• Journal of the Korea Society of Computer and Information
• /
• v.24 no.10
• /
• pp.91-99
• /
• 2019

In this paper, we propose partial denoising boundary matching based on an index for faster matching in very large image databases. Attempts have recently been made to convert boundary images to time-series with the objective of solving the partial denoising problem in boundary matching. In this paper, we deal with the disk I/O overhead problem of boundary matching to support partial denoising in a large image database. Although the solution to the problem superficially appears trivial as it only applies indexing techniques to boundary matching, it is not trivial since multiple indexes are required for every possible denoising parameters. Our solution is an efficient index-based approach to partial denoising using $R^*-tree$ in boundary matching. The results of experiments conducted show that our index-based matching methods improve search performance by orders of magnitude.

• Journal of Broadcast Engineering
• /
• v.19 no.6
• /
• pp.854-865
• /
• 2014

This paper proposes a method to generate a stereoscopic image pair from a digital hologram by considering the situation that digital hologram data is serviced but the end-user does not have the proper display equipment, etc. We use Fresnel transform as the method to convert a digital hologram into an image. Each image of the stereoscopic image pair uses a part of the given digital hologram and the sizes of the two partial digital holograms for the two images are chosen to be the same. Here, the size of the image is adjusted by the size of the partial digital hologram and the disparity between the pair images is adjusted by the distance between the centers of the two partial hologram. This paper also deals with how to adjust the size and the disparity of the images. In this paper the generated stereoscopic images are implemented as an anaglyphic display type to confirm the feeling of distance by wearing the red-blue glasses.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.1
• /
• pp.436-450
• /
• 2017

Recently, the method based on fractional order partial differential equation has been used in image processing. Usually, the optional order of fractional differentiation is determined by a lot of experiments. In this paper, a denoising model is proposed based on adaptive fractional order anisotropic diffusion. In the proposed model, the complexity of the local image texture is reflected by the local variance, and the order of the fractional differentiation is determined adaptively. In the process of the adaptive fractional order model, the discrete Fourier transform is applied to compute the fractional order difference as well as the dynamic evolution process. Experimental results show that the peak signal-to-noise ratio (PSNR) and structural similarity index measurement (SSIM) of the proposed image denoising algorithm is better than that of other some algorithms. The proposed algorithm not only can keep the detailed image information and edge information, but also obtain a good visual effect.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.1-15
• /
• 2022

The MobileNetV3 is specially designed for mobile devices with limited memory and computing power. To reduce the network parameters and improve the network inference speed, a new lightweight network is proposed based on MobileNetV3. Firstly, to reduce the computation of residual blocks, a partial residual structure is designed by dividing the input feature maps into two parts. The designed partial residual structure is used to replace the residual block in MobileNetV3. Secondly, a dual-path feature extraction structure is designed to further reduce the computation of MobileNetV3. Different convolution kernel sizes are used in the two paths to extract feature maps with different sizes. Besides, a transition layer is also designed for fusing features to reduce the influence of the new structure on accuracy. The CIFAR-100 dataset and Image Net dataset are used to test the performance of the proposed partial residual structure. The ResNet based on the proposed partial residual structure has smaller parameters and FLOPs than the original ResNet. The performance of improved MobileNetV3 is tested on CIFAR-10, CIFAR-100 and ImageNet image classification task dataset. Comparing MobileNetV3, GhostNet and MobileNetV2, the improved MobileNetV3 has smaller parameters and FLOPs. Besides, the improved MobileNetV3 is also tested on CPU and Raspberry Pi. It is faster than other networks

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.2
• /
• pp.291-298
• /
• 2022

A generative adversarial network (GAN) is a network in which two internal neural networks (generative network and discriminant network) learn while competing with each other. The generator creates an image close to reality, and the delimiter is programmed to better discriminate the image of the constructor. This technology is being used in various ways to create, transform, and restore the entire image X into another image Y. This paper describes a method that can be forged into another object naturally, after extracting only a partial image from the original image. First, a new image is created through the previously trained DCGAN model, after extracting only a partial image from the original image. The original image goes through a process of naturally combining with, after re-styling it to match the texture and size of the original image using the overall style transfer technique. Through this study, the user can naturally add/transform the desired object image to a specific part of the original image, so it can be used as another field of application for creating fake images.

• Journal of the Society of Naval Architects of Korea
• /
• v.59 no.2
• /
• pp.118-124
• /
• 2022

Marine environment analysis and ship motion prediction during ship navigation are important technologies for safe and economical operation of autonomous ships. As a marine environment analysis technology, there is a method of analyzing waves by measuring the sea states through images acquired based on radar(radio detection and ranging) signal. However, in the process of deriving marine environment information from radar images, noises generated by external factors are included, limiting the interpretation of the marine environment. Therefore, image processing for noise removal is required. In this study, image inpainting by partial convolutional neural network model is proposed as a method to remove noises and reconstruct radar images.

• The KIPS Transactions:PartB
• /
• v.15B no.2
• /
• pp.81-86
• /
• 2008

This paper discusses the problem of partial object recognition in image databases. We propose the method to reconstruct and estimate partially occluded shapes and regions of objects in images from overlapping and cutting. We present the robust method for recognizing partially occluded objects based on symmetry properties, which is based on an ellipse of objects. Our method provides simple techniques to reconstruct occluded regions via a region copy using the symmetry axis within an object. Since our method relies on reconstruction of the object based on the symmetry rather than statistical estimates, it has proven to be remarkably robust in recognizing partially occluded objects in the presence of scale changes, rotation, and viewpoint changes.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.431-436
• /
• 2018

In this paper, a simple but effective algorithm to reduce the computational complexity of thumbnail generation and to improve image quality without aliasing artifacts is proposed. For the high speed decoding, the proposed algorithm performs partial decoding per $4{\times}4$ boundary in TU(Transform Unit), and preforms TU boundary in PU(Prediction Unit). The proposed method defines the weights based on intra prediction directions and estimates the thumbnail pixel by using that weights. this method remains thumbnail extraction time and improves thumbnail image quality compared with conventional algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.10
• /
• pp.4108-4125
• /
• 2015

This paper presents a scalable coding method for depth images by considering the quality of synthesized images in virtual views. First, we design a new edge detection algorithm that is based on calculating the depth difference between two neighboring pixels within the depth map. By choosing different thresholds, this algorithm generates a scalable bit stream that puts larger depth differences in front, followed by smaller depth differences. A scalable scheme is also designed for coding depth pixels through a layered sampling structure. At the receiver side, the full-resolution depth image is reconstructed from the received bits by solving a partial-differential-equation (PDE). Experimental results show that the proposed method improves the rate-distortion performance of synthesized images at virtual views and achieves better visual quality.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.8
• /
• pp.1553-1559
• /
• 2017

This paper proposes a lane departure detection algorithm using a single camera equipped in front of a vehicle. The proposed algorithm generates a partial top-view image for a small ROI (region of interest) designated on the top-view space form the image acquired by the camera, detects lanes on the small partial top-view image, and makes a decision on the lane departure by checking overlap between the pre-assigned virtual vehicle and the detected lanes. The proposed algorithm also includes the removal of lines occurred by road symbols (noises) disturbing the lane departure detection between lanes and the prediction of lost lanes using lane information of previous fames. In lane departure detection test using real road videos, the proposed algorithm makes the right decision of 99.0% in lane keeping conditions and 94.7% in lane departure conditions.