• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.3
• /
• pp.195-198
• /
• 2013

Many libraries utilize RFID tags for checking in and out of books. However, the recognition rate of this automatic process may depend on the orientation of antennas and RFID tags. Therefore we need supplemental systems to improve the recognition rate. The proposed algorithm sets up the ROI of the book existing area from the input image and then performs Canny edge detection algorithm to extract edges of books. Finally Hough line transform algorithm allows to detect the number of books from the extracted edges. To evaluate the performance of the proposed method, we applied our method to 350 book images under various circumstances. We then analyzed the performance of proposed method from results using recognition and mismatch ratio. The experimental result gave us 97.1% accuracy in book counting.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.11-19
• /
• 2021

An abnormal object refers to a person, an object, or a mechanical device that performs abnormal and unusual behavior and needs observation or supervision. In order to detect this through artificial intelligence algorithm without continuous human intervention, a method of observing the specificity of temporal features using optical flow technique is widely used. In this study, an abnormal situation is identified by learning an algorithm that translates an input image frame to an optical flow image using a Generative Adversarial Network (GAN). In particular, we propose a technique that improves the pre-processing process to exclude unnecessary outliers and the post-processing process to increase the accuracy of identification in the test dataset after learning to improve the performance of the model's abnormal behavior identification. UCSD Pedestrian and UMN Unusual Crowd Activity were used as training datasets to detect abnormal behavior. For the proposed method, the frame-level AUC 0.9450 and EER 0.1317 were shown in the UCSD Ped2 dataset, which shows performance improvement compared to the models in the previous studies.

• Proceedings of the Korea Technical Association of the Pulp and Paper Industry Conference
• /
• 2003.11a
• /
• pp.230-248
• /
• 2003

In this work an integrated model for paper plants combining wet-end and dry section is developed and a model predictive control scheme based on the plant model is proposed. Closed-loop process identification method is employed to produce a state-space model. Thick stock, filler flow, machine speed and steam pressure are selected as Input variables and basis weight, ash content and moisture content are considered as output variables. The desired output trajectory is constructed in the form of 1st-order dynamics. Results of simulations for control of grade change operations are compared with plant operation data collected during the grade change operations under the same conditions as in simulations. From the comparison, we can see that the proposed model predictive control scheme reduces the grade change time and achieves stable steady-state.

• The Journal of the Korea Contents Association
• /
• v.7 no.2
• /
• pp.40-50
• /
• 2007

In this paper, we propose an efficient method for detecting and tracking multiple moving objects based on morphological region merging from real-time video sequences. The proposed approach consists of adaptive threshold extraction, morphological region merging and detecting and tracking of objects. Firstly, input frame is separated into moving regions and static regions using the difference of images between two consecutive frames. Secondly, objects are segmented with a reference background image and adaptive threshold values, then, the segmentation result is refined by morphological region merge algorithm. Lastly, each object segmented in a previous step is assigned a consistent identification over time, based on its spatio-temporal information. The experimental results show that a proposed method is efficient and useful in terms of real-time multiple objects detecting and tracking.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.2
• /
• pp.241-249
• /
• 1997

In this paper, a new technique is proposed for generating a minimum-length synchronizable test sequence that can be applied in the distributed test architecture where both external synchtonization and input/output operation costs are taken into consideration. the method defines a set of transformation rules that constructs a duplex digraph from a given finite state machine representation of a protocol specification rules that constructs a duplex digraph from a given finite state machine representation of a protocol specificatio such that a rural chinese postman tour of the duplex digraph can be used to generate a minimum-length synchronizable test sequence using synchronizable distinguishing sequences as the state identification sequence for each state of the given finite state machine. The method provides an elegant solution to the synchronization problem that arises during the application of a predetermined test sequence in some protocol test architectures that utilize remote testers.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.19 no.2 s.72
• /
• pp.125-138
• /
• 2006

The use of system identification approaches for damage detection has been expanded in recent years owing to the advancements in data acquisition system andinformation processing techniques. Soft computing techniques such as neural networks and genetic algorithm have been utilized increasingly for this end due to their excellent pattern recognition capability. In this study, damage detection of bridge structures using neural networks technique based on the modal properties is presented, which can effectively consider the modeling uncertainty in the analysis model from which the training patterns are to be generated. The differences or the ratios of the mode shape components between before and after damage are used as the input to the neural networks in this method, since they are found to be less sensitive to the modeling errors than the mode shapes themselves. Two numerical example analyses on a simple beam and a multi-girder bridge are presented to demonstrate the effectiveness and applicability of the proposed method.

