• 대한산업공학회지
• /
• 제41권4호
• /
• pp.389-395
• /
• 2015

According to much research on cognitive science, the impact of the scene-context on human visual search in real-world images could be as important as the saliency. Therefore, this study proposed a method of Adaptive Control of Thought-Rational (ACT-R) modeling of visual search in real-world images, based on saliency and scene-context. The modeling method was developed by using the utility system of ACT-R to describe influences of saliency and scene-context in real-world images. Then, the validation of the model was performed, by comparing the data of the model and eye-tracking data from experiments in simple task in which subjects search some targets in indoor bedroom images. Results show that model data was quite well fit with eye-tracking data. In conclusion, the method of modeling human visual search proposed in this study should be used, in order to provide an accurate model of human performance in visual search tasks in real-world images.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.89-92
• /
• 1996

In this paper, we developed visual tracking algorithm using double active bar. The active bar model to represent the object can reduce the search space of energy surface and better performance than those of snake model. However, the contour will not find global equilibrium when driving force caused by image may be weak. To overcome this problem. Double active bar is proposed for finding the global minimum point without any dependence on initialization. To achieve the goal, an deformable model with two initial contours in attempted to search for a global minimum within two specific initial contours. This approach improve the performance of finding the contour of target. To evaluate the performance, some experiments are executed. We can achieved the good result for tracking a object on noisy image.

• 대한임베디드공학회논문지
• /
• 제16권6호
• /
• pp.323-330
• /
• 2021

Visual object tracking is a challenging area of study in the field of computer vision due to many difficult problems, including a fast variation of target shape, occlusion, and arbitrary ground truth object designation. In this paper, we focus on the reinforced feature of the dynamic search area to get better performance than conventional discriminative model prediction trackers on the condition when the accuracy deteriorates since low feature discrimination. We propose a reinforced input feature method shown like the spotlight effect on the dynamic search area of the target tracking. This method can be used to improve performances for deep learning based discriminative model prediction tracker, also various types of trackers which are used to infer the center of the target based on the visual object tracking. The proposed method shows the improved tracking performance than the baseline trackers, achieving a relative gain of 38% quantitative improvement from 0.433 to 0.601 F-score at the visual object tracking evaluation.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 추계학술대회
• /
• pp.945-949
• /
• 2009

비디오 부호화 기법에서 압축률 및 화질을 결정하는 중요한 부분인 움직임 예측 및 보상(motion estimation and compensation)의 성능을 개선하기 위한 방법을 제안한다. 가장 기본적인 움직임 예측 기법인 전역 탐색 방법은 가장 좋은 화질을 보이지만, 현재 프레임의 각 블록과 가장 유사한 블록을 찾기 위하여 탐색영역(search area)내의 모든 점에 대해 탐색을 수행하므로 그 계산량이 매우 많게 된다. 따라서 좋은 화질을 유지하면서 계산량을 낮추기 위한 많은 고속 알고리즘이 제안되었는데, MPEG-4 표준에 채택된 PMVFAST는 움직임 벡터 간의 상관도를 이용하여 계산량을 낮추면서도 전역 탐색 기법에 근접한 화질을 보인다. 본 논문에서는 움직임 벡터의 예측을 위하여 중간값(median) 계산법에 의한 새로운 방법을 제안하고, 이를 이용하여 움직임 예측의 계산량을 획기적으로 줄일 수 있음을 보인다. 실험결과 제안한 알고리즘은 PMVFAST보다 빠르면서도 전역 탐색 기법보다 높은 평균 PNSR을 보인다.

• 반도체디스플레이기술학회지
• /
• 제13권2호
• /
• pp.45-52
• /
• 2014

This paper proposes an efficient photo retrieval system that automatically indexes for searching of relevant images, using a combination of geo-coded information, direction/location of image capture device and content-based visual features. A photo image is labeled with its GPS (Global Positioning System) coordinates and direction of the camera view at the moment of capture, and the label leads to generate a geo-spatial index with three core elements of latitude, longitude and viewing direction. Then, content-based visual features are extracted and combined with the geo-spatial information, for indexing and retrieving the photo images. For user's querying process, the proposed method adopts two steps as a progressive approach, filtering the relevant subset prior to use a content-based ranking function. To evaluate the performance of the proposed scheme, we assess the simulation performance in terms of average precision and F-score, using a natural photo collection. Comparing the proposed approach to retrieve using only visual features, an improvement of 20.8% was observed. The experimental results show that the proposed method exhibited a significant enhancement of around 7.2% in retrieval effectiveness, compared to previous work. These results reveal that a combination of context and content analysis is markedly more efficient and meaningful that using only visual feature for image search.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2002년도 International Meeting on Information Display
• /
• pp.1064-1067
• /
• 2002

The effects of different optical characteristics between desktop CRT and TFT-LCD were compared in terms of visual performance during a 4-hr visual text and icon search tasks. The result showed that CRT is more suitable for presenting graphic information whereas TFT-LCD is suitable for presenting text information at the state of the art display technology.

