• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.61-71
• /
• 2004

Recently, various techniques for face detection are studied, but most of them still have problems on processing in real-time. Therefore, in this paper, we propose novel techniques for real-time detection of human faces in sequential images using motion and chroma information. First, background model is used to find a moving area. In this procmoving area. edure, intensity values for reference images are averaged, then skin-color are detected in We use HCr color-space model and adaptive threshold method for detection. Second, binary image labeling is applied to acquire candidate regions for faces. Candidates for mouth and eyes on a face are obtained using differences between green(G) and blue(B), intensity(I) and chroma-red(Cr) value. We also considered distances between eye points and mouth on a face. Experimental results show effectiveness of real-time detection for human faces in sequential images.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.11A
• /
• pp.1197-1205
• /
• 2007

An adaptive K-best detection scheme is proposed for MIMO systems. The proposed scheme changes the number of survivor paths, K based on the degree of the reliability of Zero-Forcing (ZF) estimates at each K-best step. The critical drawback of the fixed K-best detection is that the correct path's metric may be temporarily larger than K minimum paths metrics due to imperfect interference cancellation by the incorrect ZF estimates. Based on the observation that there are insignificant differences among path metrics (ML distances) when the ZF estimates are incorrect, we use the ratio of the minimum ML distance to the second minimum as a reliability indicator for the ZF estimates. So, we adaptively select the value of K according to the ML distance ratio. It is shown that the proposed scheme achieves the significant improvement over the conventional fixed K-best scheme. The proposed scheme effectively achieves the performance of large K-best system while maintaining the overall average computation complexity much smaller than that of large K system.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.9
• /
• pp.110-117
• /
• 2016

Applying the contrast enhancement algorithms to luminance values of color images is a widely used approach to enhance the contrast of color images. The results obtained by this approach have reduced saturation compared with that of the original images in spite of contrast enhancement without color degradation. Applying the contrast enhancement algorithm to each channel of color images is another approach for the contrast enhancement of color images. This method produces improved images in terms of contrast and saturation while the hue of original images is changed. In this paper, main cause of color degradation is analyzed and then solving the problem based on the analysis. The channel adaptive contrast enhancement method considering characteristics of each channel is also proposed to deal with color degradation. As a result, the proposed method enhances the contrast and saturation simultaneously without color degradation. Experimental results show that the proposed method outperforms the conventional methods not only on subjective evaluation but on objective criteria.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.6A
• /
• pp.614-623
• /
• 2008

A very low complexity QRD-M algorithm based on adaptive search area is proposed for MIMO systems. The conventional QRD-M scheme extends each survivor paths to all constellation symbols at each layer and selects M paths of minimum path metrics. We found that performance will not be degraded even if we adaptively restrict the survivor path extension only to the neighboring points of temporary detection symbol according to the channel condition at each layer. By employing this feature, we propose a new QRD-M algorithm achieving the near MLD performance with a reduced complexity. We employ the channel gain ratio among the layers as a channel condition indicator, which does not require SNR estimation. The simulation results show that the proposed scheme effectively achieves near MLD performance while maintaining the overall average computation complexity much smaller than the conventional QRD-M algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.6C
• /
• pp.523-529
• /
• 2010

We propose a very low complexity lattice reduction (LR) algorithm for MIMO detection in time varying channels. The proposed scheme reduces the complexity by performing LR in a block-wise manner. The proposed scheme takes advantage of the temporal correlation of the channel matrices in a block and its impact on the unimodular matrices during LR process. From this, the proposed scheme can skip a number of redundant LR processes for consecutive channel matrices and performs a single LR in a block. The simulation results investigated in this letter reveal that the proposed detection scheme requires only 43.4% multiplications and 17.3% divisions of LLL-LR and only 50.2% multiplications and 68.2% divisions of the conventional adaptive LR with almost no performance degradation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.12A
• /
• pp.1339-1345
• /
• 2007

