• Journal of Korea Multimedia Society
• /
• v.7 no.3
• /
• pp.438-449
• /
• 2004

More and more users are using the query e-mail according to the increment of use of internet. The operator of internet site desires the users to check the FAQ and Q＆A contents first before sending the query e-mail to the operator However the users try to get the solution for a problem easily by simply sending a query e-mail. Therefore the increment of query e-mail is inevitable, and the site operator is suffering from too heavy loads and spending too much time and cost to reply the query e-mail. In this paper, we are proposing an efficient method of classifying the query e-mail of users automatically by using a neural network. To verify the reasonability of our work, the query e-mails of KORNET are used as the test data, which is actually gathered in KT. A total of 210 learning data and 280 test data were used to test the performance of the proposed approach. From the experiments we got the encouraging result from the view point of application in real life. The proposed approach satisfied the request of users who wanted rapid response for their query e-mail.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.4
• /
• pp.2124-2148
• /
• 2017

Accurate facial expression recognition (FER) requires reliable signal filtering and the effective feature extraction. Considering these requirements, this paper presents a novel approach for FER which is robust to noise. The main contributions of this work are: First, to preserve texture details in facial expression images and remove image noise, we improved the anisotropic diffusion filter by adjusting the diffusion coefficient according to two factors, namely, the gray value difference between the object and the background and the gradient magnitude of object. The improved filter can effectively distinguish facial muscle deformation and facial noise in face images. Second, to further improve robustness, we propose a new feature descriptor based on a combination of the Histogram of Oriented Gradients with the Canny operator (Canny-HOG) which can represent the precise deformation of eyes, eyebrows and lips for FER. Third, Canny-HOG's block and cell sizes are adjusted to reduce feature dimensionality and make the classifier less prone to overfitting. Our method was tested on images from the JAFFE and CK databases. Experimental results in L-O-Sam-O and L-O-Sub-O modes demonstrated the effectiveness of the proposed method. Meanwhile, the recognition rate of this method is not significantly affected in the presence of Gaussian noise and salt-and-pepper noise conditions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.11
• /
• pp.5522-5536
• /
• 2017

In this paper, a video based smoke detection method using dynamic texture feature extraction with volume local binary patterns is studied. Block based method was used to distinguish smoke frames in high definition videos obtained by experiments firstly. Then we propose a method that directly extracts dynamic texture features based on irregular motion regions to reduce adverse impacts of block size and motion area ratio threshold. Several general volume local binary patterns were used to extract dynamic texture, including LBPTOP, VLBP, CLBPTOP and CVLBP, to study the effect of the number of sample points, frame interval and modes of the operator on smoke detection. Support vector machine was used as the classifier for dynamic texture features. The results show that dynamic texture is a reliable clue for video based smoke detection. It is generally conducive to reducing the false alarm rate by increasing the dimension of the feature vector. However, it does not always contribute to the improvement of the detection rate. Additionally, it is found that the feature computing time is not directly related to the vector dimension in our experiments, which is important for the realization of real-time detection.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2005.05a
• /
• pp.345-349
• /
• 2005

Massive amount of satellite image processing such asglobal/continental-level analysis and monitoring requires automated and speedy georegistration. There could be two major automated approaches: (1) rigid mathematical modeling using sensor model and ephemeris data; (2) heuristic co-registration approach with respect to existing reference image. In case of ETM+, the accuracy of the first approach is known as RMSE 250m, which is far below requested accuracy level for most of satellite image processing. On the other hands, the second approach is to find identical points between new image and reference image and use heuristic regression model for registration. The latter shows better accuracy but has problems with expensive computation. To improve efficiency of the coregistration approach, the author proposed a pre-qualified matching algorithm which is composed of feature extraction with canny operator and area matching algorithm with correlation coefficient. Throughout the pre-qualification approach, the computation time was significantly improved and make the registration accuracy is improved. A prototype was implemented and tested with the proposed algorithm. The performance test of 14 TM/ETM+ images in the U.S. showed: (1) average RMSE error of the approach was 0.47 dependent upon terrain and features; (2) the number average matching points were over 15,000; (3) the time complexity was 12 min per image with 3.2GHz Intel Pentium 4 and 1G Ram.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.181-185
• /
• 2006

Image co-registration is the process of overlaying two images of the same scene, one of which represents a reference image, while the other is geometrically transformed to the one. In order to improve efficiency and effectiveness of the co-registration approach, the author proposed a pre-qualified area matching algorithm which is composed of feature extraction with canny operator and area matching algorithm with cross correlation coefficient. For refining matching points, outlier detection using studentized residual was used and iteratively removes outliers at the level of three standard deviation. Throughout the pre-qualification and the refining processes, the computation time was significantly improved and the registration accuracy is enhanced. A prototype of the proposed algorithm was implemented and the performance test of 3 Landsat images of Korea showed: (1) average RMSE error of the approach was 0.436 Pixel (2) the average number of matching points was over 38,475 (3) the average processing time was 489 seconds per image with a regular workstation equipped with a 3 GHz Intel Pentium 4 CPU and 1 Gbytes Ram. The proposed approach achieved robustness, full automation, and time efficiency.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.315-322
• /
• 2006

