• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.441-446
• /
• 2020

In this paper, we propose the α-Feature Map Scaling (α-FMS) method which extends the FMS method that was designed to enhance the discriminative power of feature maps of deep neural networks in Speaker Verification (SV) systems. The FMS derives a scale vector from a feature map and then adds or multiplies them to the features, or sequentially apply both operations. However, the FMS method not only uses an identical scale vector for both addition and multiplication, but also has a limitation that it can only add a value between zero and one in case of addition. In this study, to overcome these limitations, we propose α-FMS to add a trainable parameter α to the feature map element-wise, and then multiply a scale vector. We compare the performance of the two methods: the one where α is a scalar, and the other where it is a vector. Both α-FMS methods are applied after each residual block of the deep neural network. The proposed system using the α-FMS methods are trained using the RawNet2 and tested using the VoxCeleb1 evaluation set. The result demonstrates an equal error rate of 2.47 % and 2.31 % for the two α-FMS methods respectively.

• Journal of information and communication convergence engineering
• /
• v.12 no.2
• /
• pp.128-134
• /
• 2014

In this paper, we present a graphics processing unit (GPU)-based matching technique for the purpose of fast feature matching between different images. The scale invariant feature transform algorithm developed by Lowe for various feature matching applications, such as stereo vision and object recognition, is computationally intensive. To address this problem, we propose a matching technique optimized for GPUs to perform computations in less time. We optimize GPUs for fast computation of keypoints to make our system quick and efficient. The proposed method uses a self-organizing map feature matching technique to perform efficient matching between the different images. The experiments are performed on various image sets to examine the performance of the system under varying conditions, such as image rotation, scaling, and blurring. The experimental results show that the proposed algorithm outperforms the existing feature matching methods, resulting in fast feature matching due to the optimization of the GPU.

• Journal of The Institute of Information and Telecommunication Facilities Engineering
• /
• v.9 no.2
• /
• pp.73-79
• /
• 2010

The most popular technique for image retrieval in a heterogeneous collection of color images is the comparison of images based on their color histogram. The color histogram describes the distribution of colors in the color space of a color image. In the most image retrieval systems, the color histogram is used to compute similarities between the query image and all the images in a database. But, small changes in the resolution, scaling, and illumination may cause important modifications of the color histogram, and so two color images may be considered to be very different from each other even though they have completely related semantics. A new method of color feature representation based on the 3-dimensional RGB color map is proposed to improve the defects of the color histogram. The proposed method is based on the three 2-dimensional projection map evaluated by projecting the RGB color space on the RG, GB, and BR surfaces. The experimental results reveal that the proposed is less sensitive to small changes in the scene and that achieve higher retrieval performances than the traditional color histogram.

• Journal of information and communication convergence engineering
• /
• v.2 no.2
• /
• pp.123-127
• /
• 2004

The most popular technique for image retrieval in a heterogeneous collection of color images is the comparison of images based on their color histogram. The color histogram describes the distribution of colors in the color space of a color image. In the most image retrieval systems, the color histogram is used to compute similarities between the query image and all the images in a database. But, small changes in the resolution, scaling, and illumination may cause important modifications of the color histogram, and so two color images may be considered to be very different from each other even though they have completely related semantics. A new method of color feature representation based on the 3-dimensional RGB color map is proposed to improve the defects of the color histogram. The proposed method is based on the three 2-dimensional projection map evaluated by projecting the RGB color space on the RG, GB, and BR surfaces. The experimental results reveal that the proposed is less sensitive to small changes in the scene and that achieve higher retrieval performances than the traditional color histogram.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.3
• /
• pp.665-676
• /
• 2014

As social media draws attention as a business tool, organizations, large or small, are trying to exploit social media in their business. However, lack of understanding the characteristics of each social media led them to develop a naive strategy for dealing with social media. Thus, this study aims to deepen the understanding by comparatively analyzing how social media users perceive (the image of) each social media. Facebook, Twitter, YouTube, Blogs, Communities and Cyworld were chosen for our study and data from 132 respondents were analyzed using multidimensional scaling technique. The results show that there are meaningful differences in users' perception of social media attributes, which are grouped into four; information feature, motivation, promotion tool, usability. It is also analyzed whether such differences can be found between male and female users. (Such differences are also analyzed in both male and female users' perceptions.) Further, we discuss some implications of the research results for both practitioners and researchers.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.6
• /
• pp.309-317
• /
• 2022

In this paper, we propose a machine learning-based copy-move forgery detection network with dual branches. Because the rotation or scaling operation is frequently involved in copy-move forger, the conventional convolutional neural network is not effectively applied in detecting copy-move tampering. Therefore, we divide the input into rotation-invariant and scaling-invariant features based on the wavelet coefficients. Each of the features is input to different branches having the same structure, and is fused in the combination module. Each branch comprises feature extraction, correlation, and mask decoder modules. In the proposed network, VGG16 is used for the feature extraction module. To check similarity of features generated by the feature extraction module, the conventional correlation module used. Finally, the mask decoder model is applied to develop a pixel-level localization map. We perform experiments on test dataset and compare the proposed method with state-of-the-art tampering localization methods. The results demonstrate that the proposed scheme outperforms the existing approaches.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.29 no.4
• /
• pp.301-308
• /
• 2016

