• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.411-420
• /
• 1999

In geology, lineament features have been used to identify geological events, and many of scientists have been developed the algorithm that can be applied with the computer to recognize the lineaments. We choose several edge detection filter, line detection filters and Hough transform to detect an edge, line, and to vectorize the extracted lineament features, respectively. firstly the edge detection filter using a first-order derivative is applied to the original image In this step, rough lineament image is created Secondly, line detection filter is used to refine the previous image for further processing, where the wrong detected lines are, to some extents, excluded by using the variance of the pixel values that is composed of each line Thirdly, the thinning process is carried out to control the thickness of the line. At last, we use the Hough transform to convert the raster image to the vector one. A Landsat image is selected to extract lineament features. The result shows the lineament well regardless of directions. However, the degree of extraction of linear feature depends on the values of parameters and patterns of filters, therefore the development of new filter and the reduction of the number of parameter are required for the further study.

• Journal of Institute of Control, Robotics and Systems
• /
• v.2 no.4
• /
• pp.324-329
• /
• 1996

In this paper, we present a vision algorithm to extract the tire information markings on the sidewall of tires. Since the appearance of tire marks is the same as its background, a primary feature to distinguish tire marks from their background is the roughness. Generally, the roughness of tire marks is different from that of its bakground: the surface of tire marks is smoother than the backgrounds. Light incident on the tire surface is reflected differently according to the roughness. For smoother surfaces, the surface irradiance is much stronger than that of rough surfaces. Based on these phenomena and observation, we propose an optimal illumination condition based on Torrance-Sparrow reflection model. We also develop an efficient reflectance-ratio based operator to extract the boundary of tire marks. Even with a very simple masking operation, we were able to obtain remarkable boundary extraction results from real experiments using many tires. By explicitly using the surface reflection model to explain the intensity variation on the black tire surface, we demonstrate that a physics-based vision method is powerful and feasible in extracting surface markings on tires.

• Journal of Korea Multimedia Society
• /
• v.18 no.10
• /
• pp.1189-1196
• /
• 2015

In this paper, we proposed automatic extraction of brain tumor using morphological operation and statistical tumors size in MR images. Neurosurgery have used gamma-knife therapy by MR images. However, the gamma-knife plan systems needs the brain tumor regions, because gamma-ray should intensively radiate to the brain tumor except for normal cells. Therefore, gamma-knife plan systems spend too much time on designating the tumor regions. In order to reduce the time of designation of tumors, we progress the automatical extraction of tumors using proposed method. The proposed method consist of two steps. First, the information of skull at MRI slices remove using statistical tumors size. Second, the ROI is extracted by tumor feature and average of tumors size. The detection of tumor is progressed using proposed and threshold method. Moreover, in order to compare the effeminacy of proposed method, we compared snap-shot and results of proposed method.

• Journal of KIISE:Software and Applications
• /
• v.36 no.12
• /
• pp.1009-1015
• /
• 2009

Handwriting verification is a technique of distinguishing the same person's handwriting specimen from imitations with any two or more texts using one's handwriting individuality. This paper suggests an effective verification method for the handwritten signature or text on the off-line environment using pattern recognition technology. The core processes of the method which has been researched in this paper are extraction of letter area, extraction of features employing structural characteristics of handwritten text, feature analysis employing DTW(Dynamic Time Warping) algorithm and PCA(Principal Component Analysis). The experimental results show a superior performance of the suggested method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.4
• /
• pp.328-336
• /
• 2012

In this paper, we propose a robust fingertip extraction and extended Continuously Adaptive Mean Shift (CAMSHIFT) based robust hand gesture recognition for natural human-like HRI (Human-Robot Interaction). Firstly, for efficient and rapid hand detection, the hand candidate regions are segmented by the combination with robust $YC_bC_r$ skin color model and haar-like features based adaboost. Using the extracted hand candidate regions, we estimate the palm region and fingertip position from distance transformation based voting and geometrical feature of hands. From the hand orientation and palm center position, we find the optimal fingertip position and its orientation. Then using extended CAMSHIFT, we reliably track the 2D hand gesture trajectory with extracted fingertip. Finally, we applied the conditional density propagation (CONDENSATION) to recognize the pre-defined temporal motion trajectories. Experimental results show that the proposed algorithm not only rapidly extracts the hand region with accurately extracted fingertip and its angle but also robustly tracks the hand under different illumination, size and rotation conditions. Using these results, we successfully recognize the multiple hand gestures.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.390-395
• /
• 2009

