• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.2
• /
• pp.827-833
• /
• 2012

In this paper, we propose an improved optical flow algorithm which reduces computational complexity as well as noise level. This algorithm reduces computational time by applying level simplification technique and removes noise by using eigenvectors of objects. Optical flow is one of the accurate algorithms used to generate depth information from two image frames using the vectors which track the motions of pixels. This technique, however, has disadvantage of taking very long computational time because of the pixel-based calculation and can cause some noise problems. The level simplifying technique is applied to reduce the computational time, and the noise is removed by applying optical flow only to the area of having eigenvector, then using the edge image to generate the depth information of background area. Three-dimensional images were created from two-dimensional images using the proposed method which generates the depth information first and then converts into three-dimensional image using the depth information and DIBR(Depth Image Based Rendering) technique. The error rate was obtained using the SSIM(Structural SIMilarity index).

• Journal of KIISE:Software and Applications
• /
• v.36 no.2
• /
• pp.122-130
• /
• 2009

Conventional approaches for car number plate detection have dealt with those input images having similar sizes and simple background acquired under well organized environment. Thus their performance get reduced when input images include number plates with different sizes and when they are acquired under different lighting conditions. To solve these problem, this paper proposes a new scheme that uses the geometrical features of number plates and their topological information with reference to other features of the car. In the first step, those edges constructing a rectangle are detected and several pixels neighboring those edges are selected as the seed pixels for region growing. For region growing, color and intensity are used as the features, and the result regions are merged to construct the candidate for a number plate if their features are within a certain boundary. Once the candidates for the number plates are generated then their topological relations with other parts of the car such as lights are tested to finally determine the number plate region. The experimental results have shown that the proposed method can be used even for detecting small size number plates where characters are not visible.

• Journal of Digital Convergence
• /
• v.12 no.7
• /
• pp.239-245
• /
• 2014

In this paper, a weighted value wrinkle detection method is suggested based on the analysis on the entire facial features such as face contour, face size, eyes and ears. Firstly, the main facial elements are detected with AAM method entirely from the input screen images. Such elements are mainly composed of shape-based and appearance methods. These are used for learning the facial model and for matching the face from new screen images based on the learned models. Secondly, the face and background are separated in the screen image. Four points with the biggest possibilities for wrinkling are selected from the face and high wrinkle weighted values are assigned to them. Finally, the wrinkles are detected by applying Canny edge algorithm for the interested points of weighted value. The suggested algorithm adopts various screen images for experiment. The experiments display the excellent results of face and wrinkle detection in the most of the screen images.

• Journal of Radiation Protection and Research
• /
• v.44 no.4
• /
• pp.156-160
• /
• 2019

Background: To compare the dose of radiation received by the fetus in a pregnant patient irradiated for head and neck cancer using helical tomotherapy and three-dimensional conformal radiation therapy (3DCRT). Materials and Methods: The patient was modeled with a humanoid phantom to mimic a gestation of 26 weeks. Radiotherapy with a total dose of 2 Gy was delivered with both tomotherapy (2.5 and 5.0 cm jaw size) and 3DCRT. The position of the fetus was predicted to be 45 cm from the field edge at the time of treatment. The delivered dose was measured according to the distance from the field edge and the fetus. Results and Discussion: The accumulated dose to the fetus was 1.6 cGy by 3DCRT and 2 and 2.3 cGy by the 2.5 and 5 cm jaw tomotherapy plans. For tomotherapy, the fetal dose with the 2.5 cm jaw was lower than that with the 5 cm jaw, although the radiation leakage was greater for 2.5 cm jaw plan due to the 1.5 fold longer beam-on time. At the uterine fundus, tomotherapy with a 5 cm jaw delivered the highest dose of 2.4 cGy. When the fetus moves up to 35 cm at the 29th week of gestation, the resultant fetal doses for 3DCRT and tomotherapy with 2.5 and 5 cm jaws were estimated as 2.1, 2.7, and 3.9 cGy, respectively. Conclusion: For tomotherapy, scattering radiation was more important due to the high monitor unit values. Therefore, selecting a smaller jaw size for tomotherapy may reduce the fetal dose. however, evaluation of risk should be individually performed for each patient.

