• Journal of Information Processing Systems
• /
• v.11 no.3
• /
• pp.325-341
• /
• 2015

This paper describes the Tezpur University dataset of online handwritten Assamese characters. The online data acquisition process involves the capturing of data as the text is written on a digitizer with an electronic pen. A sensor picks up the pen-tip movements, as well as pen-up/pen-down switching. The dataset contains 8,235 isolated online handwritten Assamese characters. Preliminary results on the classification of online handwritten Assamese characters using the above dataset are presented in this paper. The use of the support vector machine classifier and the classification accuracy for three different feature vectors are explored in our research.

• Korean Journal of Remote Sensing
• /
• v.25 no.3
• /
• pp.287-294
• /
• 2009

KOMPSAT-2 like other high-resolution satellites has the time and angle difference in the acquisition of the panchromatic (PAN) and multispectral (MS) images because the imaging systems have the offset of the charge coupled device combination in the focal plane. Due to the differences, high altitude and moving objects, such as clouds, have a different position between the PAN and MS images. Therefore, a mis-registration between the PAN and MS images occurs when a registration algorithm extracted matching points from these cloud objects. To overcome this problem, we proposed a new registration method. The main idea is to discard the matching points extracted from cloud boundaries by using an automatic thresholding technique and a classification technique on a distance disparity map of the matching points. The experimental result demonstrates the accuracy of the proposed method at ground region around cloud objects is higher than a general method which does not consider cloud objects. To evaluate the proposed method, we use KOMPSAT-2 cloudy images.

• Advances in Computational Design
• /
• v.8 no.3
• /
• pp.255-271
• /
• 2023

The gear drive of a combat aircraft engine is responsible for power transmission to the different accessories necessary for the engine's operation. Incorrect power transmission can occur due to the presence of failure modes in the gears like bending fatigue, pitting, adhesive wear, scuffing, abrasive wear and polished wear etc. Fault diagnosis of the gear drive is necessary to get an early indication of failure of the gears. The present research is to develop an algorithm using different vibration signal processing techniques on industrial vibration acquisition systems to establish gear fault diagnosis architecture. The signal processing techniques have been used to extract various feature vectors in the development of the fault diagnosis architecture. An open-source dataset of other gear fault conditions is used to validate the developed architecture. The results is a basis for development of artificial intelligence based expert systems for gear fault diagnosis of a combat aircraft engine.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1206-1208
• /
• 2003

The extraction of earthquake damage from remote sensed imagery requires high spatial resolution and temporal effectiveness of acquisition of imagery. The analog photographs and visual interpretation were taken traditionally. Now it is possible to acquire damage information from many commercial high resolution RS satellites. The key techniques are processing velocity and precision. The authors developed the automatic / semiautomatic image process techniques including feature enhancement, and classification, designed the emergency Earthquake Damage and Losses Evaluate System based on Remote Sensing (RSEDLES). The paper introduced the functions of RSEDLES as well as its application to the earthquakes occurred recently.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.576-589
• /
• 2023

To upgrade home style recommendations and user satisfaction, this paper proposes a personalized and optimized recommendation algorithm for interior design style based on local social network, which includes data acquisition by three-dimensional (3D) model, home-style feature definition, and style association mining. Through the analysis of user behaviors, the user interest model is established accordingly. Combined with the location-based social network of association rule mining algorithm, the association analysis of the 3D model dataset of interior design style is carried out, so as to get relevant home-style recommendations. The experimental results show that the proposed algorithm can complete effective analysis of 3D interior home style with the recommendation accuracy of 82% and the recommendation time of 1.1 minutes, which indicates excellent application effect.

• ETRI Journal
• /
• v.46 no.3
• /
• pp.513-525
• /
• 2024

Deep neural networks trained on labeled medical data face major challenges owing to the economic costs of data acquisition through expensive medical imaging devices, expert labor for data annotation, and large datasets to achieve optimal model performance. The heterogeneity of diseases, such as Alzheimer's disease, further complicates deep learning because the test cases may substantially differ from the training data, possibly increasing the rate of false positives. We propose a reconstruction-based self-supervised anomaly detection model to overcome these challenges. It has a dual-subnetwork encoder that enhances feature encoding augmented by skip connections to the decoder for improving the gradient flow. The novel encoder captures local and global features to improve image reconstruction. In addition, we introduce an entropy-based image conversion method. Extensive evaluations show that the proposed model outperforms benchmark models in anomaly detection and classification using an encoder. The supervised and unsupervised models show improved performances when trained with data preprocessed using the proposed image conversion method.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.05a
• /
• pp.81-86
• /
• 2002

In current CBR(Case-Based Reasoning) systems, the case adaptation is usually performed by rule-based method that use rules hand-coded by the system developer. So, CBR system designer faces knowledge acquisition bottleneck similar to those found in traditional expert system design. In this thesis, 1 present a model for learning method of case adaptation knowledge using case base. The feature difference of each pair of cases are noted and become the antecedent part of an adaptation rule, the differences between the solutions in the compared cases become the consequent part of the rule. However, the number of rules that can possibly be discovered using a learning algorithm is enormous. The first method for finding cases to compare uses a syntactic measure of the distance between cases. The threshold fur identification of candidates for comparison is fixed th the maximum number of differences between the target and retrived case from all retrievals. The second method is to use similarity metric since the threshold method may not be an accurate measure. I suggest the elimination method of duplicate rules. In the elimination process, a confidence value is assigned to each rule based on its frequency. The learned adaptation rules is applied in riven target Problem. The basic. process involves search for all rules that handle at least one difference followed by a combination process in which complete solutions are built.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.27 no.2
• /
• pp.119-125
• /
• 2017

The mud flat in Korea is the geographical feature generated from the sediment of rivers of Korea and China and it is the important topography for pollution purification and fishing industry. The mud flat is difficult to access such that it requires the aerial survey for the high-resolution spatial information of the area. In this study we used drones instead of the conventional aerial and remote sensing approaches which have shortcomings of costs and revisit times. We carried out GPS-based control point survey, temporal image acquisition using drones, bundle adjustment, stereo image processing for DSM and ortho photo generation, followed by co-registration between the spatio-temporal information.

• Journal of KIISE:Software and Applications
• /
• v.31 no.1
• /
• pp.71-81
• /
• 2004

Minutiae-based fingerprint identification systems use minutiae points, which cannot completely characterize local ridge structures. Further, this method requires many methods for matching two fingerprint images containing different number of minutiae points. Therefore, to represent the fired length information for one fingerprint image, the filterbank-based method was proposed as an alternative to minutiae-based fingerprint representation. However, it has two shortcomings. One shortcoming is that similar feature vectors are extracted from the different fingerprints which have the same fingerprint type. Another shortcoming is that this method has overload to reduce the rotation error in the fingerprint image acquisition. In this paper, we propose the minutia-weighted feature vector extraction method that gives more weight in extracting feature value, if the region has minutiae points. Also, we Propose new fingerprint alignment method that uses the average local orientations around the reference point. These methods improve the fingerprint system's Performance and speed, respectively. Experimental results indicate that the proposed methods can reduce the FRR of the filterbank-based fingerprint matcher by approximately 0.524% at a FAR of 0.967%, and improve the matching performance by 5% in ERR. The system speed is over 1.28 times faster.

• 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.