• Journal of Computing Science and Engineering
• /
• 제11권1호
• /
• pp.24-31
• /
• 2017

Face-based video retrieval has become an active and important branch of intelligent video analysis. Face profiling and matching is a fundamental step and is crucial to the effectiveness of video retrieval. Although many algorithms have been developed for processing static face images, their effectiveness in face-based video retrieval is still unknown, simply because videos have different resolutions, faces vary in scale, and different lighting conditions and angles are used. In this paper, we combined content-based and semantic-based image analysis techniques, and systematically evaluated four mainstream local features to represent face images in the video retrieval task: Harris operators, SIFT and SURF descriptors, and eigenfaces. Results of ten independent runs of 10-fold cross-validation on datasets consisting of TED (Technology Entertainment Design) talk videos showed the effectiveness of our approach, where the SIFT descriptors achieved an average F-score of 0.725 in video retrieval and thus were the most effective, while the SURF descriptors were computed in 0.3 seconds per image on average and were the most efficient in most cases.

• 제어로봇시스템학회논문지
• /
• 제8권3호
• /
• pp.275-280
• /
• 2002

A new algorithm for gradual scene change detection in MPEG based frame sequences is proposed in this paper. The proposed algorithm is based on the fact that most of gradual curves can be characterized by variance distributions of edge information in the frame sequences. Average edge frame sequences are obtained by performing "sober" edge detection. Features are extracted by comparing variances with those of local blocks in the average edge frames. Those features are further processed by the opening operation to obtain smoothing variance curves. The lowest variance in the local frame sequences is chosen as a gradual detection point. Experimental results show that the proposed method provides 85% precision and 86% recall rate fur gradual scene changes.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 D
• /
• pp.2634-2636
• /
• 2001

This paper proposes a new method of retrieving images from large image databases. The method is based on VQ(Vector Quantization) of local texture information at interest points automatically detected in an image. The texture features are extracted by Gabor wavelet filter bank, and rearranged for rotation. These features are classified by VQ and then construct a pattern histogram. Retrievals are performed by just comparing pattern histograms between images. Experimental results have shown the robustness of the proposed method to image rotation, small scale change, noise addition and brightness change and also shown the possibility of the retrieval by a partial image.

• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2003년도 하계학술대회 논문집
• /
• pp.62-65
• /
• 2003

We propose an algorithm for almost unsupervised detection of linear structures, in particular, axes in road network and river, as seen in synthetics aperture radar (SAR) images. The first is local step and used to extract linear features from the speckle radar image, which are treated as road segment candidates. We present two local line detectors as well as a method for fusing information from these detectors. The second is global step, we identify the real roads among the segment candidates by defining a Markov random field (MRF) on a set of segments, which introduces contextual knowledge about the shape of road objects.

• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2000년도 하계종합학술대회논문집
• /
• pp.221-224
• /
• 2000

We propose an algorithm for almost unsupervised detection of linear structures, in particular, axes in road network and river, as seen in synthetics aperture radar (SAR) images. The first is local step and used to extract linear features from the speckle radar image, which are treated as road segment candidates. We present two local line detectors as well as a method for fusing information from these detectors. The second is global step, we identify the real roads among the segment candidates by defining a Markov random field (MRF) on a set of segments, which introduces contextual knowledge about the shape of road objects.

• 대한두개안면성형외과학회지
• /
• 제19권4호
• /
• pp.283-286
• /
• 2018

Malignant pilomatricoma (pilomatrical carcinoma) is a rare, locally occurring malignant tumor with a high rate of recurrence in the case of incomplete excision. This tumor has two characteristics. First, recurrences of pilomatrical carcinoma are common; second, distant metastasis is rare, but if it occurs, it is very fatal. It has characteristic features of high mitotic counts, cellular atypia, and local invasion. Although fine needle aspiration and excisional biopsy could help to confirm this tumor diagnosis, pathologic findings are critical. Pilomatricomas have some characteristic features in histological aspect, such as epithelial islands of basaloid cells and shadow cells or ghost cell. Also, various types of immunohistochemical staining are used to confirm the diagnosis. Despite the lack of clear surgical criteria, treatment is a wide local excision with histologically clear resection margins with or without adjuvant radiotherapy.

