• The Journal of Korean Institute of Information Technology
• /
• v.17 no.8
• /
• pp.11-19
• /
• 2019

Against advanced image-related crimes, a high level of digital forensic methods is required. However, feature-based methods are difficult to respond to new device features by utilizing human-designed features, and deep learning-based methods should improve accuracy. This paper proposes a deep learning model to identify camera models based on DenseNet, the recent technology in the deep learning model field. To extract camera sensor features, a HPF feature extraction filter was applied. For camera model identification, we modified the number of hierarchical iterations and eliminated the Bottleneck layer and compression processing used to reduce computation. The proposed model was analyzed using the Dresden database and achieved an accuracy of 99.65% for 14 camera models. We achieved higher accuracy than previous studies and overcome their disadvantages with low accuracy for the same manufacturer.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.465-472
• /
• 2022

In this paper, the style synthesis network is trained to generate style-synthesized video through the style synthesis through training Stylegan and the video synthesis network for video synthesis. In order to improve the point that the gaze or expression does not transfer stably, 3D face restoration technology is applied to control important features such as the pose, gaze, and expression of the head using 3D face information. In addition, by training the discriminators for the dynamics, mouth shape, image, and gaze of the Head2head network, it is possible to create a stable style synthesis video that maintains more probabilities and consistency. Using the FaceForensic dataset and the MetFace dataset, it was confirmed that the performance was increased by converting one video into another video while maintaining the consistent movement of the target face, and generating natural data through video synthesis using 3D face information from the source video's face.

• Computers and Concrete
• /
• v.33 no.4
• /
• pp.425-443
• /
• 2024

Floods are among the most common natural hazards in urban areas. To mitigate the problems caused by flooding, unstructured data such as images and videos collected from closed circuit televisions (CCTVs) or unmanned aerial vehicles (UAVs) have been examined for flood management (FM). Many computer vision (CV) techniques have been widely adopted to analyze imagery data. Although some papers have reviewed recent CV approaches that utilize UAV images or remote sensing data, less effort has been devoted to studies that have focused on CCTV data. In addition, few studies have distinguished between the main research objectives of CV techniques (e.g., flood depth and flooded area) for a comprehensive understanding of the current status and trends of CV applications for each FM research topic. Thus, this paper provides a comprehensive review of the literature that proposes CV techniques for aspects of FM using ground camera (e.g., CCTV) data. Research topics are classified into four categories: flood depth, flood detection, flooded area, and surface water velocity. These application areas are subdivided into three types: urban, river and stream, and experimental. The adopted CV techniques are summarized for each research topic and application area. The primary goal of this review is to provide guidance for researchers who plan to design a CV model for specific purposes such as flood-depth estimation. Researchers should be able to draw on this review to construct an appropriate CV model for any FM purpose.

• Imaging Science in Dentistry
• /
• v.36 no.1
• /
• pp.49-54
• /
• 2006

Purpose : To evaluate accuracy and reliability of program to measure facial soft tissue thickness using 3D computed tomographic images by comparing with direct measurement. Materials and Methods : One cadaver was scanned with a Helical CT with 3 mm slice thickness and 3 mm/sec table speed. The acquired data was reconstructed with 1.5 mm reconstruction interval and the images were transferred to a personal computer. The facial soft tissue thickness were measured using a program developed newly in 3D image. For direct measurement, the cadaver was cut with a bone cutter and then a ruler was placed above the cut side. The procedure was followed by taking pictures of the facial soft tissues with a high-resolution digital camera. Then the measurements were done in the photographic images and repeated for ten times. A repeated measure analysis of variance was adopted to compare and analyze the measurements resulting from the two different methods. Comparison according to the areas was analyzed by Mann-Whitney test. Results : There were no statistically significant differences between the direct measurements and those using the 3D images (p>0.05). There were statistical differences in the measurements on 17 points but all the points except 2 points showed a mean difference of 0.5 mm or less. Conclusion : The developed software program to measure the facial soft tissue thickness using 3D images was so accurate that it allows to measure facial soft tissues thickness more easily in forensic science and anthropology.