• Journal of the Korean Geophysical Society
• /
• v.9 no.1
• /
• pp.1-6
• /
• 2006

To remove ringing and increase vertical resolution of GRP data, signature deconvolution was applied to GPR data obtained using a 100 MHz antenna in the Soyang Lake. The signature was extracted through stacking reflection signals from the lake bottom. Results of this deterministic deconvolution was compared with those from the conventional Wienner method. Due to increased vertical resolution, both deconvolution methods are able to resolve three or more layers in an apparent single layer on the input data. However, identification of reflection boundaries from ringing is not easy due to poor definition in the output data of the Wienner filter. On the contrary, the signature deconvolution greatly enhances both vertical resolution and definition of reflection boundaries, showing detailed internal stratigraphic features of the three sedimentary layers. Since extraction of signature at various depths is possible, this deconvolution method can be appled effectively to unstationary GPR data.

• Steel and Composite Structures
• /
• v.19 no.3
• /
• pp.569-583
• /
• 2015

Recent years, explosive welding structures have been widely used in many engineering fields. The bonding state detection of explosive welding structures is significant to prevent unscheduled failures and even catastrophic accidents. However, this task still faces challenges due to the complexity of the bonding interface. In this paper, a new method called dual-tree complex wavelet transform based permutation entropy (DTCWT-PE) is proposed to detect bonding state of such structures. Benefiting from the complex analytical wavelet function, the dual-tree complex wavelet transform (DTCWT) has better shift invariance and reduced spectral aliasing compared with the traditional wavelet transform. All those characters are good for characterizing the vibration response signals. Furthermore, as a statistical measure, permutation entropy (PE) quantifies the complexity of non-stationary signals through phase space reconstruction, and thus it can be used as a viable tool to detect the change of bonding state. In order to more accurate identification and detection of bonding state, PE values derived from DTCWT coefficients are proposed to extract the state information from the vibration response signal of explosive welding structure, and then the extracted PE values serve as input vectors of support vector machine (SVM) to identify the bonding state of the structure. The experiments on bonding state detection of explosive welding pipes are presented to illustrate the feasibility and effectiveness of the proposed method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.9
• /
• pp.2121-2128
• /
• 2015

In this paper presents a method of extracting reliable and regions of interest (ROI) in barcode for the purpose of factory automation. backgrounds are separated based on directional components and the characteristics of detected patterns. post-processing is performed on candidate images with analysis of problems caused by blur, rotation and areas of high similarity. In addition, the resizing factor is used to achieve faster calculations through image resizing. The input images contained multiple product or barcode for application to diverse automation environments; a high extraction success rate is accomplished despite the maximum shooting distance of 80 cm. Simulations involving images with various shooting distances gave an ROI detection rate of 100% and a post-processing success rate of 99.3%.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.12
• /
• pp.1772-1781
• /
• 2017

In this study, the design methodology for alleviating the overfitting problem of Polynomial Neural Networks(PNN) is realized with the aid of two kinds techniques such as L2 regularization and Sum of Squared Coefficients (SSC). The PNN is widely used as a kind of mathematical modeling methods such as the identification of linear system by input/output data and the regression analysis modeling method for prediction problem. PNN is an algorithm that obtains preferred network structure by generating consecutive layers as well as nodes by using a multivariate polynomial subexpression. It has much fewer nodes and more flexible adaptability than existing neural network algorithms. However, such algorithms lead to overfitting problems due to noise sensitivity as well as excessive trainning while generation of successive network layers. To alleviate such overfitting problem and also effectively design its ensuing deep network structure, two techniques are introduced. That is we use the two techniques of both SSC(Sum of Squared Coefficients) and $L_2$ regularization for consecutive generation of each layer's nodes as well as each layer in order to construct the deep PNN structure. The technique of $L_2$ regularization is used for the minimum coefficient estimation by adding penalty term to cost function. $L_2$ regularization is a kind of representative methods of reducing the influence of noise by flattening the solution space and also lessening coefficient size. The technique for the SSC is implemented for the minimization of Sum of Squared Coefficients of polynomial instead of using the square of errors. In the sequel, the overfitting problem of the deep PNN structure is stabilized by the proposed method. This study leads to the possibility of deep network structure design as well as big data processing and also the superiority of the network performance through experiments is shown.