• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.2C
• /
• pp.16-24
• /
• 2005

In this paper, we proposed a face tracking algorithm for a viewpoint adaptive multi-view synthesis system. The original scene captured by a depth camera contains a texture image and 8 bit gray-scale depth map. From this original image, multi-view images can be synthesized which correspond to viewer's position by using geometrical transformation such as a rotation and a translation. The proposed face tracking technique gives a motion parallax cue by different viewpoints and view angles. In the proposed algorithm, tracking of viewer's dominant face initially established from camera by using statistical characteristics of face colors and deformable templates is done. As a result, we can provide motion parallax cue by detecting viewer's dominant face area and tracking it even under a heterogeneous background and can successfully display the synthesized sequences.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.1
• /
• pp.23-28
• /
• 2017

Shape from focus (SFF) is a technique used to reconstruct 3D shape of objects from a sequence of images obtained at different focus settings of the lens. In this paper, a new shape from focus method for 3D reconstruction of microscopic objects is described, which is based on gradient operator in Mathematical Morphology. Conventionally, in SFF methods, a single focus measure is used for measuring the focus quality. Due to the complex shape and texture of microscopic objects, single measure based operators are not sufficient, so we propose morphological operators with multi-structuring elements for computing the focus values. Finally, an optimal focus measure is obtained by combining the response of all focus measures. The experimental results showed that the proposed algorithm has provided more accurate depth maps than the existing methods in terms of three-dimensional shape recovery.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.45-52
• /
• 2021

In this paper, we propose a prediction model for osteopenia and osteoporosis based on a convolutional neural network(CNN) using computed tomography(CT) images. In a single CT image, CNN had a limitation in utilizing important local features for diagnosis. So we propose a compound model which has two identical structures. As an input, two different texture images are used, which are converted from a single normalized CT image. The two networks train different information by using dissimilarity loss function. As a result, our model trains various features in a single CT image which includes important local features, then we ensemble them to improve the accuracy of predicting osteopenia and osteoporosis. In experiment results, our method shows an accuracy of 77.11% and the feature visualize of this model is confirmed by using Grad-CAM.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1445-1456
• /
• 2018

Environment perception and three-dimensional (3D) reconstruction tasks are used to provide unmanned ground vehicle (UGV) with driving awareness interfaces. The speed of obstacle segmentation and surrounding terrain reconstruction crucially influences decision making in UGVs. To increase the processing speed of environment information analysis, we develop a CPU-GPU hybrid system of automatic environment perception and 3D terrain reconstruction based on the integration of multiple sensors. The system consists of three functional modules, namely, multi-sensor data collection and pre-processing, environment perception, and 3D reconstruction. To integrate individual datasets collected from different sensors, the pre-processing function registers the sensed LiDAR (light detection and ranging) point clouds, video sequences, and motion information into a global terrain model after filtering redundant and noise data according to the redundancy removal principle. In the environment perception module, the registered discrete points are clustered into ground surface and individual objects by using a ground segmentation method and a connected component labeling algorithm. The estimated ground surface and non-ground objects indicate the terrain to be traversed and obstacles in the environment, thus creating driving awareness. The 3D reconstruction module calibrates the projection matrix between the mounted LiDAR and cameras to map the local point clouds onto the captured video images. Texture meshes and color particle models are used to reconstruct the ground surface and objects of the 3D terrain model, respectively. To accelerate the proposed system, we apply the GPU parallel computation method to implement the applied computer graphics and image processing algorithms in parallel.

• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.15-22
• /
• 2020

In this paper, we proposed a deep learning based super-resolution method that combines Channel Attention and Spatial Attention feature enhancement methods. It is important to restore high-frequency components, such as texture and features, that have large changes in surrounding pixels during super-resolution processing. We proposed a super-resolution method using feature enhancement that combines Channel Attention and Spatial Attention. The existing CNN (Convolutional Neural Network) based super-resolution method has difficulty in deep network learning and lacks emphasis on high frequency components, resulting in blurry contours and distortion. In order to solve the problem, we used an emphasis block that combines Channel Attention and Spatial Attention to which Skip Connection was applied, and a Residual Block. The emphasized feature map extracted by the method was extended through Sub-pixel Convolution to obtain the super resolution. As a result, about PSNR improved by 5%, SSIM improved by 3% compared with the conventional SRCNN, and by comparison with VDSR, about PSNR improved by 2% and SSIM improved by 1%.