The robustness of audio fingerprinting system in a noisy environment is a principal challenge in the area of content-based audio retrieval. The selected feature for the audio fingerprints must be robust in a noisy environment and the computational complexity of the searching algorithm must be low enough to be executed in real-time. The audio fingerprint proposed by Philips uses expanded hash table lookup to compensate errors introduced by noise. The expanded hash table lookup increases the searching complexity by a factor of 33 times the degree of expansion defined by the hamming distance. We propose a new method to improve noise robustness of audio fingerprinting in noise environment using predominant pitch which reduces the bit error of created hash values. The sub-fingerprint of our approach method is computed in each time frames of audio. The time frame is transformed into the frequency domain using FFT. The obtained audio spectrum is divided into 33 critical bands. Finally, the 32-bit hash value is computed by difference of each bands of energy. And only store bits near predominant pitch. Predominant pitches are extracted in each time frames of audio. The extraction process consists of harmonic enhancement, harmonic summation and selecting a band among critical bands.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.7
• /
• pp.3076-3092
• /
• 2020

An IKPCA-ELM-based intrusion detection method is developed to address the problem of the low accuracy and slow speed of intrusion detection caused by redundancies and high dimensions of data in the network. First, in order to reduce the effects of uneven sample distribution and sample attribute differences on the extraction of KPCA features, the sample attribute mean and mean square error are introduced into the Gaussian radial basis function and polynomial kernel function respectively, and the two improved kernel functions are combined to construct a hybrid kernel function. Second, an improved particle swarm optimization (IPSO) algorithm is proposed to determine the optimal hybrid kernel function for improved kernel principal component analysis (IKPCA). Finally, IKPCA is conducted to complete feature extraction, and an extreme learning machine (ELM) is applied to classify common attack type detection. The experimental results demonstrate the effectiveness of the constructed hybrid kernel function. Compared with other intrusion detection methods, IKPCA-ELM not only ensures high accuracy rates, but also reduces the detection time and false alarm rate, especially reducing the false alarm rate of small sample attacks.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.6
• /
• pp.710-715
• /
• 2003

In this paper, we propose the new emotion recognition method for intelligently recognizing the human's emotion using the template vector and neural network. In the proposed method, human's emotion is divided into four emotion (surprise, anger, happiness, sadness). The proposed method is based on the template vector extraction and the template location recognition by using the color difference. It is not easy to extract the skin color area correctly using the single color space. To solve this problem, we propose the extraction method using the various color spaces and using the each template vectors. And then we apply the back-propagation algorithm by using the template vectors among the feature points). Finally, we show the practical application possibility of the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.245-265
• /
• 2022

In response to problems such as insufficient extraction information, low detection accuracy, and frequent misdetection in the field of Thangka image defects, this paper proposes a YOLOv5 prediction algorithm fused with the attention mechanism. Firstly, the Backbone network is used for feature extraction, and the attention mechanism is fused to represent different features, so that the network can fully extract the texture and semantic features of the defect area. The extracted features are then weighted and fused, so as to reduce the loss of information. Next, the weighted fused features are transferred to the Neck network, the semantic features and texture features of different layers are fused by FPN, and the defect target is located more accurately by PAN. In the detection network, the CIOU loss function is used to replace the GIOU loss function to locate the image defect area quickly and accurately, generate the bounding box, and predict the defect category. The results show that compared with the original network, YOLOv5-SE and YOLOv5-CBAM achieve an improvement of 8.95% and 12.87% in detection accuracy respectively. The improved networks can identify the location and category of defects more accurately, and greatly improve the accuracy of defect detection of Thangka images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.1
• /
• pp.80-87
• /
• 2004

In this paper we proposed the novel feature extraction method that is able to extract the individual characters from the license plate area of the car image more precisely by using the RGB color information and the fuzzy binarization newly proposed. The proposed method, first, extracts from the original image the areas that the pixels with the colors around the green are concentrated on as the candidate areas of the license plate, and selects the area with the most intensive distribution of pixels with the white color among the candidate areas as the license plate area. Second the noises of the license plate area should be removed by using 34{\times}$3 Sobel masking, and the fuzzy binarization method are proposed and applied to the license plate area to generate the binarized image of the license plate area. Lastly, the application of the contour tracking algorithm to the binarized area extracts the individual characters from the license plate area. The experiment on a variety of the real car images showed that the proposed method generates the higher rate of success for character extraction than the previous methods.