• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1262-1270
• /
• 2020

Recently, the smart video surveillance research, which has been receiving increasing attention, has mainly focused on the intruder detection and tracking, and abandoned object detection. On the other hand, research on real-time detection of stolen objects is relatively insufficient compared to its importance. Considering various smart surveillance video application environments, this paper presents two different types of stolen object detection algorithms. We first propose an algorithm that detects theft of statically and dynamically registered surveillance objects using a dual background subtraction model. In addition, we propose another algorithm that detects theft of general surveillance objects by applying the dual background subtraction model and Mask R-CNN-based object segmentation technology. The former algorithm can provide economical theft detection service for pre-registered surveillance objects in low computational power environments, and the latter algorithm can be applied to the theft detection of a wider range of general surveillance objects in environments capable of providing sufficient computational power.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1212-1223
• /
• 2022

Skin lesions are common diseases that range from skin rashes to skin cancer, which can lead to death. Note that early diagnosis of skin diseases can be important because early diagnosis of skin diseases considerably can reduce the course of treatment and the harmful effect of the disease. Recently, the development of computer-aided diagnosis (CAD) systems based on artificial intelligence has been actively made for the early diagnosis of skin diseases. In a typical CAD system, the accurate classification of skin lesion types is of great importance for improving the diagnosis performance. Motivated by this, we propose a novel deep ensemble classification with multi-scale attention networks. The proposed deep ensemble networks are jointly trained using a single loss function in an end-to-end manner. In addition, the proposed deep ensemble network is equipped with a multi-scale attention mechanism and segmentation information of the original skin input image, which improves the classification performance. To demonstrate our method, the publicly available human skin disease dataset (HAM 10000) and the private animal skin lesion dataset were used for the evaluation. Experiment results showed that the proposed methods can achieve 97.8% and 81% accuracy on each HAM10000 and animal skin lesion dataset. This research work would be useful for developing a more reliable CAD system which helps doctors early diagnose skin diseases.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.1
• /
• pp.91-97
• /
• 2009

This paper proposes novel FE-CBIRS that finds best position of a cut to be retrieved based on color feature distribution in digital contents of IPTV. Conventional CBIRS have used a method that utilizes both color and shape information together to classify images, as well as a method that utilizes both feature information of the entire region and feature information of a partial region that is extracted by segmentation for searching. Also, in the algorithm, average, standard deviation and skewness values are used in case of color features for each hue, saturation and intensity values respectively. Furthermore, in case of using partial regions, only a few major colors are used and in case of shape features, the invariant moment is mainly used on the extracted partial regions. Due to these reasons, some problems have been issued in CBIRS in processing time and accuracy so far. Therefore, in order to tackle these problems, this paper proposes the FE-CBIRS that makes searching speed faster by classifying and indexing the extracted color information by each class and by using several cuts that are restricted in range as comparative images.

• Restorative Dentistry and Endodontics
• /
• v.46 no.4
• /
• pp.57.1-57.9
• /
• 2021

Objectives: This study aimed to compare and evaluate the porosity and pore size distribution of high-viscosity glass ionomer cements (HVGICs) and conventional glass ionomer cements (GICs) using micro-computed tomography (micro-CT). Materials and Methods: Forty cylindrical specimens (n = 10) were produced in standardized molds using HVGICs and conventional GICs (Ketac Molar Easymix, Vitro Molar, MaxxionR, and Riva Self-Cure). The specimens were prepared according to ISO 9917-1 standards, scanned in a high-energy micro-CT device, and reconstructed using specific parameters. After reconstruction, segmentation procedures, and image analysis, total porosity and pore size distribution were obtained for specimens in each group. After checking the normality of the data distribution, the Kruskal-Wallis test followed by the Student-Newman-Keuls test was used to detect differences in porosity among the experimental groups with a 5% significance level. Results: Ketac Molar Easymix showed statistically significantly lower total porosity (0.15%) than MaxxionR (0.62%), Riva (0.42%), and Vitro Molar (0.57%). The pore size in all experimental cements was within the small-size range (< 0.01 mm³), but Vitro Molar showed statistically significantly more pores/defects with a larger size (> 0.01 mm³). Conclusions: Major differences in porosity and pore size were identified among the evaluated GICs. Among these, the Ketac Molar Easymix HVGIC showed the lowest porosity and void size.

