• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1098-1101
• /
• 2004

The ordinary stereo image of an object consists of data of left and right views. Therefore, the left and right image pairs have to be transmitted simultaneously in order to display 3-dimentional video at the remote site. However, due to the twice data in comparing with a monoscopic image of the same object, it needs to be compressed for fast transmission and resource saving. Hence, it needs an effective coding algorithm for compressing stereo image. It was found previously that compressing left and right frames independently will achieve the compression ratio lower than compressing by utilizing the spatial redundancy between both frames. Therefore, in this paper, we study the stereo image compression technique based on the multiresolution wavelet transform using varied disparity-block size for estimation and compensation. The size of disparity-block in the stereo pair subbands are scaling on a coarse-to-fine wavelet coefficients strategy. Finally, the reference left image and residual right image after disparity estimation and compensation are coded by using SPIHT coding. The considered method demonstrates good performance in both PSNR measures and visual quality for stereo image.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3745-3761
• /
• 2020

Low-rank representation methods already achieve many applications in the image reconstruction. However, for high-gradient image patches with rich texture details and strong edge information, it is difficult to find sufficient similar patches. Existing low-rank representation methods usually destroy image critical details and fail to preserve edge structure. In order to promote the performance, a new representation-based image super-resolution reconstruction method is proposed, which combines gradient domain guided image filter with the structure-constrained low-rank representation so as to enhance image details as well as reveal the intrinsic structure of an input image. Firstly, we extract the gradient domain guided filter of each atom in high resolution dictionary in order to acquire high-frequency prior information. Secondly, this prior information is taken as a structure constraint and introduced into the low-rank representation framework to develop a new model so as to maintain the edges of reconstructed image. Thirdly, the approximate optimal solution of the model is solved through alternating direction method of multipliers. After that, experiments are performed and results show that the proposed algorithm has higher performances than conventional state-of-the-art algorithms in both quantitative and qualitative aspects.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.192-194
• /
• 2003

Since the details in quasi-homogeneous region will be destroyed from the conventional global image enhancement method such as histogram equalization. This defect is caused by the saturation of gray level in equalization process. So the local histogram equalization for each quasi-homogeneous region will be used in order to improve the details in the region itself. To obtain the quasi- homogeneous regions, the original image must be segmented. Here we applied the watershed transform to the interesting image. Since the watershed transform is based on mathematical morphology, therefore, the regions touch can be effectively separated. Hence two adjacent regions which have the similar gray pixels will be split off. The process will be independently applied to three different spectral images. Then three different colors are assigned to each processed image in order to produce a color composite image. By the proposed algorithm, the result image shows the better perception on image details. Therefore, the high efficiency of image classification can be obtained by using this color image.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.8
• /
• pp.2749-2763
• /
• 2021

The desirable result of infrared (IR) and visible (VIS) image fusion should have textural details from VIS images and salient targets from IR images. However, detail information in the dark regions of VIS image has low contrast and blurry edges, resulting in performance degradation in image fusion. To resolve the troubles of fuzzy details in dark regions of VIS image fusion, we have proposed a method of reflectance estimation for IR and VIS image fusion. In order to maintain and enhance details in these dark regions, dark region approximation (DRA) is proposed to optimize the Retinex model. With the improved Retinex model based on DRA, quasi-Newton method is adopted to estimate the reflectance of a VIS image. The final fusion outcome is obtained by fusing the DRA-based reflectance of VIS image with IR image. Our method could simultaneously retain the low visibility details in VIS images and the high contrast targets in IR images. Experiment statistic shows that compared to some advanced approaches, the proposed method has superiority on detail preservation and visual quality.

• Korean Journal of Remote Sensing
• /
• v.2 no.1
• /
• pp.35-47
• /
• 1986

The progress in computer technology has significantly improved the capabilities of the microcomputer image processing systems and brought down their hardware costs. This on-going trend of technological development seems to bring further substantive improvements in microcomputer image processing and decreasing hardware costs. The technical development in microcomputer image processing system including VLSI technology, semiconductor memory, disk and tape storage, and image display subsystems have been reviewed and their future trend have been projected. The impact of this technology to the development of image processing has been assessed in the time period of immediate future (2-3 years) and near future (5 years).