• Smart Structures and Systems
• /
• 제23권4호
• /
• pp.393-403
• /
• 2019

Applying more features gives us better accuracy in modeling; however, increasing the inputs causes the curse of dimensions. In this paper, a new structure has been proposed for fault detecting and identifying (FDI) of high-dimensional systems. This structure consist of two structure. The first part includes Auto-Encoders (AE) as Deep Neural Networks (DNNs) to produce feature engineering process and summarize the features. The second part consists of the Local Model Networks (LMNs) with LOcally LInear MOdel Tree (LOLIMOT) algorithm to model outputs (multiple models). The fault detection is based on these multiple models. Hence the residuals generated by comparing the system output and multiple models have been used to alarm the faults. To show the effectiveness of the proposed structure, it is tested on single-shaft industrial gas turbine prototype model. Finally, a brief comparison between the simulated results and several related works is presented and the well performance of the proposed structure has been illustrated.

• 로봇학회논문지
• /
• 제17권4호
• /
• pp.425-430
• /
• 2022

As robots are considered one of the mainstream digital transformations, robots with machine vision becomes a main area of study providing the ability to check what robots watch and make decisions based on it. However, it is difficult to find a small object in the image mainly due to the flaw of the most of visual recognition networks. Because visual recognition networks are mostly convolution neural network which usually consider local features. So, we make a model considering not only local feature, but also global feature. In this paper, we propose a detection method of a small marker on the object using deep learning and an algorithm that considers global features by combining Transformer's self-attention technique with a convolutional neural network. We suggest a self-attention model with new definition of Query, Key and Value for model to learn global feature and simplified equation by getting rid of position vector and classification token which cause the model to be heavy and slow. Finally, we show that our model achieves higher mAP than state of the art model YOLOr.

• Smart Structures and Systems
• /
• 제15권2호
• /
• pp.375-393
• /
• 2015

In this study, local dynamic characteristics of mountable PZT interfaces are numerically analyzed to verify their feasibility on impedance monitoring of the prestress-loss in tendon anchorage subsystems. Firstly, a prestressed tendon-anchorage system with mountable PZT interfaces is described. Two types of mountable interfaces which are different in geometric and boundary conditions are designed for impedance monitoring in the tendon-anchorage subsystems. Secondly, laboratory experiments are performed to evaluate the impedance monitoring via the two mountable PZT interfaces placed on the tendon-anchorage under the variation of prestress forces. Impedance features such as frequency-shifts and root-mean-square-deviations are quantified for the two PZT interfaces. Finally, local dynamic characteristics of the two PZT interfaces are numerically analyzed to verify their performances on impedance monitoring at the tendon-anchorage system. For the two PZT interfaces, the relationships between structural parameters and local vibration responses are examined by modal sensitivity analyses.

• Journal of Electrical Engineering and Technology
• /
• 제12권1호
• /
• pp.402-410
• /
• 2017

For many years, researchers in face description area have been representing and recognizing faces based on different methods that include subspace discriminant analysis, statistical learning and non-statistics based approach etc. But still automatic face recognition remains an interesting but challenging problem. This paper presents a novel and efficient face image representation method based on Optimized Local Ternary Pattern (OLTP) texture features. The face image is divided into several regions from which the OLTP texture feature distributions are extracted and concatenated into a feature vector that can act as face descriptor. The recognition is performed using nearest neighbor classification method with Chi-square distance as a similarity measure. Extensive experimental results on Yale B, ORL and AR face databases show that OLTP consistently performs much better than other well recognized texture models for face recognition.