• Korean Journal of Radiology
• /
• v.21 no.4
• /
• pp.450-461
• /
• 2020

Objective: We performed a meta-analysis to evaluate the agreement of cardiac computed tomography (CT) with cardiac magnetic resonance imaging (CMRI) in the assessment of right ventricle (RV) volume and functional parameters. Materials and Methods: PubMed, EMBASE, and Cochrane library were systematically searched for studies that compared CT with CMRI as the reference standard for measurement of the following RV parameters: end-diastolic volume (EDV), end-systolic volume (ESV), stroke volume (SV), or ejection fraction (EF). Meta-analytic methods were utilized to determine the pooled weighted bias, limits of agreement (LOA), and correlation coefficient (r) between CT and CMRI. Heterogeneity was also assessed. Subgroup analyses were performed based on the probable factors affecting measurement of RV volume: CT contrast protocol, number of CT slices, CT reconstruction interval, CT volumetry, and segmentation methods. Results: A total of 766 patients from 20 studies were included. Pooled bias and LOA were 3.1 mL (-5.7 to 11.8 mL), 3.6 mL (-4.0 to 11.2 mL), -0.4 mL (5.7 to 5.0 mL), and -1.8% (-5.7 to 2.2%) for EDV, ESV, SV, and EF, respectively. Pooled correlation coefficients were very strong for the RV parameters (r = 0.87-0.93). Heterogeneity was observed in the studies (I² > 50%, p < 0.1). In the subgroup analysis, an RV-dedicated contrast protocol, ≥ 64 CT slices, CT volumetry with the Simpson's method, and inclusion of the papillary muscle and trabeculation had a lower pooled bias and narrower LOA. Conclusion: Cardiac CT accurately measures RV volume and function, with an acceptable range of bias and LOA and strong correlation with CMRI findings. The RV-dedicated CT contrast protocol, ≥ 64 CT slices, and use of the same CT volumetry method as CMRI can improve agreement with CMRI.

• Journal of the Korean Society of Radiology
• /
• v.83 no.6
• /
• pp.1229-1239
• /
• 2022

Recently, artificial intelligence (AI) technology has shown potential clinical utility in a wide range of MRI fields. In particular, AI models for improving the efficiency of the image acquisition process and the quality of reconstructed images are being actively developed by the MR research community. AI is expected to further reduce acquisition times in various MRI protocols used in clinical practice when compared to current parallel imaging techniques. Additionally, AI can help with tasks such as planning, parameter optimization, artifact reduction, and quality assessment. Furthermore, AI is being actively applied to automate MR image analysis such as image registration, segmentation, and object detection. For this reason, it is important to consider the effects of protocols or devices in MR image analysis. In this review article, we briefly introduced issues related to AI application of MR image acquisition and reconstruction.

• Smart Media Journal
• /
• v.2 no.4
• /
• pp.60-65
• /
• 2013

In this paper, we propose a high-resolution disparity map generation method using a low-resolution time-of-flight (TOF) depth camera and color camera. The TOF depth camera is efficient since it measures the range information of objects using the infra-red (IR) signal in real-time. It also quantizes the range information and provides the depth image. However, there are some problems of the TOF depth camera, such as noise and lens distortion. Moreover, the output resolution of the TOF depth camera is too small for 3D applications. Therefore, it is essential to not only reduce the noise and distortion but also enlarge the output resolution of the TOF depth image. Our proposed method generates a depth map for a color image using the TOF camera and the color camera simultaneously. We warp the depth value at each pixel to the color image position. The color image is segmented using the mean-shift segmentation method. We define a cost function that consists of color values and segmented color values. We apply a weighted average filter whose weighting factor is defined by the random walk probability using the defined cost function of the block. Experimental results show that the proposed method generates the depth map efficiently and we can reconstruct good virtual view images.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.273-282
• /
• 2022

