• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.322-330
• /
• 2021

In modern aquaculture, mass mortality is a very important issue that determines the success of aquaculture business. If a fish disease is not detected at an early stage in the farm, the disease spreads quickly because the farm is a closed environment. Therefore, early detection of diseases is crucial to prevent mass mortality of fish raised in farms. Recently deep learning-based automatic identification of fish diseases has been widely used, but there are many difficulties in identifying objects due to insufficient images of fish diseases. Therefore, this paper suggests a method to generate a large number of fish disease images by synthesizing normal images and disease images using SinGAN deep learning model in order to to solve the lack of fish disease images. We generate images from the three most frequently occurring Paralichthys Olivaceus diseases such as Scuticociliatida, Vibriosis, and Lymphocytosis and compare them with the original image. In this study, a total of 330 sheets of scutica disease, 110 sheets of vibrioemia, and 110 sheets of limphosis were made by synthesizing 10 disease patterns with 11 normal halibut images, and 1,320 images were produced by quadrupling the images.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.11 no.2
• /
• pp.49-57
• /
• 2007

In fingerprints, singular regions including core or delta points have different directional characteristics from non-singular regions. Generally, the ridges of singular regions change more abruptly than those of nonsingular areas, thus in order to effectively enhance fingerprint images regardless of region, local ridge curvature information needs to be used. In this paper, we present an improved Directional Filter Bank (DFB)-based fingerprint image enhancement method that effectively takes advantage of such ridge curvature information. The proposed method first decomposes a fingerprint image into 8 directional subbands using the DFB and then classifies the image into background, low curvature, and high curvature regions using the directional energy estimates calculated from the subbands. Thereafter, the weight values for directional subband processing are determined using classification information and directional energy estimates. Finally, the enhanced image is obtained by synthesizing the processed subbands. The experimental results show that the proposed approach is effective in enhancing both singular and non-singular regions.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1347-1349
• /
• 1996

Most real image sequences contain multiple moving objects or multiple motions. In this paper, we segmented the moving objects with optical flow. Motion estimation by this method can estimate and compress the image sequences better than other methods such as block matching method. And, especially, we can make new image sequences by synthesizing the segmented objects. But, it takes too much time for motion estimation. And, it is not easy for a hardware implementation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.6
• /
• pp.3092-3107
• /
• 2019

Visible-infrared image fusion is a process of synthesizing an infrared image and a visible image into a fused image. This process synthesizes the complementary advantages of both images. The infrared image is able to capture a target object in dark or foggy environments. However, the utility of the infrared image is hindered by the blurry appearance of objects. On the other hand, the visible image clearly shows an object under normal lighting conditions, but it is not ideal in dark or foggy environments. In this paper, we propose a multi-guided filter and a real-time image fusion method. The proposed multi-guided filter is a modification of the guided filter for multiple guidance images. Using this filter, we propose a real-time image fusion method. The speed of the proposed fusion method is much faster than that of conventional image fusion methods. In an experiment, we compare the proposed method and the conventional methods in terms of quantity, quality, fusing speed, and flickering artifacts. The proposed method synthesizes 57.93 frames per second for an image size of $320{\times}270$. Based on our experiments, we confirmed that the proposed method is able to perform real-time processing. In addition, the proposed method synthesizes flicker-free video.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.12
• /
• pp.5073-5086
• /
• 2015

The rock fracture detection by image analysis is significant for fracture measurement and assessment engineering. The paper proposes a novel image segmentation algorithm for the centerline tracing of a rock fracture based on Hessian Matrix at Multi-scales and Steger algorithm. A traditional fracture detection method, which does edge detection first, then makes image binarization, and finally performs noise removal and fracture gap linking, is difficult for images of rough rock surfaces. To overcome the problem, the new algorithm extracts the centerlines directly from a gray level image. It includes three steps: (1) Hessian Matrix and Frangi filter are adopted to enhance the curvilinear structures, then after image binarization, the spurious-fractures and noise are removed by synthesizing the area, circularity and rectangularity; (2) On the binary image, Steger algorithm is used to detect fracture centerline points, then the centerline points or segments are linked according to the gap distance and the angle differences; and (3) Based on the above centerline detection roughly, the centerline points are searched in the original image in a local window along the direction perpendicular to the normal of the centerline, then these points are linked. A number of rock fracture images have been tested, and the testing results show that compared to other traditional algorithms, the proposed algorithm can extract rock fracture centerlines accurately.

