state followed by a 2D C-MLCA basis image. Then, we divide the video into multiple frames. Once, we perform exclusive-OR operation with the split frames and the 2D basis image, the final encrypted video can be obtained. By altering values of pixel, the fundamental information in visualizing image data, the proposed method provides improved security. Moreover, we carry out some computational experiments to further evaluate our method where the results confirm its feasibility.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.53-61
• /
• 2010

In this paper, we present a color interpolation algorithm that uses novel edge direction estimator and region classifier. The proposed edge direction estimator accurately determines the edge direction based on the correlation between the images obtained by the channel separated and down-sampled Bayer color filter array(CFA) pattern. The correlation is defined based on the similarity between the edge direction in the local region of the image and the shifting direction of the images. Also, the region of an image is defined as the flat, the edge, and the pattern-edge regions, where the edges are appeared repeatedly. When all the pixels in the image are classified into the three different regions, each pixel is interpolated horizontally or vertically according to the estimated direction. Experimental results show that the proposed algorithm outperforms the conventional edge-directed methods on objective and subjective criteria.

• Korean Journal of Optics and Photonics
• /
• v.27 no.5
• /
• pp.165-173
• /
• 2016

In this paper, we propose a three-dimensional (3D) scanning system based on two line lasers. This system uses two line lasers with different wavelengths as light sources. 532-nm and 630-nm line lasers can compensate for missing scan data generated by geometrical occlusion. It also can classify two laser planes by using the red and green channels. For automatic registration of scanning data, we control a stepping motor and divide the motor's rotational degree of freedom into micro-steps. To this end, we design a control printed circuit board for the laser and stepping motor, and use an image processing board. To compute a 3D point cloud, we obtain 200 and 400 images with laser lines and segment lines on the images at different degrees of rotation. The segmented lines are thinned for one-to-one matching of an image pixel with a 3D point.