An important drawback in Lattice Reduction (LR) aided detectors has been investigated. For the solution, an improved LR aided detection with ignorable complexity overhead is proposed for MIMO system, where the additional correction operation is performed for the case of unreliable symbol decision. We found that LR aided detection errors mainly occur when the lattice points after the inverse lattice transform in the final step fall outside the constellation point set. In the proposed scheme, we check whether or not the lattice point obtained through LR detection is out of constellation. Only for the case of out of constellation, we additionally perform ML search with reduced search region restricted to the neighboring points near to the obtained lattice points. Using this approach, we can effectively and significantly improve the detection performance with just a slight complexity overhead which is negligible compared to full searched ML scheme. Simulation results show that the proposed scheme achieves the detection performance near to that of the ML detection with a lower computational complexity.

• The Journal of the Korea Contents Association
• /
• v.6 no.9
• /
• pp.19-27
• /
• 2006

Mean shift procedure is applied for the data points in the joint spatial-range domain and achieves a high quality. However, a color image is segmented differently according to the inputted spatial parameter or range parameter and the demerit is that the image is broken into many small regions in case of the small parameter. In this paper, to improve this demerit, we propose the method that groups similar regions using region merging method for over-segmented images. The proposed method converts a over-segmented image in RGB color space into in HSI color space and merges similar regions by hue information. Here, to preserve edge information, the region merge constraints are used to decide whether regions are merged or not. After then, we merge the regions in RGB color space for non-processed regions in HSI color space. Experimental results show the superiority in region's segmentation results.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.2 no.1
• /
• pp.3-10
• /
• 1998

In this paper, a new superimposition scheme using a computer vision system was proposed with 7 pairs of skull and ante-mortem photographs, which were already identified through other tests and DNA fingerprints at the Korea National Institute of Scientific Investigation. At this computer vision system, an unidentified skull was caught by video-camcoder with the MPEG and a ante-mortem photograph was scanned by scanner. These two images were processed and superimposed using pixel processing. Recognition of the individual identification by anatomical references was performed on the two superimposed images. This image processing techniques for the superimposition of skull and ante-morterm photographs simplify used the previous approach taking skull photographs and developing it to the same size as the ante-mortem Photographs. This system using various image Processing techniques on computer screen, a more precise and time-saving superimposition technique could be able to be applied in the area of computer individual identification.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.5
• /
• pp.81-89
• /
• 2021

This study aimed to investigate the factors affecting Logistics capabilities for Logistics Service Providers in Vietnam. Researchers inherited and developed based on previous research to focus on analyzing and evaluating dynamics, measuring Logistics capabilities, and the factors affecting Logistics capabilities for Logistics Service Providers. The logistics capabilities Model is used based on three factors: customer demand management capability, innovation capability, and information management capability. The empirical analysis used data from the survey data of l90 managers of Logistics Service Providers in Hai Phong, Ho Chi Minh City, Da Nang, Hue, Hanoi with reliable tools (SPSS 26.0 software). The data were analyzed by frequencies, percentages, means, Pearson's Linear Correlation Coefficient, exploratory factor analysis, and multi-linear regression model based on the survey data. The research results identified the following factors affecting Logistics capabilities for Logistics Service Providers: innovation capability has the strongest impact on Logistics capabilities; customer demand management capability has the following strong effects on Logistics capabilities; and finally, information management capability that affects Logistics capabilities. There is also a positive relationship between all factors and Logistics capabilities. Several recommendations are further suggested to enhance to improve Logistics capabilities for Logistics Service Providers in Vietnam.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.731-734
• /
• 2009

In this paper, we propose the method the vehicle color recognizing in the image including a vehicle. In an image, the color feature vector of a vehicle is extracted and by using the backpropagation learning algorithm, that is the multi-layer perceptron, the recognized vehicle color. By using the RGB and HSI color model the feature vector used as the input of the backpropagation learning algorithm is the feature of the color used as the input of the neural network. The color of a vehicle recognizes as the white, the silver color, the black, the red, the yellow, the blue, and the green among the color of the vehicle most very much found out as 7 colors. By using the image including a vehicle for the performance evaluation of the method proposing, the color recognition performance was experimented.