• Communications for Statistical Applications and Methods
• /
• v.10 no.2
• /
• pp.457-469
• /
• 2003

In this paper, we have proposed the efficient algorithm that can segment the video scene change using a various statistical characteristics obtained from by applying the wavelet transformation for each frames. Our method firstly extracts the histogram features from low frequency subband of wavelet-transformed image and then uses these features to detect the abrupt scene change. Second, it extracts the edge information from applying the mesh method to the high frequency subband of transformed image. We quantify the extracted edge information as the values of variance characteristic of each pixel and use these values to detect the gradual scene change. And we have also proposed an algorithm how extract the proper key frame from segmented video scene. Experiment results show that the proposed method is both very efficient algorithm in segmenting video frames and also is to become the appropriate key frame extraction method.

• Journal of Cadastre & Land InformatiX
• /
• v.53 no.2
• /
• pp.5-18
• /
• 2023

As the development of drones and sensors accelerates, new services and values are created by fusing data acquired from various sensors mounted on drone. However, the construction of spatial information through data fusion is mainly constructed depending on the image, and the quality of data is determined according to the specification and performance of the hardware. In addition, it is difficult to utilize it in the actual field because expensive equipment is required to construct spatial information of high-quality. In this study, super-resolution was performed by applying deep learning to low-resolution images acquired through RGB and THM cameras mounted on a drone, and quantitative evaluation and feature point extraction were performed on the generated high-resolution images. As a result of the experiment, the high-resolution image generated by super-resolution was maintained the characteristics of the original image, and as the resolution was improved, more features could be extracted compared to the original image. Therefore, when generating a high-resolution image by applying a low-resolution image to an super-resolution deep learning model, it is judged to be a new method to construct spatial information of high-quality without being restricted by hardware.

• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.376-381
• /
• 1998

In this study, we was measured the radiance reflectance by using multi-spectral image of low resolution camera(LRC) which will be loaded in the multi-purpose satellite(KOMPSAT) to use the data in analyzing water pollution. Also we investigated the possibility of extraction of water quality factors in rivers and water body by using high resolution remote sensing data such as Airborne MSS. Especially, we tried to extract the environmental factors related with eutrophication, and also tried to develop the process technique and the radiance feature of reflectance related with eutrophication. The results were summarized as follows: First, the spectrum of sun's rays which reaches the surface of the earth was consistent with visible rays bands of 0.4${\mu}{\textrm}{m}$~0.7${\mu}{\textrm}{m}$ and about 50% of total quantity of radiation were there. And at around 0.5${\mu}{\textrm}{m}$ of green spectral band in visible rays bands, the spectrum was highest. Second, as a result of the radiance reflectance Chlorophyll-a represented high spectral reflectance mainly around 0.52${\mu}{\textrm}{m}$ of green spectral band, and suspended sediments and turbidity represented high spectral reflectance at 0.8${\mu}{\textrm}{m}$ and at 0.57${\mu}{\textrm}{m}$ each. Third, as a result of the water quality analysis by using Airborne MSS, Chlorophyll-a could have a distribution chart when carried out ratio of B3 and BS to B7. And Band 7 was useful for making the distribution chart of suspended sediments. And when we carried out PCA, suspended sediments and turbidity had distributions at PC 1 , PC 4 each similarly to ground truth data. Above results can be changed according to the change of season and time. Therefore, in order to analyze more exactly the environmental factors of water quality by using LRC data, we need to investigate constantly the ground truth data and the radiance feature of reflectance of water body. Afterward in this study, we will constantly analyze the radiance feature of the surface of water in water body by measuring the on-the-spot radiance reflectance and using low resolution satellite image(SeaWiFs). Besides, we will gather the data of water quality analysis in water body and analyze the pattern of water pollution.

• Journal of Korea Multimedia Society
• /
• v.8 no.8
• /
• pp.1057-1068
• /
• 2005

This paper proposes a real-time face detection system which detects multiple faces from low resolution video such as web-camera video. First, It finds face region candidates by using AdaBoost based object detection method which selects a small number of critical features from a larger set. Next, it generates reduced feature vector for each face region candidate by using principle component analysis. Finally, it classifies if the candidate is a face or non-face by using SVM(Support Vector Machine) based binary classification. According to experiment results, the proposed method achieves real-time face detection from low resolution video. Also, it reduces the false detection rate than existing methods by using PCA and SVM based face classification step.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.8
• /
• pp.74-86
• /
• 1994

In this paper a hierarchical stereo matching algorithm to obtain the disparity in wavelet transformed domain by using locally adaptive window and weights is proposed. The pyramidal structure obtained by wavelet transform is used to solve the loss of information which the conventional Gaussian or Laplacian pyramid have. The wavelet transformed images are decomposed into the blurred image the horizontal edges the vertical edges and the diagonal edges. The similarity between each wavelet channel of left and right image determines the relative importance of each primitive and make the algorithm perform the area-based and feature-based matching adaptively. The wavelet transform can extract the features that have the dense resolution as well as can avoid the duplication or loss of information. Meanwhile the variable window that needs to obtain precise and stable estimation of correspondense is decided adaptively from the disparities estimated in coarse resolution and LL(low-low) channel of wavelet transformed stereo image. Also a new relaxation algorithm that can reduce the false match without the blurring of the disparity edge is proposed. The experimental results for various images show that the proposed algorithm has good perfpormance even if the images used in experiments have the unfavorable conditions.