• Food Science of Animal Resources
• /
• v.43 no.3
• /
• pp.471-490
• /
• 2023

In this study, the duck eggs were salted with none or 2.5% and 5.0% (v/v) of liquid smoke (LS), respectively. As a control, samples salted without LS were used. The 2-thiobarbituric acid (TBA) values, 1-diphenyl-2-picrylhydrazyl (DPPH) radical scavenging ability, and reducing power of the three groups were tested at 0, 7, 14, and 21 and 28 days to determine the effects of LS on the antioxidant activity of treated eggs. In addition, gas chromatography-mass spectrometry (GC-MS) and electronic nose (E-Nose) were used to analyze the volatile flavor components of fresh duck eggs, LS, control, and salted duck eggs enriched with 2.5% (v/v) LS after 28 days of salting. The TBA value considerably increased with an increase in salting period, and the treated egg's TBA value significantly associated with LS concentration. The TBA value decreased as the LS concentration increased. The amount of LS present was highly associated with their capacity to scavenge DPPH radicals. The reducing power of the samples was substantially correlated with the LS concentration, and the reducing power increased with increasing LS concentration. The GC-MS data revealed that phenols and ketones were the predominant chemicals present in the LS, and they were also found in the eggs added to the LS even though they were absent in the fresh eggs and control. The flavor of the control group and treated eggs with LS differed significantly, according to the principal component analysis and radar map of the E-nose. The texture study results revealed that the LS significantly impacted the hardness, cohesiveness, and chewiness of eggs.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.2D
• /
• pp.341-347
• /
• 2006

Geographically Imha basin is adjacent to Andong basin, but the occurrence of turbid water in each reservoir by storm events shows big differences. Hence, it is very important to identify the reason for these large differences. This study compared and analyzed soil erosion using the semi-empirical soil erosion model, RUSLE for both Imha and Andong basin, especially with emphasis on high-density turbid water. The agricultural district, which is the most vulnerable to soil erosion, was intensively analyzed based on land cover map produced by Ministry of Environment. As a result, the portion of the agricultural area is 11.88% for Andong basin, while it is 14.95% for Imha basin. Also all RUSLE factors excepts practice factor turned out to be higher for Imha basin. This means that the basin characteristics such as soil texture, terrain, and land cover for Imha basin is more vulnerable to soil erosion. Estimation of soil erosion by RUSLE for Andong and Imha basin is 1,275,806 ton and 1,501,608 ton, respectively, showing higher soil erosion by 225,802 ton for Imha basin.

• Geomechanics and Engineering
• /
• v.36 no.3
• /
• pp.205-215
• /
• 2024

Manually mapping fractures in construction stone mines is challenging, time-consuming, and hazardous. In this method, there is no physical access to all points. In contrast, digital image processing offers a safe, cost-effective, and fast alternative, with the capability to map all joints. In this study, two methods of detecting the trace of discontinuities using image processing in construction stone mines are presented. To achieve this, we employ two modified Hough transform algorithms and the degree of neighborhood technique. Initially, we introduced a method for selecting the best edge detector and smoothing algorithms. Subsequently, the Canny detector and median smoother were identified as the most efficient tools. To trace discontinuities using the mentioned methods, common preprocessing steps were initially applied to the image. Following this, each of the two algorithms followed a distinct approach. The Hough transform algorithm was first applied to the image, and the traces were represented through line drawings. Subsequently, the Hough transform results were refined using fuzzy clustering and reduced clustering algorithms, along with a novel algorithm known as the farthest points' algorithm. Additionally, we developed another algorithm, the degree of neighborhood, tailored for detecting discontinuity traces in construction stones. After completing the common preprocessing steps, the thinning operation was performed on the target image, and the degree of neighborhood for lineament pixels was determined. Subsequently, short lines were removed, and the discontinuities were determined based on the degree of neighborhood. In the final step, we connected lines that were previously separated using the method to be described. The comparison of results demonstrates that image processing is a suitable tool for identifying rock mass discontinuity traces. Finally, a comparison of two images from different construction stone mines presented at the end of this study reveals that in images with fewer traces of discontinuities and a softer texture, both algorithms effectively detect the discontinuity traces.

