• Current Optics and Photonics
• /
• v.1 no.6
• /
• pp.587-597
• /
• 2017

The extraction of the valid measurement region from the interference fringe pattern is a significant step when measuring gear tooth flank form deviation with grazing incidence interferometry, which will affect the measurement accuracy. In order to overcome the drawback of the conventionally used method in which the object image pattern must be captured, an improved segmentation approach is proposed in this paper. The interference fringe patterns feature, which is smoothed by the nonlinear diffusion, would be extracted by the structure tensor first. And then they are incorporated into the vector-valued Chan-Vese model to extract the valid measurement region. This method is verified in a variety of interference fringe patterns, and the segmentation results show its feasibility and accuracy.

• Journal of Korea Multimedia Society
• /
• v.11 no.9
• /
• pp.1195-1203
• /
• 2008

Onomatopoeia of korean documents is to represent from natural or artificial sound to human language and it can express onomatopoeia language which is the nearest an object and also able to utilize as standard for clustering of Multimedia data. In this study, We get frequency of onomatopoeia in the experiment subject and select 100 onomatopoeia of use to our study In order to cluster onomatopoeia's relation, we extract feature of similarity and distance metric and then represent onomatopoeia's relation on vector space by using PCA. At the end, we can clustering onomatopoeia by using k-means algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.3 no.1
• /
• pp.84-95
• /
• 2009

The ubiquitous smart home is the home of the future, which exploits context information from both the human and the home environment, providing an automatic home service for the human. Human location and motion are the most important contexts in the ubiquitous smart home. In this paper, we present a real-time human tracker that predicts human location and motion for the ubiquitous smart home. The system uses four network cameras for real-time human tracking. This paper explains the architecture of the real-time human tracker, and proposes an algorithm for predicting human location and motion. To detect human location, three kinds of images are used: $IMAGE_1$ - empty room image, $IMAGE_2$ - image of furniture and home appliances, $IMAGE_3$ - image of $IMAGE_2$ and the human. The real-time human tracker decides which specific furniture or home appliance the human is associated with, via analysis of three images, and predicts human motion using a support vector machine (SVM). The performance experiment of the human's location, which uses three images, lasted an average of 0.037 seconds. The SVM feature of human motion recognition is decided from the pixel number by the array line of the moving object. We evaluated each motion 1,000 times. The average accuracy of all types of motion was 86.5%.

• Journal of Computing Science and Engineering
• /
• v.9 no.4
• /
• pp.204-213
• /
• 2015

Under the conditional independence assumption among local features, the Naive Bayes Nearest Neighbor (NBNN) classifier has been recently proposed and performs classification without any training or quantization phases. While the original NBNN shows high classification accuracy without adopting an explicit training phase, the conditional independence among local features is against the compositionality of objects indicating that different, but related parts of an object appear together. As a result, the assumption of the conditional independence weakens the accuracy of classification techniques based on NBNN. In this work, we look into this issue, and propose a novel Bayesian network for an NBNN based classification to consider the conditional dependence among features. To achieve our goal, we extract a high-level feature and its corresponding, multiple low-level features for each image patch. We then represent them based on a simple, two-level layered Bayesian network, and design its classification function considering our Bayesian network. To achieve low memory requirement and fast query-time performance, we further optimize our representation and classification function, named relation-based Bayesian network, by considering and representing the relationship between a high-level feature and its low-level features into a compact relation vector, whose dimensionality is the same as the number of low-level features, e.g., four elements in our tests. We have demonstrated the benefits of our method over the original NBNN and its recent improvement, and local NBNN in two different benchmarks. Our method shows improved accuracy, up to 27% against the tested methods. This high accuracy is mainly due to consideration of the conditional dependences between high-level and its corresponding low-level features.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.13-22
• /
• 2004

Because video sequence consists of dynamic objects in nature, the object motion in video is an effective feature in describing the contents of video sequence and motion feature plays an important role in video retrieval. In this paper, we propose a method that converts motion vectors (MVs) to a uniform set on MPEG coded domain, independent of the frame type and the direction of prediction, and utilizes these normalized MVs (N-MVs) as motion descriptor to understand video contents. We describe a frame-type independent representation of the various types of frames presented in an MPEG video in which all frames can be considered equivalently, without full-decoding. In the experiments, we show that the proposed method is better than the conventional one in terms of performance.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.6
• /
• pp.565-570
• /
• 2013

