• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.10
• /
• pp.5120-5142
• /
• 2018

Social media enables customers to share their views, opinions and experiences as product reviews. These product reviews facilitate customers in buying quality products. Due to the significance of online reviews, fake reviews, commonly known as spam reviews are generated to mislead the potential customers in decision-making. To cater this issue, review spam detection has become an active research area. Existing studies carried out for review spam detection have exploited feature engineering approach; however limited number of features are considered. This paper proposes a Feature-Centric Model for Review Spam Detection (FMRSD) to detect spam reviews. The proposed model examines a wide range of feature sets including ratings, sentiments, content, and users. The experimentation reveals that the proposed technique outperforms the baseline and provides better results.

• The Journal of Korea Robotics Society
• /
• v.16 no.2
• /
• pp.103-111
• /
• 2021

This study addresses a low-cost lidar sensor-based glass feature extraction method for an accurate map representation using statistical moments, i.e. the mean and variance. Since the low-cost lidar sensor produces range-only data without intensity and multi-echo data, there are some difficulties in detecting glass-like objects. In this study, a principle that an incidence angle of a ray emitted from the lidar with respect to a glass surface is close to zero degrees is concerned for glass detection. Besides, all sensor data are preprocessed and clustered, which is represented using statistical moments as glass feature candidates. Glass features are selected among the candidates according to several conditions based on the principle and geometric relation in the global coordinate system. The accumulated glass features are classified according to the distance, which is lastly represented on the map. Several experiments were conducted in glass environments. The results showed that the proposed method accurately extracted and represented glass windows using proper parameters. The parameters were empirically designed and carefully analyzed. In future work, we will implement and perform the conventional SLAM algorithms combined with our glass feature extraction method in glass environments.

• Convergence Security Journal
• /
• v.8 no.4
• /
• pp.161-166
• /
• 2008

This paper proposes a new approach to align 3D data sets by using curvatures of feature surface. We use the Gaussian curvatures and the covariance matrix which imply the physical characteristics of the model to achieve registration of unaligned 3D data sets. First, the physical characteristics of local area are obtained by the Gaussian curvature. And the camera position of 3D range finder system is calculated from by using the projection matrix between 3D data set and 2D image. Then, the physical characteristics of whole area are obtained by the covariance matrix of the model. The corresponding points can be found in the overlapping region with the cross-projection method and it concentrates by removed points of self-occlusion. By the repeatedly the process discussed above, we finally find corrected points of overlapping region and get the optimized registration result.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.1
• /
• pp.7-16
• /
• 2010

Face recognition of face images is an active subject in the area of computer pattern recognition, which has a wide range of potential. Automatic extraction of face image of the feature points is an important step during automatic face recognition. Whether correctly extract the facial feature has a direct influence to the face recognition. In this paper, a new method of facial feature extraction based on Discrete Wavelet Transform is proposed. Firstly, get the face image by using PC Camera. Secondly, decompose the face image using discrete wavelet transform. Finally, we use the horizontal direction, vertical direction projection method to extract the features of human face. According to the results of the features of human face, we can achieve face recognition. The result show that this method could extract feature points of human face quickly and accurately. This system not only can detect the face feature points with great accuracy, but also more robust than the tradition method to locate facial feature image.

• Korean Institute of Interior Design Journal
• /
• v.22 no.5
• /
• pp.152-161
• /
• 2013

