• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.983-991
• /
• 2019

This study aims to analyze movies which contain various stories according to the size of their shots. To achieve this, it is needed to classify dataset according to the shot size, such as extreme close-up shots, close-up shots, medium shots, full shots, and long shots. However, a typical video storytelling is mainly composed of close-up shots, medium shots, full shots, and long shots, it is not an easy task to construct an appropriate dataset for extreme close-up shots. To solve this, we propose an image cropping method based on the region of interest (ROI) detection. In this paper, we use the face detection and saliency detection to estimate the ROI. By cropping the ROI of close-up images, we generate extreme close-up images. The dataset which is enriched by proposed method is utilized to construct a model for classifying shots based on its size. The study can help to analyze the emotional changes of characters in video stories and to predict how the composition of the story changes over time. If AI is used more actively in the future in entertainment fields, it is expected to affect the automatic adjustment and creation of characters, dialogue, and image editing.

• Journal of the Korean Society of Radiology
• /
• v.17 no.3
• /
• pp.335-341
• /
• 2023

In this study, four algorithms (Standard, Bone, Dual volume, and Stent Follow up) were applied to the image of the aneurysm in cerebral angiography to reconstruct the image in 3D, and quantitatively evaluate Noise, SNR, and CNR based on the reconstructed image to find out the optimal algorithm. As an analysis method, Image J program, which can analyze images and calculate area and pixel values, was used for images reconstructed with four algorithms. In order to obtain Noise, SNR, and CNR, the region of interest (ROI) is measured by designating the point where the abnormal artery (aneurysm) is located and the surrounding normal artery in the image are measured, and the mean value and SD value are obtained. Background noise was set to two surrounding normal artery to increase reliability. The values of SNR and CNR were calculated based on the given formula. As a result, the noise was the lowest in the stent follow-up algorithm, and the SNR and CNR were the highest. Therefore, the stent follow-up algorithm is judged to be the most appropriate algorithm. The data of this study are expected to be useful as basic data for 3D image evaluation of the vascular and aneurysm in cerebral angiography, and it is believed that appropriate algorithm changes will serve as an opportunity to further improve image quality.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.11
• /
• pp.41-47
• /
• 2016

High efficiency video coding (HEVC) employs a coding tree unit (CTU) to improve the coding efficiency. A CTU consists of coding units (CU), prediction units (PU), and transform units (TU). All possible block partitions should be performed on each depth level to obtain the best combination of CUs, PUs, and TUs. To reduce the complexity of block partitioning process, this paper proposes the PU mode skip algorithm with region of interest (RoI) selection using motion vector. In addition, this paper presents the CU depth level skip algorithm using the co-located block information in the previously encoded frames. First, the RoI selection algorithm distinguishes between dynamic CTUs and static CTUs and then, asymmetric motion partitioning (AMP) blocks are skipped in the static CTUs. Second, the depth level skip algorithm predicts the most probable target depth level from average depth in one CTU. The experimental results show that the proposed fast CU decision algorithm can reduce the total encoding time up to 44.8% compared to the HEVC test model (HM) 14.0 reference software encoder. Moreover, the proposed algorithm shows only 2.5% Bjontegaard delta bit rate (BDBR) loss.

• The KIPS Transactions:PartD
• /
• v.10D no.7
• /
• pp.1171-1176
• /
• 2003

In this paper, we propose an effective bar code detection algorithm using the feature analysis and the labeling. After computing the direction of pixels using four line operators, we obtain the histogram about the direction of pixels by a block unit. We calculate the difference between the maximum value and the minimum value of the histogram and consider the block that have the largest difference value as the block of the bar code region. We get the line passing by the bar code region with the selected block but detect blocks of interest to get the more accurate line. The largest difference value is used to decide the threshold value to obtain the binary image. After obtaining a binary image, we do the labeling about the binary image. Therefore, we find blocks of interest in the bar code region. We calculate the gradient and the center of the bar code with blocks of interest, and then get the line passing by the bar code and detect the bar code. As we obtain the gray level of the line passing by the bar code, we grasp the information of the bar code.

• Journal of Broadcast Engineering
• /
• v.11 no.3 s.32
• /
• pp.336-348
• /
• 2006

The recent advances in multimedia signal coding and transmission technologies allow lots of users to watch videos on small LCD displays. In this paper, we briefly describe an intelligent display technique to provide small-display-viewers with comfortable experiences, and study the minimum image size tolerated and utility of displaying region of interest (ROI) only when needed. The study, with 111 participants, examines minimum image size to ensure viewers pleasant viewing experiences, and evaluates the degree of satisfaction when they are viewed with region of interest (ROI) only. The experimental results show that the ROI display enhances the viewers' satisfaction when the image size becomes less than $320{\times}240$, and thus it is useful to provide the intelligent display, if necessary, which can extract and display ROI only.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.3
• /
• pp.65-75
• /
• 2017

As a 360-degree image carries information of all directions, it often has too much information. Moreover, in order to investigate a 360-degree image on a 2D display, a user has to either click and drag the image with a mouse, or project it to a 2D panorama image, which inevitably introduces severe distortions. In consequence, investigating a 360-degree image and finding an object of interest in such a 360-degree image could be a tedious task. To resolve this issue, this paper proposes a method to find a region of interest and produces a 2D naturally looking image from a given 360-degree image that best matches a description given by a user in a natural language sentence. Our method also considers photo composition so that the resulting image is aesthetically pleasing. Our method first converts a 360-degree image to a 2D cubemap. As objects in a 360-degree image may appear distorted or split into multiple pieces in a typical cubemap, leading to failure of detection of such objects, we introduce a modified cubemap. Then our method applies a Long Short Term Memory (LSTM) network based object detection method to find a region of interest with a given natural language sentence. Finally, our method produces an image that contains the detected region, and also has aesthetically pleasing composition.