• Journal of Intelligence and Information Systems
• /
• v.19 no.4
• /
• pp.81-96
• /
• 2013

Video information retrieval has become a very important issue because of the explosive increase in video data from Web content development. Meanwhile, content-based video analysis using visual features has been the main source for video information retrieval and browsing. Content in video can be represented with content-based analysis techniques, which can extract various features from audio-visual data such as frames, shots, colors, texture, or shape. Moreover, similarity between videos can be measured through content-based analysis. However, a movie that is one of typical types of video data is organized by story as well as audio-visual data. This causes a semantic gap between significant information recognized by people and information resulting from content-based analysis, when content-based video analysis using only audio-visual data of low level is applied to information retrieval of movie. The reason for this semantic gap is that the story line for a movie is high level information, with relationships in the content that changes as the movie progresses. Information retrieval related to the story line of a movie cannot be executed by only content-based analysis techniques. A formal model is needed, which can determine relationships among movie contents, or track meaning changes, in order to accurately retrieve the story information. Recently, story-based video analysis techniques have emerged using a social network concept for story information retrieval. These approaches represent a story by using the relationships between characters in a movie, but these approaches have problems. First, they do not express dynamic changes in relationships between characters according to story development. Second, they miss profound information, such as emotions indicating the identities and psychological states of the characters. Emotion is essential to understanding a character's motivation, conflict, and resolution. Third, they do not take account of events and background that contribute to the story. As a result, this paper reviews the importance and weaknesses of previous video analysis methods ranging from content-based approaches to story analysis based on social network. Also, we suggest necessary elements, such as character, background, and events, based on narrative structures introduced in the literature. We extract characters' emotional words from the script of the movie Pretty Woman by using the hierarchical attribute of WordNet, which is an extensive English thesaurus. WordNet offers relationships between words (e.g., synonyms, hypernyms, hyponyms, antonyms). We present a method to visualize the emotional pattern of a character over time. Second, a character's inner nature must be predetermined in order to model a character arc that can depict the character's growth and development. To this end, we analyze the amount of the character's dialogue in the script and track the character's inner nature using social network concepts, such as in-degree (incoming links) and out-degree (outgoing links). Additionally, we propose a method that can track a character's inner nature by tracing indices such as degree, in-degree, and out-degree of the character network in a movie through its progression. Finally, the spatial background where characters meet and where events take place is an important element in the story. We take advantage of the movie script to extracting significant spatial background and suggest a scene map describing spatial arrangements and distances in the movie. Important places where main characters first meet or where they stay during long periods of time can be extracted through this scene map. In view of the aforementioned three elements (character, event, background), we extract a variety of information related to the story and evaluate the performance of the proposed method. We can track story information extracted over time and detect a change in the character's emotion or inner nature, spatial movement, and conflicts and resolutions in the story.

• Journal of the Korea Computer Graphics Society
• /
• v.16 no.1
• /
• pp.1-7
• /
• 2010

With the widespread use of vision-based surveillance systems, the capability for person identification is now an essential component. However, the CCTV cameras used in surveillance systems tend to produce relatively low-resolution images, making it difficult to use face recognition techniques for person identification. Therefore, an algorithm is proposed for person identification in CCTV camera images based on the clothing. Whenever a person is authenticated at the main entrance of a building, the clothing feature of that person is extracted and added to the database. Using a given image, the clothing area is detected using background subtraction and skin color detection techniques. The clothing feature vector is then composed of textural and color features of the clothing region, where the textural feature is extracted based on a local edge histogram, while the color feature is extracted using octree-based quantization of a color map. When given a query image, the person can then be identified by finding the most similar clothing feature from the database, where the Euclidean distance is used as the similarity measure. Experimental results show an 80% success rate for person identification with the proposed algorithm, and only a 43% success rate when using face recognition.