Ant Colony System(ACS) is easily applicable to the traveling salesman problem(TSP) and it has demonstrated good performance on TSP. Recently, ACS has been emerged as the useful tool for the pattern recognition, feature extraction, and edge detection. The edge detection is wifely utilized in the area of document analysis, character recognition, and face recognition. However, the conventional operator-based edge detection approaches require additional postprocessing steps for the application. In the present study, in order to overcome this shortcoming, we have proposed the new ACS-based edge detection algorithm. The experimental results indicate that this proposed algorithm has the excellent performance in terms of robustness and flexibility.

• 전자공학회논문지 IE
• /
• v.48 no.2
• /
• pp.26-31
• /
• 2011

In this paper we show the LCD simulator for defect inspection using image processing algorithm and neural network. The defect inspection algorithm of the LCD consists of preprocessing, feature extraction and defect classification. Preprocess removes noise from LCD image, using morphology operator and neural network is used for the defect classification. Sample images with scratch, pinhole, and spot from real LCD color filter image are used. From some experiments results, the proposed algorithms show that defect detected and classified in the ratio of 92.3% and 94.5 respectively. Accordingly, in this paper, a possibility of practical implementation of the LCD defect inspection system is finally suggested.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.220-223
• /
• 2004

Automatic image registration is an essential element of remote sensing because remote sensing system generates enormous amount of data, which are multiple observations of the same features at different times and by different sensor. The general process of automatic image registration includes three steps: 1) The extraction of features to be used in the matching process, 2) the feature matching strategy and accurate matching process, 3) the resampling of the data based on the correspondence computed from matched feature. For step 2) and 3), we have developed an algorithms for automated registration of satellite images with RANSAC(Random Sample Consensus) in success. However, for step 1), There still remains human operation to generate GCP Chips, which is time consuming, laborious and expensive process. The main idea of this research is that we are able to automatically generate GCP chips with comer detection algorithms without GPS survey and human interventions if we have systematic corrected satellite image within adaptable positional accuracy. In this research, we use SUSAN(Smallest Univalue Segment Assimilating Nucleus) algorithm in order to detect the comer. SUSAN algorithm is known as the best robust algorithms for comer detection in the field of compute vision. However, there are so many comers in high-resolution images so that we need to reduce the comer points from SUSAN algorithms to overcome redundancy. In experiment, we automatically generate GCP chips from IKONOS images with geo level using SUSAN algorithms. Then we extract reference coordinate from IKONOS images and DEM data and filter the comer points using texture analysis. At last, we apply automatically collected GCP chips by proposed method and the GCP by operator to in-house automatic precision correction algorithms. The compared result will be presented to show the GCP quality.

• Journal of KIISE:Software and Applications
• /
• v.28 no.12
• /
• pp.947-954
• /
• 2001

In this paper, we propose a method for the recognition of various head gestures with automata technique applied to the sequence of facial pose states. Facial regions as detected by using the optimum facial color of I-component in YIQ model and the difference of images adaptively selected. And eye regions are extracted by using Sobel operator, projection, and the geometric location of eyes Hierarchical feature analysis is used to classify facial states, and automata technique is applied to the sequence of facial pose states to recognize 13 gestures: Gaze Upward, Downward, Left ward, Rightward, Forward, Backward Left Wink Right Wink Left Double Wink, Left Double Wink , Right Double Wink Yes, and No As an experimental result with total 1,488 frames acquired from 8 persons, it shows 99.3% extraction rate for facial regions, 95.3% extraction rate for eye regions 94.1% recognition rate for facial states and finally 99.3% recognition rate for head gestures. .

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.10
• /
• pp.520-529
• /
• 2005

A feature-based 3D modeling algorithm is presented in this paper. Since conventional methods use depth-based techniques, they need much time for the image matching to extract depth information. Even feature-based methods have less computation load than that of depth-based ones, the calculation of modeling error about whole pixels within a triangle is needed in feature-based algorithms. It also increase the computation time. Therefore, the proposed algorithm consists of three phases, which are an initial 3D model generation, model evaluation, and model refinement phases, in order to acquire an efficient 3D model. Intensity gradients and incremental Delaunay triangulation are used in the Initial model generation. In this phase, a morphological edge operator is adopted for a fast edge filtering, and the incremental Delaunay triangulation is modified to decrease the computation time by avoiding the calculation errors of whole pixels and selecting a vertex at the near of the centroid within the previous triangle. After the model generation, sparse vertices are matched, then the faces are evaluated with the size, approximation error, and disparity fluctuation of the face in evaluation stage. Thereafter, the faces which have a large error are selectively refined into smaller faces. Experimental results showed that the proposed algorithm could acquire an adaptive model with less modeling errors for both smooth and abrupt areas and could remarkably reduce the model acquisition time.