This study is about the visual appreciation by sex with the analysis of time range of observing data which was got through observation experiment with the space of lobby in hospitals. The observation data of the subjects who observed the space include the frequency and time, through which the process of visual appreciation could be evaluated with the definition of the frequency and the time of observation. First, the fact that men had higher frequency of observation than women means the former had more movement than the latter, and another fact of their fewer times can be understood as the time of their staying was shorter. That is, even though the men had more movements of sight, they showed the feature of staying shorter. Second, the rate high and low of observation frequency and times made it possible for observation characteristics to be defined as 'intensive search' 'active search' 'fixed concentration' and 'search wandering.' The definition of understanding this process of visual appreciation can be available for a frame of effective analysis of observation characteristics according to the passage of time. Third, the intense search is the case of 'high frequency' having the feature of high visual appreciation owing to the active visual actions for acquiring information. Men were found to have more intense search which decreased gradually as time passed, while women showed the feature of many times of intense search. Fourth, it was found that with many observation data in a certain range of time the subjects had fixed concentration, where women were found to have repetitive fixed concentration along with the change of observation time while men were seen to have more observation tendency for fixed concentration. Fifth, at the cross tabulation of frequency and times, men had the feature of dispersed visual appreciation while women had more distinction between fixation and movement, which revealed that there is surely the difference between men and women in the process of visual appreciation.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.4
• /
• pp.17-22
• /
• 2020

Behavior-based authentication technology, which is currently being researched a lot, requires a long extraction of a lot of data to increase the recognition rate of authentication compared to other authentication technologies. This paper uses the touch sensor and the gyroscope embedded in the smartphone in the Android environment to measure five times to the user to use only the minimum data that is essential among the behavior feature data used in the behavior-based authentication study. By requesting, a total of six behavior feature data were collected by touching the five touch screen, and the mean value was calculated from the changes in data during the next touch measurement to measure the cosine similarity between the value and the measured value. After generating the allowable range of cosine similarity by performing, we propose a user behavior based authentication method that compares the cosine similarity value of the authentication attempt data. Through this paper, we succeeded in demonstrating high performance from the first EER of 37.6% to the final EER of 1.9% by adjusting the threshold applied to the cosine similarity authentication range even in a small number of feature data and experimenter environments.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.116-122
• /
• 2010

This paper proposes a method for classifying targets robust to geometric transformations of targets such as rotation, scale change, translation, and pose change. Targets which have rotation, scale change, and shift is firstly classified based on CM(Confidence Map) which is generated by similarity, scale ratio, and range of orientation for SIFT(Scale-Invariant Feature Transform) feature vectors. On the other hand, DB(DataBase) which is acquired in various angles is used to deal with pose variation of targets. Range of the angle is determined by comparing and analyzing the execution time and performance for sampling intervals. We experiment on various images which is geometrically changed to evaluate performance of proposed target classification method. Experimental results show that the proposed algorithm has a good classification performance.

• Journal of Sensor Science and Technology
• /
• v.30 no.2
• /
• pp.76-81
• /
• 2021

In this study, we propose a machine vision system with a high object recognition rate. By utilizing a multiple-exposure image sensing technique, the proposed deep learning-based machine vision system can cover a wide light intensity range without further learning processes on the various light intensity range. If the proposed machine vision system fails to recognize object features, the system operates in a multiple-exposure sensing mode and detects the target object that is blocked in the near dark or bright region. Furthermore, short- and long-exposure images from the multiple-exposure sensing mode are synthesized to obtain accurate object feature information. That results in the generation of a wide dynamic range of image information. Even with the object recognition resources for the deep learning process with a light intensity range of only 23 dB, the prototype machine vision system with the multiple-exposure imaging method demonstrated an object recognition performance with a light intensity range of up to 96 dB.

• 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.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.143-151
• /
• 2012

A new data-driven method for the design of a blind modulation frequency filter that suppresses the slow-varying noise components is proposed. The proposed method is based on the temporal local decorrelation of the feature vector sequence, and is done on an utterance-by-utterance basis. Although the conventional modulation frequency filtering approaches the same form regardless of the task and environment conditions, the proposed method can provide an adaptive modulation frequency filter that outperforms conventional methods for each utterance. In addition, the method ultimately performs channel normalization in a feature domain with applications to log-spectral parameters. The performance was evaluated by speaker-independent isolated-word recognition experiments under additive noise environments. The proposed method achieved outstanding improvement for speech recognition in environments with significant noise and was also effective in a range of feature representations.