In this study, a novel method referred as non-marker vision-based displacement measuring system(NVDMS) was introduced in order to measure the displacement of structure. There are two distinct differences between proposed NVDMS and existing vision-based displacement measuring system(VDMS). First, the NVDMS extracts the pixel coordinates of the structure using a feature point not a marker. Second, in the NVDMS, the scaling factor in order to convert the coordinates of a feature points from pixel value to physical value can be calculated by using the external conditions between the camera and the structure, which are distance, angle, and focal length, while the scaling factor for VDMS can be calculated by using the geometry of marker. The free vibration test using the three-stories scale model was conducted in order to analyze the reliability of the displacement data obtained from the NVDMS by comparing the reference data obtained from laser displacement sensor(LDS), and the measurement of dynamic characteristics was proceed using the displacement data. The NVDMS can accurately measure the dynamic displacement of the structure without the marker, and the high reliability of the dynamic characteristics obtained from the NVDMS are secured.

• Korean Journal of Ecology and Environment
• /
• v.41 no.spc
• /
• pp.1-10
• /
• 2008

We patterned water quality of agricultural reservoirs according to the differences of six physico-chemical environmental factors (TN, TP, DO, BOD, COD, and SS) using four different ordination methods: Principal Components Analysis (PCA), Detrended Correspondence Analysis (DCA), Nonmetric Multidimensional Scaling (NMS), and Isometric Feature Mapping (Isomap). The data set was obtained from the water quality monitoring networks operated by the Ministry of Agriculture and Forestry and the Ministry of Environments. Chlorophyll-${\alpha}$ displayed the highest correlation with COD, followed by TP, BOD, SS, and TN (p<0.01), while negatively correlated with altitude and bank height of the reservoirs (p<0.01). Although four different ordination methods similarly patterned the reservoirs according to the gradient of nutrient concentration, PCA and NMS appeared to be the most efficient methods to pattern water quality of reservoirs based on the explanation power. Considering variable scores in the ordination map, the concentration of nutrients was positively correlated with Chl-${\alpha}$, while negatively correlated with altitude and bank height. These ordination methods may help to pattern agricultural reservoirs according to their water quality characteristics.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.3 s.309
• /
• pp.30-38
• /
• 2006

In this paper, we improved to drops recognition rate according to distance using distance and depth information with 3D from stereo face images. A monocular face image has problem to drops recognition rate by uncertainty information such as distance of an object, size, moving, rotation, and depth. Also, if image information was not acquired such as rotation, illumination, and pose change for recognition, it has a very many fault. So, we wish to solve such problem. Proposed method consists of an eyes detection algorithm, analysis a pose of face, md principal component analysis (PCA). We also convert the YCbCr space from the RGB for detect with fast face in a limited region. We create multi-layered relative intensity map in face candidate region and decide whether it is face from facial geometry. It can acquire the depth information of distance, eyes, and mouth in stereo face images. Proposed method detects face according to scale, moving, and rotation by using distance and depth. We train by using PCA the detected left face and estimated direction difference. Simulation results with face recognition rate of 95.83% (100cm) in the front and 98.3% with the pose change were obtained successfully. Therefore, proposed method can be used to obtain high recognition rate with an appropriate scaling and pose change according to the distance.

• Korean Journal of Remote Sensing
• /
• v.31 no.5
• /
• pp.449-459
• /
• 2015

The conventional National Forest Inventory(NFI)-based forest carbon stock estimation method is suitable for national-scale estimation, but is not for regional-scale estimation due to the lack of NFI plots. In this study, for the purpose of regional-scale carbon stock estimation, we created grid-based forest carbon stock maps using spatial ancillary data and two types of up-scaling methods. Chungnam province was chosen to represent the study area and for which the $5^{th}$ NFI (2006~2009) data was collected. The first method (method 1) selects forest type map as ancillary data and uses regression model for forest carbon stock estimation, whereas the second method (method 2) uses satellite imagery and k-Nearest Neighbor(k-NN) algorithm. Additionally, in order to consider uncertainty effects, the final AGB carbon stock maps were generated by performing 200 iterative processes with Monte Carlo simulation. As a result, compared to the NFI-based estimation(21,136,911 tonC), the total carbon stock was over-estimated by method 1(22,948,151 tonC), but was under-estimated by method 2(19,750,315 tonC). In the paired T-test with 186 independent data, the average carbon stock estimation by the NFI-based method was statistically different from method2(p<0.01), but was not different from method1(p>0.01). In particular, by means of Monte Carlo simulation, it was found that the smoothing effect of k-NN algorithm and mis-registration error between NFI plots and satellite image can lead to large uncertainty in carbon stock estimation. Although method 1 was found suitable for carbon stock estimation of forest stands that feature heterogeneous trees in Korea, satellite-based method is still in demand to provide periodic estimates of un-investigated, large forest area. In these respects, future work will focus on spatial and temporal extent of study area and robust carbon stock estimation with various satellite images and estimation methods.