• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.6
• /
• pp.105-114
• /
• 2011

The snake algorithm is widely adopted to track objects by extracting the active contour of the object from background. However, it fails to track the target converging to the background if there exists background whose gradient is greater than that of the pixels on the contour. Also, the contour may shrink when the target moves fast and the snake algorithm misses the boundary of the object in its searching window. To alleviate these problems, we propose an improved algorithm that can track object contour more robustly. Firstly, we propose two external energy functions, the edge energy and the contrast energy. One is designed to give more weight to the gradient on the boundary and the other to reflect the contrast difference between the object and background. Secondly, by computing the motion vector of the contour from the difference of the two consecutive frames, we can move the snake pointers of the previous frame near the region where the object boundary is probable at the current frame. Computer experiments show that the proposed method is more robust to the complicated background than the previously known methods and can track the object with fast movement.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.3
• /
• pp.23-32
• /
• 2007

The H.264/AVC video coding standard uses rate distortion optimization (RDO) method to improve the compression performance in the intra prediction. The complexity and computational load are increased more than previous standard by using this method, even though this standard selects the best coding mode for the current macroblock. This paper proposes a fast intra mode decision algorithm for H.264/AVC encoder based on dominant edge direction (DED). To apply the idea, this algorithm uses the approximation of discrete cosine transform (DCT) coefficient. By detecting the DED, 3 modes instead of 9 modes are chosen for RDO calculation to decide the best mode in the $4{\times}4$ luma block. As for the $16{\times}16$ luma and $8{\times}8$ chroma block, instead of 4 modes, only 2 modes are searched. Experimental results show that the computation time of the proposed algorithm is decreased to about 72% of the full search method with negligible quality loss.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.2 s.308
• /
• pp.1-11
• /
• 2006

In this paper, we propose the novel video retrieval algorithm using non-parametric based motion classification in the shot-based video indexing structure. The proposed system firstly gets the key frame and motion information from each shot segmented by scene change detection method, and then extracts visual features and non-parametric based motion information from them. Finally, we construct real-time retrieval system supporting similarity comparison of these spatio-temporal features. After the normalized motion vector fields is created from MPEG compressed stream, the extraction of non-parametric based motion feature is effectively achieved by discretizing each normalized motion vectors into various angle bins, and considering a mean, a variance, and a direction of these bins. We use the edge-based spatial descriptor to extract the visual feature in key frames. Experimental evidence shows that our algorithm outperforms other video retrieval methods for image indexing and retrieval. To index the feature vectors, we use R*-tree structures.

• Journal of Korea Multimedia Society
• /
• v.14 no.2
• /
• pp.329-338
• /
• 2011

Recent augmentation reality demands more realistic multimedia data with the mixture of various media. High-technology for multimedia data which combines existing media data with various media such as audio and video dominates entire media industries. In particular, there is a growing need to serve augmentation reality, 3-dimensional contents and realtime interaction system development which are communication method and visualization tool in Internet. The existing services do not correspond to generate depth value for 3-dimensional space structure recovery which is to form solidity in existing contents. Therefore, it requires research for effective depth-map generation using 2-dimensional video. Complementing shortcomings of existing depth-map generation method using 2-dimensional video, this paper proposes an enhanced depth-map generation method that defines the depth direction in regard to loss location in a video in which none of existing algorithms has defined.

• Journal of Broadcast Engineering
• /
• v.17 no.3
• /
• pp.471-479
• /
• 2012

Intra prediction is one of the significant techniques in H.264/AVC reference software; however, it has heavy computational complexity. In order to solve this problem, many fast algorithms have been proposed. In this paper, we propose a fast intra mode decision algorithm which predicts the edge direction of the current block using sub-sampled pixels to reduce high computational complexity of the H.264/AVC encoder. The proposed algorithm shows that it not only improves the coding performance but also reduces the computational complexity of the H.264/AVC encoder compared to previous algorithms. The experimental results show that the proposed algorithm achieves the encoding time reduction of 75.93% on an average with slight peak signal-to-noise ratio (PSNR) drop and bit-rate increment.