The mirror neuron regions which are distributed in cortical area handled a functionality of intention recognition on the basis of imitative learning of an observed action which is acquired from visual-information of a goal-directed action. In this paper an automated intention recognition system is proposed by applying computational model of mirror neuron system to the human-robot interaction system. The computational model of mirror neuron system is designed by using dynamic neural networks which have model input which includes sequential feature vector set from the behaviors from the target object and actor and produce results as a form of motor data which can be used to perform the corresponding intentional action through the imitative learning and estimation procedures of the proposed computational model. The intention recognition framework is designed by a system which has a model input from KINECT sensor and has a model output by calculating the corresponding motor data within a virtual robot simulation environment on the basis of intention-related scenario with the limited experimental space and specified target object.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.12
• /
• pp.2836-2842
• /
• 2010

An NPC grouping method is proposed for various 3D games depending on their characteristics. Immovable objects tend to have particular orientation features in their Gabor filtering results whereas the movable objects controlled by AI appearing as a human or an animal do not. First of all, We analyzed directional and frequency domain features in the NPC object and configured them as 24 Gabor filter banks. Then, 24-dimensional feature vectors according to the scale and direction of the filter are calculated. Each extracted vector represents the energy of a certain direction. This energy indicates the particular direction strength of the object texture. Thus, using this property, NPCs could be grouped as artificial objects and natural objects effectively and it draws the game more speed and strategic actions as a result.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.6
• /
• pp.682-689
• /
• 2019

In part-based image representation, the partial shapes of an object are represented as basis vectors, and an image is decomposed as a linear combination of basis vectors where the coefficients of those basis vectors represent the partial (or local) feature of an object. In this paper, a face recognition for occluded faces is proposed in which face images are represented using non-negative matrix factorization(NMF), one of part-based representation techniques, and recognized using an artificial neural network technique. Standard NMF, projected gradient NMF and orthogonal NMF were used in part-based representation of face images, and their performances were compared. Learning vector quantizer were used in the recognizer where Euclidean distance was used as the distance measure. Experimental results show that proposed recognition is more robust than the conventional face recognition for the occluded faces.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.6
• /
• pp.139-146
• /
• 2008

Masked fake face detection using ordinary visible images is a formidable task when the mask is accurately made with special makeup. Considering recent advances in special makeup technology, a reliable solution to detect masked fake faces is essential to the development of a complete face recognition system. This research proposes a method for masked fake face detection that exploits reflectance disparity due to object material and its surface color. First, we have shown that measuring of albedo can be simplified to radiance measurement when a practical face recognition system is deployed under the user-cooperative environment. This enables us to obtain albedo just by grey values in the image captured. Second, we have found that 850nm infrared light is effective to discriminate between facial skin and mask material using reflectance disparity. On the other hand, 650nm visible light is known to be suitable for distinguishing different facial skin colors between ethnic groups. We use a 2D vector consisting of radiance measurements under 850nm and 659nm illumination as a feature vector. Facial skin and mask material show linearly separable distributions in the feature space. By employing FIB, we have achieved 97.8% accuracy in fake face detection. Our method is applicable to faces of different skin colors, and can be easily implemented into commercial face recognition systems.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.2
• /
• pp.135-140
• /
• 2012

The mirror neuron system in the cerebrum, which are handled by visual information-based imitative learning. When we observe the observer's range of mirror neuron system, we can assume intention of performance through progress of neural activation as specific range, in include of partially hidden range. It is goal of our paper that imitative learning is applied to 3D vision-based intelligent system. We have experiment as stereo camera-based restoration about acquired 3D image our previous research Using Optical flow, unscented Kalman filter. At this point, 3D input image is sequential continuous image as including of partially hidden range. We used Hidden Markov Model to perform the intention recognition about performance as result of restoration-based hidden range. The dynamic inference function about sequential input data have compatible properties such as hand gesture recognition include of hidden range. In this paper, for proposed intention recognition, we already had a simulation about object outline and feature extraction in the previous research, we generated temporal continuous feature vector about feature extraction and when we apply to Hidden Markov Model, make a result of simulation about hand gesture classification according to intention pattern. We got the result of hand gesture classification as value of posterior probability, and proved the accuracy outstandingness through the result.