• 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.

• The Journal of the Korea Contents Association
• /
• v.22 no.2
• /
• pp.10-21
• /
• 2022

In order to improve formal presentation attitudes such as presentation of job interviews and presentation of project results at the company, there are few automated methods other than observation by colleagues or professors. In previous studies, it was reported that the speaker's stable speech and gaze processing affect the delivery power in the presentation. Also, there are studies that show that proper feedback on one's presentation has the effect of increasing the presenter's ability to present. In this paper, considering the positive aspects of correction, we developed a program that intelligently corrects the wrong presentation habits and attitudes of college students through facial analysis of videos and analyzed the proposed program's performance. The proposed program was developed through web-based verification of the use of redundant words and facial recognition and textualization of the presentation contents. To this end, an artificial intelligence model for classification was developed, and after extracting the video object, facial feature points were recognized based on the coordinates. Then, using 4000 facial data, the performance of the algorithm in this paper was compared and analyzed with the case of facial recognition using a Teachable Machine. Use the program to help presenters by correcting their presentation attitude.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.2
• /
• pp.112-118
• /
• 2009

This paper proposes a rapid detection algorithm of a salient region for music video browsing system, which can be applied to mobile device and digital video recorder (DVR). The input music video is decomposed into the music and video tracks. For the music track, the music highlight including musical chorus is detected based on structure analysis using energy-based peak position detection. Using the emotional models generated by SVM-AdaBoost learning algorithm, the music signal of the music videos is classified into one of the predefined emotional classes of the music automatically. For the video track, the face scene including the singer or actor/actress is detected based on a boosted cascade of simple features. Finally, the salient region is generated based on the alignment of boundaries of the music highlight and the visual face scene. First, the users select their favorite music videos from various music videos in the mobile devices or DVR with the information of a music video's emotion and thereafter they can browse the salient region with a length of 30-seconds using the proposed algorithm quickly. A mean opinion score (MOS) test with a database of 200 music videos is conducted to compare the detected salient region with the predefined manual part. The MOS test results show that the detected salient region using the proposed method performed much better than the predefined manual part without audiovisual processing.

• Journal of Distribution Science
• /
• v.10 no.4
• /
• pp.47-53
• /
• 2012

Businesses make use of advertising strategy using models to give consumers efficient product information. Modern advertisements often make use of models for greater reminiscence to create messages and remind viewers of the product. The purpose of this study was to examine the characteristics of each type of model. The subjects were 230 college students in their twenties or older, and the material was collected from October 20, 2011 to November 5, 2011 to examine the effects of model characteristics on buying intention as well as attitude toward a brand. A questionnaire survey was used; investigators gave one copy to each interviewee. The study investigated the characteristics of each model using a questionnaire of each 40 copies with five kinds of photographs. The characteristics of models had great influence on buying intention and attitude toward the brand: First, factor 2 (being honest and virtuous and having good credit and a good press assessment) and factor 3 (being interesting and a good communicator and creating good memories) had great influence on buying intention. Factor 2 was explained by reliability, and factor 3 by the efficiency of the model in creating a feeling. Second, factors 1 (being attractive, smart, unique, friendly, loved by others, and popular), 2, and 3 influenced attitude toward brand. Factor 1 encapsulated the outgoing characteristics of a model, factor 2 was based on reliability, and factor 3 was based on the efficiency of the model in creating a feeling. The model's positive effects on buying intention and attitudes toward brand shall be examined. For their positive influence on buying intention, reliability and efficiency shall be given attention. For their positive influence on attitude toward brand, creating a good impression, having outgoing characteristics, being reliable, and efficiency shall be given attention. The findings were as follows: Model characteristics influencing buying intention were similar to those influencing attitude toward brand. The differences were as follows. First, reliability and efficiency influenced buying intention. When customers were asked to consider the influence on buying intention of an advertisement, regardless of the strength of the buying intention, they considered these two characteristics. Customers decided to buy based not only on the credibility of the product as presented in the advertisement but also the transmission of the contents of the advertisement. Second, outgoing characteristics, reliability, and efficiency influenced attitude toward a brand. The attitude toward a brand was said to be the attitude toward the business. The attitude is produced even after buying, so businesses view it as very important. The attitude might vary depending upon the model used rather than the brand. Therefore, a model with outgoing characteristics was thought to be important. Therefore, attitude toward a brand whose model influenced buying intention as well as attitude toward brand had outgoing characteristics. The result is that an image the model was related to attitude toward the brand. As such, customers would buy the goods advertised. However, an outgoing image of a model was also important to create a positive attitude toward a business brand. For instance, talent Park Gyeong-Rim's photo was used to promote cosmetics about 10 years ago. When she worked as a model of cosmetics products, she had to make compensation for losses and damages because she made a mistake on a talk show program. At that time, customers who had bought the cosmetics product asked for refunds of several billion won. As such, models who are said to be the face of the businesses they represent can play an important role. To advertise in the most attractive and effective way, the current image of a model should be investigated by examining current activities and news articles after selecting the model, and the model's efficiency and attitude toward the brand should be examined. Factors that stimulate customers' buying decisions can be used to plan advertisement that have positive influence on a brand. This study had the limitation of investigating mainly college students and there were insufficient copies of the questionnaire. The investigation was not done widely but in detail so that a concrete investigation could not be done. Further studies shall supplement these shortcomings and discuss new directions.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2005.11a
• /
• pp.286-289
• /
• 2005