• Journal of Korea Multimedia Society
• /
• v.25 no.10
• /
• pp.1395-1403
• /
• 2022

Lately, over 4K high definition and high dynamic range (HDR) display devices are popularized, various interpolation and HDR methods have been researched to expand the size and the dynamic range. Since most of the legacy low resolution (LR) images require both an interpolation and a HDR tone mapping methods, the two processes should be subsequently applied. Therefore, the proposed algorithm presents a HDR up-scaling algorithm using undecimated wavelet transform and Retinex method, which transfers a LR image of low dynamic range (LDR) into the high resolution (HR) with HDR. The proposed algorithm consists of an up-scaling scheme increasing the image size and a tone mapping scheme expanding the dynamic range. The up-scaling scheme uses the undecimated version of the simplest Haar wavelet analysis for the 8-directional interpolation and the change region is extracted during the analysis. This region information is utilized in controlling the surround functions' size of the proposed tone mapping using MSRCR, to enhance the pixels of around the edges that are dominant feature of the subjective image quality. As the results, the proposed algorithm can apply an up-scaling and tone mapping processes in accordance with the type of pixel.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4326-4344
• /
• 2021

The SinGAN is one of generative adversarial networks that can be trained on a single nature image. It has poor ability to learn more global features from nature image, and losses much local detail information when it generates arbitrary size image sample. To solve the problem, a non-linear function is firstly proposed to control downsampling ratio that is ratio between the size of current image and the size of next downsampled image, to increase the ratio with increase of the number of downsampling. This makes the low-resolution images obtained by downsampling have higher proportion in all downsampled images. The low-resolution images usually contain much global information. Therefore, it can help the model to learn more global feature information from downsampled images. Secondly, the attention mechanism is introduced to the generative network to increase the weight of effective image information. This can make the network learn more local details. Besides, in order to make the output image more natural, the TVLoss function is introduced to the loss function of SinGAN, to reduce the difference between adjacent pixels and smear phenomenon for the output image. A large number of experimental results show that our proposed model has better performance than other methods in generating random samples with fixed size and arbitrary size, image harmonization and editing.

• Journal of the Korean Society of Visualization
• /
• v.21 no.1
• /
• pp.110-118
• /
• 2023

Characterizing the extensional rheological properties of non-Newtonian fluids is crucial in many industrial processes, such as inkjet printing, injection molding, and fiber engineering. However, educational institutions and research laboratories with budget constraints have limited access to an expensive commercial extensional rheometer. In this study, we developed a custom-made extensional rheometer using a CO₂ laser cutting machine and 3D printer. Furthermore, we utilized a smartphone with a low-cost microscopic lens for achieving a high spatial resolution of images. The aqueous polyethylene-oxide (PEO) solutions and a Boger fluid were prepared to characterize their extensional properties. A transition from a visco-capillary to an elasto-capillary regime was observed clearly through the developed rheometer. The extensional relaxation time and viscosity of the aqueous PEO solutions with a zero-shear viscosity of over 300 mPa·s could be quantified in the elasto-capillary regime. The extensional properties of the solutions with relatively small zero shear viscosity could be calculated using a smartphone's slow-motion feature with increasing temporal resolution of the images.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.2059-2064
• /
• 2004

Texture analysis is an important role for automatic visual insfection. This paper presents an application of wavelet extension and Gray level co-occurrence matrix (GLCM) for detection of defect encountered in textured images. Texture characteristic in low quality images is not to easy task to perform caused by noise, low frequency and small dimension. In order to solve this problem, we have developed a procedure called wavelet image extension. Wavelet extension procedure is used to determine the frequency bands carrying the most information about the texture by decomposing images into multiple frequency bands and to form an image approximation with higher resolution. Thus, wavelet extension procedure offers the ability to robust feature extraction in images. Then the features are extracted from the co-occurrence matrices computed from the sub-bands which performed by partitioning the texture image into sub-window. In the detection part, Mahalanobis distance classifier is used to decide whether the test image is defective or non defective.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.4
• /
• pp.410-415
• /
• 2006

The SVDD(support vector data description) is one of the most important one-class support vector learning methods, which depends on the strategy of utilizing the balls defined on the feature space to discriminate the normal data from all other possible abnormal objects. This paper addresses on the extension of the SVDD method toward the problem of recovering the normal contents from the data contaminated with noises. The validity of the proposed de-noising method is shown via application to recovering the high-resolution images from the low-resolution images based on the high-resolution training data.