• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.8C
• /
• pp.1125-1132
• /
• 2004

In this Paper, we Propose an effective boundary matching based error detection algorithm using causal neighbor blocks to improve video quality degraded from channel error in block-coded video. The proposed algorithm first calculates boundary mismatch powers between a current block and each of its causal neighbor blocks. It then decides that a current block should be normal if all the mismatch powers are less than an adaptive threshold, which is adaptively determined using the statistics of the two adjacent blocks. In some experiments under the environment of 16bi1s burst error at bit error rates (BERs) of 10$^{-3}$ -10$^{-4}$ , it is shown that the proposed algorithm yields the improvements of maximum 20% in error detection rate and of maximum 3.5㏈ in PSNR of concealed kames, compared with Zeng's error detection algorithm.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.2 s.314
• /
• pp.82-92
• /
• 2007

This paper describes a novel global shape (GS) feature based on radial basis function network (RBFN) and the extraction method of the proposed feature for 3D face recognition. RBFN is the weighted sum of RBfs, it well present the non-linearity of a facial shape using the linear combination of RBFs. It is the proposed facial feature that the weights of RBFN learned by the horizontal profiles of a face. RBFN based feature expresses the locality of the facial shape even if it is GS feature, and it reduces the feature complexity like existing global methods. And it also get the smoothing effect of the facial shape. Through the experiments, we get 94.7% using the proposed feature and hidden markov model (HMM) to match the features for 100 gallery set with those for 300 test set.

• The KIPS Transactions:PartB
• /
• v.11B no.3
• /
• pp.381-386
• /
• 2004

This paper proposes an independent component analysis(ICA) of the fixed-point(FP) algorithm based on Newton method by adding the kurtosis. The kurtosis is applied for clustering the components, and the FP algorithm of Newton method is applied for improving the analysis speed and performance. The proposed ICA has been applied to the problems for separating the 6-mixed signals of 500 samples and 8-mixed images of $512\times512$pixels, respectively. The experimental results show that the proposed ICA has always a fixed analysis sequence. The result can be solved the limit of conventional ICA which has a variable sequence depending on the running of algorithm. Especially, the proposed ICA can be used to classify and identify the signals or the images.

• Journal of the Korea Computer Graphics Society
• /
• v.13 no.2
• /
• pp.55-60
• /
• 2007

Diminished reality (DR) is a technique that provide a visual convenience by virtually hiding an object. Most of existing DR systems have been implemented based on HMDs or desktop displays. However, Here has been no report on the development of DR system based on projection displays due to technical difficulty in spite of its superiority in the aspect of human factor to conventional displays. Rapid advances of projection displays and projection-based vision technologies motivated us to develop a projection-based DR system. As the first attempt, this paper proposes a projection-based diminished reality system using an image completion technique. Its usefulness is demonstrated through experiments and its potential applications are discussed.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.27 no.2
• /
• pp.126-131
• /
• 2017

In this paper, we propose a method to extract meaningful motion among various kinds of hand gestures on giving commands to robots using hand gestures. On giving a command to the robot, the hand gestures of people can be divided into a preparation one, a main one, and a finishing one. The main motion is a meaningful one for transmitting a command to the robot in this process, and the other operation is a meaningless auxiliary operation to do the main motion. Therefore, it is necessary to extract only the main motion from the continuous hand gestures. In addition, people can move their hands unconsciously. These actions must also be judged by the robot with meaningless ones. In this study, we extract human skeleton data from a depth image obtained by using a Kinect v2 sensor and extract location data of hands data from them. By using the Kalman filter, we track the location of the hand and distinguish whether hand motion is meaningful or meaningless to recognize the hand gesture by using the hidden markov model.

• The KIPS Transactions:PartB
• /
• v.18B no.1
• /
• pp.1-10
• /
• 2011

Reversible watermarking inserts watermark into digital media in such a way that visual transparency is preserved, which enables the restoration of the original media from the watermarked one without any loss of media quality. It has various applications, where high capacity and high visual quality are major requirements. This paper presents a new effective multi-round embedding scheme for the differential histogram-based reversible watermarking that satisfies high capacity requirements of the application. The proposed technique exploits the row-column cross scanning to fully utilize the locality of images when multi-round embedding phase to the message inserted image. Through experiments using multiple kinds of test images, we prove that the presented algorithm provides 100% reversibility, effectiveness of multi-round embedding, and higher visual quality, while maintaining the induced-distortion low.