• Journal of Internet Computing and Services
• /
• v.21 no.5
• /
• pp.67-73
• /
• 2020

In this paper, we present a CNN-based gesture recognition approach which reduces the memory burden of input data. Most of the neural network-based gesture recognition methods have used a sequence of frame images as input data, which cause a memory burden problem. We use a motion history image in order to define a meaningful gesture. The motion history image is a grayscale image into which the temporal motion information is collapsed by synthesizing silhouette images of a user during the period of one meaningful gesture. In this paper, we first summarize the previous traditional approaches and neural network-based approaches for gesture recognition. Then we explain the data preprocessing procedure for making the motion history image and the neural network architecture with three convolution layers for recognizing the meaningful gestures. In the experiments, we trained five types of gestures, namely those for charging power, shooting left, shooting right, kicking left, and kicking right. The accuracy of gesture recognition was measured by adjusting the number of filters in each layer in the proposed network. We use a grayscale image with 240 × 320 resolution which defines one meaningful gesture and achieved a gesture recognition accuracy of 98.24%.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.4
• /
• pp.859-864
• /
• 2018

This paper is about image improvement - we used the contrast ratio and the outline emphasis method after synthesizing two low quality images utilized by several low definition cameras. Two raspberry cameras were used to capture each image, and then we synthesized images with MATLAB program. After applying the mean computation (alignment, geometry, and harmony) to synthesized image, we extracted the cross-space. In the experiment of this study, we identified and compared the improvement consequences of extracted, synthesized image after applying outline emphasis(unsharpmask filter, highboost filter) and increasing contrast ratio (histogram uniformity, histogram stretching) to the original images.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.75-77
• /
• 2021

In order to find objects in an image through deep learning technology, an image dataset for learning is required. In order to increase the recognition rate of objects, a large amount of image learning data is required. It is difficult for individuals to build large amounts of datasets because it is expensive. This paper introduces a method for more easily constructing an image dataset including several sides of an object by photographing a rotating image. A method of constructing a dataset by placing an object on a rotating plate, photographing it, and dividing and synthesizing the captured images according to the needs is proposed.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.137-142
• /
• 2001

입체 시점 확장을 위하여 많은 양의 영상 데이터가 필요하다. 그러나 이를 전송하치 위해서는 전송량, 장치 등의 여러 어려움이 존재한다. 이에 소량의 영상 데이터를 보내고 수신 측에서 시점을 확장하는 방법으로 중간 영상 합성이 연구되고 있다. 중간 영상 합성을 위해서는 많은 방법들이 제안되었다 블록 매칭, 화소 기반 매칭, 에페폴라 방식, 옵티컬 플로워 등이 그것이다. 본 고에서는 위의 방법들 중에서 블록 매칭 방법을 기본으로, 블록을 생성하는 과정에서 고정 블록이 아닌 영상의 차분 신호를 이용하여 가변 블록을 생성하게 되며, 좌에서 우나 우에서 좌의 단방향이 아닌 양 방향으로 매칭하는 방법을 제안한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1996.06b
• /
• pp.77-81
• /
• 1996

In order to conform to the needs of effective program production in multimedia era, we are studying Desk Top Program Production system. With the DTPP, users can easily produce multimedia program including video, sound, and ancillary data, and freely handle video images synthesizing video components retrieved from video database. This paper describes the new program production system, DTPP and its key technologies such as cooperative program production via multimedia network, indexing and utilization of attribute information of images, and image segmentation and spatio-temporal editing.