MPEG-VCM(Video Coding for Machine) aims to standardize video codec for machines. VCM provides data sets and anchors, which provide reference data for comparison, for several machine vision tasks including object detection, object segmentation, and object tracking. The evaluation template can be used to compare compression and machine vision task performance between anchor data and various proposed video codecs. However, performance comparison is carried out separately for each machine vision task, and information related to performance evaluation of multiple machine vision tasks on a single bitstream is not provided currently. In this paper, we propose a performance evaluation method of a video codec for AI-based multi-tasks. Based on bits per pixel (BPP), which is the measure of a single bitstream size, and mean average precision(mAP), which is the accuracy measure of each task, we define three criteria for multi-task performance evaluation such as arithmetic average, weighted average, and harmonic average, and to calculate the multi-tasks performance results based on the mAP values. In addition, as the dynamic range of mAP may very different from task to task, performance results for multi-tasks are calculated and evaluated based on the normalized mAP in order to prevent a problem that would be happened because of the dynamic range.

• Korean Journal of Radiology
• /
• v.23 no.2
• /
• pp.226-236
• /
• 2022

Objective: This study aimed to explore the myelin volume change in patients with mild traumatic brain injury (mTBI) with post-concussion syndrome (PCS) using a multidynamic multiecho (MDME) sequence and automatic whole-brain segmentation. Materials and Methods: Forty-one consecutive mTBI patients with PCS and 29 controls, who had undergone MRI including the MDME sequence between October 2016 and April 2018, were included. Myelin volume fraction (MVF) maps were derived from the MDME sequence. After three dimensional T1-based brain segmentation, the average MVF was analyzed at the bilateral cerebral white matter (WM), bilateral cerebral gray matter (GM), corpus callosum, and brainstem. The Mann-Whitney U-test was performed to compare MVF and myelin volume between patients with mTBI and controls. Myelin volume was correlated with neuropsychological test scores using the Spearman rank correlation test. Results: The average MVF at the bilateral cerebral WM was lower in mTBI patients with PCS (median [interquartile range], 25.2% [22.6%-26.4%]) than that in controls (26.8% [25.6%-27.8%]) (p = 0.004). The region-of-interest myelin volume was lower in mTBI patients with PCS than that in controls at the corpus callosum (1.87 cm³ [1.70-2.05 cm³] vs. 2.21 cm³ [1.86-3.46 cm³]; p = 0.003) and brainstem (9.98 cm³ [9.45-11.00 cm³] vs. 11.05 cm³ [10.10-11.53 cm³]; p = 0.015). The total myelin volume was lower in mTBI patients with PCS than that in controls at the corpus callosum (0.45 cm³ [0.39-0.48 cm³] vs. 0.48 cm³ [0.45-0.54 cm³]; p = 0.004) and brainstem (1.45 cm³ [1.28-1.59 cm³] vs. 1.54 cm³ [1.42-1.67 cm³]; p = 0.042). No significant correlation was observed between myelin volume parameters and neuropsychological test scores, except for the total myelin volume at the bilateral cerebral WM and verbal learning test (delayed recall) (r = 0.425; p = 0.048). Conclusion: MVF quantified from the MDME sequence was decreased at the bilateral cerebral WM in mTBI patients with PCS. The total myelin volumes at the corpus callosum and brainstem were decreased in mTBI patients with PCS due to atrophic changes.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.3
• /
• pp.163-168
• /
• 2011

In this paper, we proposed non-linear gamma curve algorithm for gamma correction. The previous non-linear gamma curve algorithm is generated by the least square polynomial using the Gauss-Jordan inverse matrix. However, the previous algorithm has some weak points. When calculating coefficients using inverse matrix of higher degree, occurred truncation errors. Also, only if input sample points are existed regular interval on 10-bit scale, the least square polynomial is accurately works. To compensate weak-points, we calculated accurate coefficients of polynomial using eigenvalue and orthogonal value of mat11x from singular value decomposition (SVD) and QR decomposition of vandemond matrix. Also, we used input data part segmentation, then we performed polynomial curve fitting and merged curve fitting results. When compared the previous method and proposed method using the mean square error (MSE) and the standard deviation (STD), the proposed segmented polynomial curve fitting is highly accuracy that MSE under the least significant bit (LSB) error range is approximately $10^{-9}$ and STD is about $10^{-5}$.