• The KIPS Transactions:PartB
• /
• v.11B no.2
• /
• pp.199-206
• /
• 2004

This paper proposes a hybrid independent component analysis(ICA) of fixed-point(FP) algorithm and robust algorithm. The FP algorithm is applied for improving the analysis speed and performance, and the robust algorithm is applied for preventing performance degradations by means of very small kurtosis and temporal correlations between components. And the adaptive adaptation of temporal correlations has been proposed for solving limits of the conventional robust algorithm dependent on the maximum time delay. The proposed ICA has been applied to the problems for separating the 4-mixed signals of 500 samples and 10-mixed images of $512\times512$pixels, respectively. The experimental results show that the proposed ICA has a characteristics of adaptively adapting the maximum time delay, and has a superior separation performances(speed, rate) to conventional FP-ICA and hybrid ICA of heuristic correlation. Especially, the proposed ICA gives the larger degree of improvement as the problem size increases.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.2 s.302
• /
• pp.49-58
• /
• 2005

In this paper, we proposed a blind watermarking algerian to use characteristics of a scalar quantizer which is the recommended in the JPEG2000 and JPEG. The proposed algorithm shifts a quantization index according to the value of each watermark bit to prevent losing the watermark information during the compression by quantization. Therefore, the watermark is embedded during the process of quantization, not an additional process for watermarking, and is adaptively applied as a assigned quantizer according application areas. Before embedding process, a LFSR(Linear feedback shift register) rearranged the watermark for the security of the watermark itself and in the embedding process, a LFSR is used to hide the watermarking positions. Therefore the embedded watermark can he extracted by only the owner who knows the initial value of LFSR without the original image. The visual recognizable pattern such as a binary image was used as the watermark. The experimental results showed that the proposed algerian satisfies the robustness and imperceptibility corresponding to the major requirement of watermarking. The results showed the largest error rate to be $5.7\%$ for attack. The experimental result which compares the proposed algorithm with the Mohamed algorithm showed that the proposed algorithm was better than it, exactly $4\~5$ times for the attacks of JPEG and JPEG2000.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.6
• /
• pp.100-110
• /
• 2007

When compressed video data is transmitted over error-prone network such as wireless channel, data is likely to be lost, so the quality of reconstructed picture is severely decreased. It is specially so in case that important information such as motion vector or macroblock mode is lost. H.264/AVC standard includes DP as error resilient technique for protecting important information from error in which data is labeled according to its relative importance. But DP technique requires a network that supports different reliabilities of transmitted data. In general, the benefits of UEP is sought by sending multiple times of same packets corresponding to important information. In this paper, we propose MDC technique based on data partitioning technique. The proposed method encodes motion vector of H.264/AVC standard into multiple parts using MDC and transmits each part as independent packet. Even if partial packet is lost, the proposed scheme can decode the compressed bitstream by using estimated motion vector with partial packets correctly transmitted, so that achieving improved performance of error concealment with minimal effect of channel error. Also in decoding process, the proposed multiple description matching increases the accuracy of estimated lost motion vector and quality of reconstructed video.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.383-394
• /
• 2018

In this paper, we investigate image and video compression techniques based on deep learning which are actively studied recently. The deep learning based image compression technique inputs an image to be compressed in the deep neural network and extracts the latent vector recurrently or all at once and encodes it. In order to increase the image compression efficiency, the neural network is learned so that the encoded latent vector can be expressed with fewer bits while the quality of the reconstructed image is enhanced. These techniques can produce images of superior quality, especially at low bit rates compared to conventional image compression techniques. On the other hand, deep learning based video compression technology takes an approach to improve performance of the coding tools employed for existing video codecs rather than directly input and process the video to be compressed. The deep neural network technologies introduced in this paper replace the in-loop filter of the latest video codec or are used as an additional post-processing filter to improve the compression efficiency by improving the quality of the reconstructed image. Likewise, deep neural network techniques applied to intra prediction and encoding are used together with the existing intra prediction tool to improve the compression efficiency by increasing the prediction accuracy or adding a new intra coding process.