• Imaging Science in Dentistry
• /
• v.50 no.1
• /
• pp.1-7
• /
• 2020

Purpose: This study was performed to evaluate the magnitude of artifacts produced by gutta-percha and metal posts on cone-beam computed tomography (CBCT) scans obtained with different tube currents and with or without metal artifact reduction (MAR). Materials and Methods: A tooth was inserted in a dry human mandible socket, and CBCT scans were acquired after root canal instrumentation, root canal filling, and metal post placement with various tube currents with and without MAR activation. The artifact magnitude was assessed by the standard deviation (SD) of gray values and the contrast-to-noise ratio (CNR) at the various distances from the tooth. Data were compared using multi-way analysis of variance. Results: At all distances, a current of 4 mA was associated with a higher SD and a lower CNR than 8 mA or 10 mA (P<0.05). For the metal posts without MAR, the artifact magnitude as assessed by SD was greatest at 1.5 cm or less (P<0.05). When MAR was applied, SD values for distances 1.5 cm or closer to the tooth were reduced (P<0.05). MAR usage did not influence the magnitude of artifacts in the control and gutta-percha groups(P>0.05). Conclusion: Increasing the tube current from 4 mA to 8 mA may reduce the magnitude of artifacts from metal posts. The magnitude of artifacts arising from metal posts was significantly higher at distances of 1.5 cm or less than at greater distances. MAR usage improved image quality near the metal post, but had no significant influence farther than 1.5 cm from the tooth.

• Korean Journal of Forensic Psychology
• /
• v.12 no.1
• /
• pp.75-97
• /
• 2021

This study investigated whether judgments of sexual violence involving juvenile victims vary by history of victim's juvenile prostitution, victim's behavior conforming to stereotypes of an "ideal" victim, and relationships between victim and perpetrator. The study also examined the effects of participants' level of authoritarianism and rape myth acceptance on their judgments of sexual violence. A total of 335 participants(170 females, 165 males) in their 20s to 50s assessed the degree of victim blaming and perpetrator sentencing. This study examined the effects of participants' gender and age on the judgments of victim blaming and perpetrator sentencing, and the mediation effects of authoritarianism and rape myth acceptance. As a result, participants blamed the victim more and imposed a lighter sentence on the perpetrator when the juvenile victim did not conform to the image of an "ideal" victim of sexual violence as opposed to a "typical victim". They also blamed the victim more when the victim and the perpetrator met through a chat application than when the victim and the perpetrator had known each other. Male participants as opposed to female participants blamed the victim more, punished the perpetrator more lightly, and exhibited a higher level of authoritarianism and rape myth acceptance. The older the participants were, the more they blamed the victim and the higher they demonstrated rape myth acceptance. The effect of the participants' gender on the judgment of the perpetrator punishment was mediated by rape myth acceptance, and the effect of the participants' gender and age on the victim blaming was mediated by authoritarianism and rape myth acceptance.

• Analytical Science and Technology
• /
• v.21 no.3
• /
• pp.222-228
• /
• 2008

On living skin the chances of a successfully developing latent fingerprint are very limited. This is due to the fact that continual perspiration and rapid absorption diffuse into the lipophillic layer on skin. A study was conducted to investigate effectively developing method of latent fingerprints on human skin surfaces and pig skin likely corpse's skin. We used commercial fingerprint powder, black powders, black magnetic powder, fluorescence magnetic powder, Cyanoacrylate fuming (CA) and direct lifting methods (lifting paper, glasses and photo glossy paper). Developing of fresh fingerprints on living skin was achieved with S-powderblack, CA fuming and CA fuming following S-powder, fluorescence powder. The other powder tends to overwhelm the latent print and the background. But, latent fingerprint residue was disappeared with time after deposit on a living surface. In case of pig skin likely corpse's skin, latent fingerprint detection was achieved with CA fuming following S-powder and deposited print during 6 hr at $25^{\circ}C$, 40% relative moisture yielded excellent fingerprints with clear ridge details using 1 min CA fuming. And enhancement of fingerprint detection image using forensic light source was achieved.