• Journal of KIISE:Software and Applications
• /
• v.37 no.1
• /
• pp.80-84
• /
• 2010

Tracking hands is an essential technique for hand gesture recognition which is an efficient way in Human Computer Interaction (HCI). Recently, many researchers have focused on hands tracking using a 3D hand model and showed robust tracking results compared to using 2D hand models. In this paper, we propose a novel 3D hand tracking method based on a coupled particle filter. This provides robust and fast tracking results by estimating each part of global hand poses and local finger motions separately and then utilizing the estimated results as a prior for each other. Furthermore, in order to improve the robustness, we apply a multi-cue based method by integrating a color-based area matching method and an edge-based distance matching method. In our experiments, the proposed method showed robust tracking results for complex hand motions in a cluttered background.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.11
• /
• pp.2277-2282
• /
• 2009

In this paper, we proposed a new recognition method can be used in application systems using morphological features, difference operators and ART2 algorithm. At first, edges are extracted from an acquired car image by a camera using difference operators and the image of extracted edges is binarized by a block binarization method. In order to extract license plate area, noise areas are eliminated by applying morphological features of new and existing types of license plate to the 8-directional edge tracking algorithm in the binarized image. After the extraction of license plate area, mean binarization and mini-max binarization methods are applied to the extracted license plate area in order to eliminated noises by morphological features of individual elements in the license plate area, and then each character is extracted and combined by Labeling algorithm. The extracted and combined characters(letter and number symbols) are recognized after the learning by ART2 algorithm. In order to evaluate the extraction and recognition performances of the proposed method, 200 vehicle license plate images (100 for green type and 100 for white type) are used for experiment, and the experimental results show the proposed method is effective.

• The KIPS Transactions:PartB
• /
• v.17B no.4
• /
• pp.303-308
• /
• 2010

In this paper, we propose a medical image registration technique combining the gradient vector flow and modified conditional entropy. The registration is conducted by the use of a measure based on the entropy of conditional probabilities. To achieve the registration, we first define a modified conditional entropy (MCE) computed from the joint histograms for the area intensities of two given images. In order to combine the spatial information into a traditional registration measure, we use the gradient vector flow field. Then the MCE is computed from the gradient vector flow intensity (GVFI) combining the gradient information and their intensity values of original images. To evaluate the performance of the proposed registration method, we conduct experiments with our method as well as existing method based on the mutual information (MI) criteria. We evaluate the precision of MI- and MCE-based measurements by comparing the registration obtained from MR images and transformed CT images. The experimental results show that the proposed method is faster and more accurate than other optimization methods.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.9
• /
• pp.129-138
• /
• 2014

Various interpolations for digital imaging devices with a single image sensor have proposed. However, conventional methods did not consider the resolution modus of image sensor using periodic sampling. Therefore, the resulting images have problems such as quality degradation and color artifacts(color moire, zipper). In this paper, we propose a color interpolation algorithm for pixel resolution modus of image sensor. The proposed algorithm consisted of an initial step to compensate edge prediction effectively and refinement step using minimum directions for pixel resolution modus. To analyze a result of the proposed algorithm with conventional methods, we evaluated subjectively using images quality comparison and objectively using PSNR(Peak Signal to Noise Ratio). Experimental results showed that the proposed algorithm was more successful in eliminating the color artifacts than conventional methods judged by both objective and subjective criteria.

• Convergence Security Journal
• /
• v.17 no.3
• /
• pp.21-29
• /
• 2017

Accurate encoding of local patterns is a very important factor in texture classification. However, LBP based methods w idely studied have fundamental problems that are vulnerable to noise. Recently, LDP method using edge response and dire ction information was proposed in facial expression recognition. LDP is more robust to noise than LBP and can accommod ate more information in it's pattern code, but it has drawbacks that it is sensitive to rotation transforms that are critical to texture classification. In this paper, we propose a new local pattern coding method called Rotation Invariant Local Direc tional Pattern, which combines rotation-invariant transform to LDP. To prove the texture classification performance of the proposed method in this paper, texture classification was performed on the widely used UIUC and CUReT datasets. As a result, the proposed RILDP method showed better performance than the existing methods.