• 대한인간공학회지
• /
• 제21권1호
• /
• pp.95-112
• /
• 2002

Two experiments were carried out to compare the suitability in visual tasks between cathode-ray tube (CRT) and thin film transistor-liquid crystal display (TFT-LCD). In the first experiment, the subjects were requested to detect pre-assigned target words or icons among distracters presented under time-invariant (static) image mode. The subjects' visual performance and fatigue were assessed while carrying out search tasks with dim and bright ambient light conditions. Significant interaction effects were found among displays, task types, and ambient light conditions. Due to visual fatigue, the subjects' accommodative power decreased in the end of task and the degradation was more significant for the CRT users and under bright ambient light. IN the second experiment, the subjects performed information processing task with time-varying road signs at a driving simulator to assess interaction effects between display types and changing speed of dynamic image. The perception time using TFT-TCD was shorter under slow image change while that of CRT was shorter rapid image change. Findings from this study suggest that, to improve visual task performance, users should carefully select their visual display type depending on the task to be performed.

• 한국전자거래학회지
• /
• 제4권3호
• /
• pp.179-196
• /
• 1999

A cyber shopping mall is a place where consumers acquire the product information and make purchase decision in the cyber space. Even though there are many advantages over traditional malls, there are still several limitations to do shopping in an existing cyber mall. One of them is the absence of efficient search tool to handle various products specifications. Existing search systems usually support the "keyword search only" with limited product information. Consumers spend lots of their time and efforts in searching products and comparing them. Recently, some web sites provide the shopping mall comparison service that supports the additional search conditions such as price and maker. These services improve the situation but it is not still acceptable. In this paper, we propose an intelligent product search system based on a mediator which supports various conditional search for each product. Our system provides consumers with search results that satisfy purchase specifications. Our system is implemented in Visual basic and pert and experimental results show satisfactory performance.

• International Journal of Computer Science & Network Security
• /
• 제21권8호
• /
• pp.87-96
• /
• 2021

The demand for e-learning through video lectures is rapidly increasing due to its diverse advantages over the traditional learning methods. This led to massive volumes of web-based lecture videos. Indexing and retrieval of a lecture video or a lecture video topic has thus proved to be an exceptionally challenging problem. Many techniques listed by literature were either visual or audio based, but not both. Since the effects of both the visual and audio components are equally important for the content-based indexing and retrieval, the current work is focused on both these components. A framework for automatic topic-based indexing and search depending on the innate content of the lecture videos is presented. The text from the slides is extracted using the proposed Merged Bounding Box (MBB) text detector. The audio component text extraction is done using Google Speech Recognition (GSR) technology. This hybrid approach generates the indexing keywords from the merged transcripts of both the video and audio component extractors. The search within the indexed documents is optimized based on the Naïve Bayes (NB) Classification and K-Means Clustering models. This optimized search retrieves results by searching only the relevant document cluster in the predefined categories and not the whole lecture video corpus. The work is carried out on the dataset generated by assigning categories to the lecture video transcripts gathered from e-learning portals. The performance of search is assessed based on the accuracy and time taken. Further the improved accuracy of the proposed indexing technique is compared with the accepted chain indexing technique.

• 대한인간공학회지
• /
• 제30권2호
• /
• pp.365-373
• /
• 2011

The existing GOMS model overestimates the performance time of mouse activities because it describes them in a serial sequence. However, parallel movements of eye and hand(eye-hand coordination) have been dominant in mouse activities and this eye-hand coordination is the main factor for the overestimation of performance time. In this study, therefore, the revised CGOMSL model was developed to implement eye-hand coordination to the mouse activity to overcome one of the limitations of GOMS model, the lack of capability for parallel processing. The suggested revised CGOMSL model for drag activity, as an example for one of mouse activities in this study, begins visual search processing before a hand movement but ends the visual search processing with the hand movement in the same time. The results show that the revised CGOMSL model made the prediction of human performance more accurately than the existing GOMS model. In other words, one of the limitations of GOMS model, the incapability of parallel processing, could be overcome with the revised CGOMSL model so that the performance time should be more accurately predicted.