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.451-454
• /
• 2003

A new query method, called query by visual keys, is proposed to aim easy operation and efficient region-based image retrieval (RBIR). Visual keys are constructed from representative regions/subimages in a given image database, and the database is indexed with visual keys. A system on PC is presented, where text retrieval techniques are applied to the image retrieval with visual keys. Experimental results show that one retrieval is done within 4ms and that the proposed system achieves the comparable retrieval precision (with user-friendly operation and low computational cost) to conventional region based image retrieval systems

• Smart Structures and Systems
• /
• v.6 no.4
• /
• pp.389-403
• /
• 2010

By using image recognition technology, this paper presents a new fault diagnosis method for rotating machinery with artificial immune algorithm. This method focuses on the vibration state parameter image. The main contribution of this paper is as follows: firstly, 3-D spectrum is created with raw vibrating signals. Secondly, feature information in the state parameter image of rotating machinery is extracted by using Wavelet Packet transformation. Finally, artificial immune algorithm is adopted to diagnose rotating machinery fault. On the modeling of 600MW turbine experimental bench, rotor's normal rate, fault of unbalance, misalignment and bearing pedestal looseness are being examined. It's demonstrated from the diagnosis example of rotating machinery that the proposed method can improve the accuracy rate and diagnosis system robust quality effectively.

• Journal of Ocean Engineering and Technology
• /
• v.36 no.1
• /
• pp.32-40
• /
• 2022

Underwater optical images face various limitations that degrade the image quality compared with optical images taken in our atmosphere. Attenuation according to the wavelength of light and reflection by very small floating objects cause low contrast, blurry clarity, and color degradation in underwater images. We constructed an image data of the Korean sea and enhanced it by learning the characteristics of underwater images using the deep learning techniques of CycleGAN (cycle-consistent adversarial network), UGAN (underwater GAN), FUnIE-GAN (fast underwater image enhancement GAN). In addition, the underwater optical image was enhanced using the image processing technique of Image Fusion. For a quantitative performance comparison, UIQM (underwater image quality measure), which evaluates the performance of the enhancement in terms of colorfulness, sharpness, and contrast, and UCIQE (underwater color image quality evaluation), which evaluates the performance in terms of chroma, luminance, and saturation were calculated. For 100 underwater images taken in Korean seas, the average UIQMs of CycleGAN, UGAN, and FUnIE-GAN were 3.91, 3.42, and 2.66, respectively, and the average UCIQEs were measured to be 29.9, 26.77, and 22.88, respectively. The average UIQM and UCIQE of Image Fusion were 3.63 and 23.59, respectively. CycleGAN and UGAN qualitatively and quantitatively improved the image quality in various underwater environments, and FUnIE-GAN had performance differences depending on the underwater environment. Image Fusion showed good performance in terms of color correction and sharpness enhancement. It is expected that this method can be used for monitoring underwater works and the autonomous operation of unmanned vehicles by improving the visibility of underwater situations more accurately.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2008.10a
• /
• pp.295-298
• /
• 2008

We developed a novel PVA pixel design for mobile application with excellent off-axis image quality and optical performance by introducing Active Level Shift technology and optimizing pixel structure. Our new pixel design enables better off-axis image quality without sacrificing other optical properties compared with a conventional mPVA structure.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.894-907
• /
• 2022

The features extracted by convolutional neural networks are more descriptive of images than traditional features, and their convolutional layers are more suitable for retrieving images than are fully connected layers. The convolutional layer features will consume considerable time and memory if used directly to match an image. Therefore, this paper proposes a feature weighting and region integration method for convolutional layer features to form global feature vectors and subsequently use them for image matching. First, the 3D feature of the last convolutional layer is extracted, and the convolutional feature is subsequently weighted again to highlight the edge information and position information of the image. Next, we integrate several regional eigenvectors that are processed by sliding windows into a global eigenvector. Finally, the initial ranking of the retrieval is obtained by measuring the similarity of the query image and the test image using the cosine distance, and the final mean Average Precision (mAP) is obtained by using the extended query method for rearrangement. We conduct experiments using the Oxford5k and Paris6k datasets and their extended datasets, Paris106k and Oxford105k. These experimental results indicate that the global feature extracted by the new method can better describe an image.