• The KIPS Transactions:PartB
• /
• v.10B no.1
• /
• pp.95-102
• /
• 2003

In surveillance video system, there are many classes of images and some spatial regions are more important than other regions. The conventional compression method in this system have been compressed there full frames without classfying them depend on their important parts. To improve the accuracy of the image coding and deliver effective compression for the surveillance video system, it was necessary to separate the regions according to their importance. In this paper, we propose a new effective surveillance video image compression method. The proposed scheme defines importance based three-level region of interest block in a frame, such as background, motion object block, and the feature object block. A captured video image frame can be separated to these three different levels of block regions. And depends on the priority, each block can be modified and compressed in different resolution, compression ratio and qualify factor. Therefore, in surveillance video system, this algorithm not only reduces the image processing time and space, but also guarantees the Important image data in high quality to acquire the system's goal.

• Hwankyungkyoyuk
• /
• v.11 no.1
• /
• pp.151-164
• /
• 1998

Conclusion and the improvement plan according to the survey on recycling wastes in 'the program of woman and environmental education' mainly for the chairwomen of the women's association of the apartment house in City and County of Chungchongnamdo during the first half of 1998 (from March tp April) are as follows. 1. Conclusion 1) It showed that the rate of recognition for recycle has no difference by regional groups and the rate of recognition is 57.4% but they mainly know vaguely or they do not know. 2) It showed that the rate they do not know how the separated wastes are recycled is 30.4% and the scope of their knowledge is approximative.(52.6%) 3) It showed that it is the housewives who mainly do the separate garbage collection (72.7%) and 19.1% of the people have no interest in the separate discharge. 4) It showed that the rate they filter the garbage or remove water from the garbage at house is 53.1%. And 20% of the people in the urban region dump untreated wastes but 8.5% of the people in the rural region do the same, so the rate of using garbage in the rural region is higher than that in the urban region. 5) It showed that the separate state of the garbage is 29.2% for the removal of toothpick and paper and 47.4% for the removal of vinyl and stopper. 6) It showed that 66.7% of the motive for recycling waste is the education activity for environment by the women's association and SAEMAEUL association and 34.5% of that is the influence of TV and radio. 7) It showed that the rate of making compost and feed using garbage in the rural region is higher than that in the urban region and in some urban regions, the rate they sprinkle the garbage in provisional compost state on the floor garden is high. 8) It showed that the recognition rate for the material of separately collected garbage corresponding to the separate waste system of 5-6 classification is 12.5% 9) It showed that the major variable which has an effect on the recycle is the education activity for environment by the neighborhood meeting(P<0.05) and by the women's association of saemaeul activity(P<0.05)

• Journal of KIISE:Software and Applications
• /
• v.27 no.3
• /
• pp.266-274
• /
• 2000

Medical image segmentation, which is essential in diagnosis and 3D reconstruction, is performed manually in most applications to produce accurate results. However, manual segmentation requires lots of time to segment, and is difficult even for the same operator to reproduce the same segmentation results for a region. To overcome such limitations, we propose a convenient and accurate semiautomatic segmentation method. The proposed method initially receives several control points of an ROI(Region of Interest Region) from a human operator, and then finds a boundary composed of a minimum cost path connecting the control points, which is the Live-wire method. Next, the boundary is modified to overcome limitations of the Live-wire, such as a zig-zag boundary and erosion of an ROI. Finally, the region is segmented by SRG(Seeded Region Growing), where the modified boundary acts as a blockage to prevent leakage. The proposed User-steered balloon method can overcome not only the limitations of the Live-wire but also the leakage problem of the SRG. Segmentation results of thigh muscles of the Visible Human are presented.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.8
• /
• pp.225-231
• /
• 2013

Medical image segmentation is an image processing technology prior to performing various medical image processing. Therefore, a variety of methods have been researched for fast and accurate medical image segmentation. Accurate judgment of segmentation region is needed to segment the interest region in which patient requested in medical image that various organs exist. However, an case that scanned a part of organs is small occurs. In this case, information to determine the segmentation region is lack. consequently, a removal of segmentation region occurs during the segmentation process. In this paper, we improved segmentation results in a small region using volume data and linear equation. In order to verify the performance of the proposed method, we segmented the lung region of chest CT images. As a result of experiments, we confirmed that image segmentation accuracy rose from 0.978 to 0.981 and standard deviation also improved from 0.281 to 0.187.