기존의 물리적 인증도구를 이용한 방식이나 패스워드 인증 방식은 분실, 도난, 해킹 등에 취약점을 가지고 있다. 따라서 지문, 서명, 홍채, 음성, 얼굴 등을 이용한 생체 인식기술을 보안 기술로 적용하려는 연구가 진행중이며 일부는 실용화도 되고 있다. 본 논문에서는 최근 널리 보급되어 있는 임베디드 시스템중의 하나인 PDA에 음성 기술을 이용한 내장형 화자 인증기를 구현하였다. 화자 인증기는 음성기술에서 널리 사용되고 있는 벡터 양자화 기술과 은닉 마코프 모델 기술을 사용하였으며, PDA의 하드웨어적인 제약 사항을 고려하여 사용되는 벡터 코드북을 두 가지로 다르게 하여 각각 구현하였다. 처음은 코드북을 화자 등록시에 발성음만을 이용하여 생성하고 화자인증 시에 이용하는 방법이며, 다른 하나는 대용량의 음성 데이터베이스를 이용하여 코드북을 사전에 생성하여 이를 화자 인증시에 이용하는 방법이다. 화자인증기의 성능평가는 5명의 화자가 10번씩 5개의 단어에 대하여 실험하여, 각각 화자종속 코득북을 이용한 인증기는 88.8%, 99.5%, 화자독립 코드북을 이용한 인증기는 85.6%, 95.5%의 인증율과 거절율을 보였으며, 93.5%와 90.0%의 평균 확률을 보였다.. 실험을 통하여 화자독립 인증기의 경우가 화자종속 인증기의 경우보다 낮은 인식율을 보였지만, 화자종속 인증기에서 나타나는 코드북 훈련시에 발생하는 메모리 문제를 해결 할 수 있었다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.9
• /
• pp.347-352
• /
• 2012

In this paper, an 2D spatial-map construction for workers identification and avoidance of AGV using the detection scheme of the spatial coordinates based on stereo camera is proposed. In the proposed system, face area of a moving person is detected from a left image among the stereo image pairs by using the YCbCr color model and its center coordinates are computed by using the centroid method and then using these data, the stereo camera embedded on the mobile robot can be controlled for tracking the moving target in real-time. Moreover, using the disparity map obtained from the left and right images captured by the tracking-controlled stereo camera system and the perspective transformation between a 3-D scene and an image plane, depth map can be detected. From some experiments on AGV driving with 240 frames of the stereo images, it is analyzed that error ratio between the calculated and measured values of the worker's width is found to be very low value of 2.19% and 1.52% on average.

• The KIPS Transactions:PartA
• /
• v.12A no.1 s.91
• /
• pp.13-22
• /
• 2005

Similarly to the edges defined in a 2D image, we can define the geometric features representing the boundary of the distinctive parts appearing on 3D meshes. The geometric features have been used as basic primitives in several applications such as mesh simplification, mesh deformation, and mesh editing. In this paper, we propose geometric livewire and geometric livelane for extracting geometric features in a 3D mesh, which are the extentions of livewire and livelane methods in images. In these methods, approximate curvatures are adopted to represent the geometric features in a 3D mesh and the 3D mesh itself is represented as a weighted directed graph in which cost functions are defined for the weights of edges. Using a well-known shortest path finding algorithm in the weighted directed graph, we extracted geometric features in the 3D mesh among points selected by a user. In this paper, we also visualize the results obtained from applying the techniques to extracting geometric features in the general meshes modeled after human faces, cows, shoes, and single teeth.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.6
• /
• pp.1333-1337
• /
• 2011

3D engines loading, and expansion of the usable capacity, next-generation smartphone game markets are rising briskly by the improvement in CPU processing speed of Phones (hardware of smartphone). Therefore, in creating 3D game characters, realistic and free-form animations in a small screen of a smartphone are becoming important. Through this paper, as a method of creating characters and operating for game characters to cause user's feeling, with NURBS data of MAYA, We completed a face in turns of eyes, a nose, and a mouth, and with Polygon Cube tool, modeled hands and feet. After dividing a cube into half and modeling it, through mirror copying We completed the whole body and modeled the low-polygon. Then to model realistic and free-form characters, We completed each detail with ZBrush and applied Divide level up to 4. Though they might look rough and exaggerated, We tried to express stuck-out parts and fallen-in parts effectively and smoothly with Smooth brush effect, map and design the low-polygon 3D characters.

• Journal of Advanced Navigation Technology
• /
• v.15 no.6
• /
• pp.1132-1137
• /
• 2011

In this paper, we propose Modified Multi CAMShift Algorithm(Modified Multi Continuously Adaptive Mean Shift Algorithm) that extracts skin color area and tracks several human body parts for real-time human tracking system. Skin color area is extracted by filtering input image in predefined RGB value range. These areas are initial search windows of hands and face for tracking. Gaussian background model prevents search window expending because it restricts skin color area. Also when occluding between these areas, we give more weights in occlusion area and move mass center of target area in color probability distribution image. As result, the proposed algorithm performs better than the original CAMShift approach in multiple object tracking and even when occluding of objects with similar colors.

• Journal of Digital Convergence
• /
• v.18 no.11
• /
• pp.459-464
• /
• 2020

This study is a study that analyzes the user experience of a virtual makeup application in the beauty industry where color or formulation testing is important. Recently, cases of beauty smart stores and beauty applications using AR and AI are increasing. However, since virtual makeup is different from testing a real product, it is necessary to derive needs through research from the user's side. In order to compare user preferences by using AR and AI cases, six factors based on the emotional interface model were analyzed through a questionnaire to identify items with statistically significant figures. As a result, the user felt comfortable with the virtual makeup function, but showed that it needs to be supplemented in terms of reliability. Since this study focused on the customer experience as a real user and identified the main experience factors and needs of virtual makeup through two types of comparison, it is hoped that this study will be useful as a prior study.