• Journal of Broadcast Engineering
• /
• v.16 no.1
• /
• pp.44-53
• /
• 2011

In this paper, we propose a 3D conversion algorithm of 2D video using depth layer partition method. In the proposed algorithm, we first set frame groups using cut detection algorithm. Each divided frame groups will reduce the possibility of error propagation in the process of motion estimation. Depth image generation is the core technique in 2D/3D conversion algorithm. Therefore, we use two depth map generation algorithms. In the first, segmentation and motion information are used, and in the other, edge directional histogram is used. After applying depth layer partition algorithm which separates objects(foreground) and the background from the original image, the extracted two depth maps are properly merged. Through experiments, we verify that the proposed algorithm generates reliable depth map and good conversion results.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.2
• /
• pp.11-23
• /
• 2011

In this paper, an accurate and fully automatic video object segmentation method is proposed for video conferencing systems in which the real-time performance is required. The proposed method consists of two steps: 1) accurate object extraction on the initial frame, 2) real-time object extraction from the next frame using the result of the first step. Object extraction on the initial frame starts with generating a cumulative edge map obtained from frame differences in the beginning. This is because we can estimate the initial shape of the foreground object from the cumulative motion. This estimated shape is used to assign the seeds for both object and background, which are needed for Graph-Cut segmentation. Once the foreground object is extracted by Graph-Cut segmentation, real-time object extraction is conducted using the extracted object and the double edge map obtained from the difference between two successive frames. Experimental results show that the proposed method is suitable for real-time processing even in VGA resolution videos contrary to previous methods, being a useful tool for immersive video conferencing systems.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.2
• /
• pp.140-146
• /
• 1989

An efficient quantization and encoding of BTC (Block Truncation Coding) parameters {($Y_{\alpha},\;Y_{\beta}),\;P_{{\beta}/{\beta}}$} are investigated, In our algorithm 4${\times}$4 blocks are classified into flat or edge block. While edge block is represented by two approximation level $Y_{\alpha},\;Y_{\beta}$ with label plane $P_{{\beta}/{\beta}}$, flat block is represented by single approximation level Y. The approximation levels Y, $Y_{\alpha}$ and $Y_{\beta}$ are encoded by predictive quatization specially designed, and the label plane $P_{{\beta}/{\beta}}$ is tried to be encoded using stored 32 reference plantes. The performance of the proposed scheme has appeared comparable to much more complex transform coding in terms of SNR, although it requires more study on the representation of small slope in background.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.3
• /
• pp.127-136
• /
• 2003

In this paper, we propose a robust object tracking algorithm based on model and edge, using deformed template and Level-Set theory. The proposed algorithm can track objects in case of background variation, object flexibility and occlusions. First we design a new potential difference energy function(PDEF) composed of two terms including inter-region distance and edge values. This function is utilized to estimate and refine the object shape. The first step is to approximately estimate the shape and location of template object based on the assumption that the object changes its shape according to the affine transform. The second step is a refinement of the object shape to fit into the real object accurately, by using the potential energy map and the modified Level-Set speed function. The experimental results show that the proposed algorithm can track non-rigid objects under various environments, such as largely flexible objects, objects with large variation in the backgrounds, and occluded objects.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.3
• /
• pp.1718-1723
• /
• 2014

We proposes the method to detect the Hangul and English character region from natural image using structural feature of Hangul and English Characters. First, we extract edge features from natural image, Next, if features are not corresponding to the heuristic rule of character features, extracted features filtered out and select candidates of character region. Next, candidates of Hangul character region are merged into one Hangul character using Hangul character merging algorithm. Finally, we detect the final character region by Hangul character class decision algorithm. English character region detected by edge features of English characters. Experimental result, proposed method could detect a character region effectively in images that contains a complex background and various environments. As a result of the performance evaluation, A proposed method showed advanced results about detection of Hangul and English characters region from natural image.

• Journal of Sensor Science and Technology
• /
• v.12 no.2
• /
• pp.57-65
• /
• 2003

When a vision chip for edge detection using CMOS process is designed, there is a necessity to implement local light adaptive-function for detecting distinctive features of an image at a wide range of light intensities. Local light adaptation is to achive the almost same output level by changing the size of receptive-fields of the local horizontal cell layers according to input light intensities, based on the lateral inhibitive-function of the horizontal cell. Thus, the almost same output level can be obtained whether input light intensities are much or less larger than background. In this paper, the horizontal cells using a resistive network which consists of p-MOSFETs were modeled and analyzed, and the local light adaptive-mechanism of the designed vision chip using the resistive network was verified.