• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.3
• /
• pp.1-7
• /
• 2019

In this paper, we propose an approach to design a practical filter and a mathematical modeling for images. In the areas of signal processing, including high-dimensional image processing, the filtering process has been fundamental and crucial in diverse practical applications such as image processing, computer vision, and pattern recognition. In general, the ideal filter is modeled as circular-shaped in the 2D frequency domain as the rectangular shape is ideal for the 1D frequency domain. This paper proposes an approach to modeling practical and efficient image filter in the 2D frequency domain. Instead of employing a circular-shaped filter, this study proposes a polygon-shaped filter inspired by the concept of a hexagon cellular system for frequency reuse in wireless communication systems. By employing the concept of frequency reuse, bandwidth efficiency is also achieved in the frequency domain. To substantiate the proposed approach, quantitative evaluation is performed using PSNR.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.166-172
• /
• 2022

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.2
• /
• pp.119-125
• /
• 2023

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.200-208
• /
• 2022

In this study, an automatic information collection system and geographic information construction algorithm for the transportation disadvantaged using electric mobility aids are implemented using an object recognition model. Recognizes objects that the disabled person encounters while moving, and acquires coordinate information. It provides an improved route selection map compared to the existing geographic information for the disabled. Data collection consists of a total of four layers including the HW layer. It collects image information and location information, transmits them to the server, recognizes, and extracts data necessary for geographic information generation through the process of classification. A driving experiment is conducted in an actual barrier-free zone, and during this process, it is confirmed how efficiently the algorithm for collecting actual data and generating geographic information is generated.The geographic information processing performance was confirmed to be 70.92 EA/s in the first round, 70.69 EA/s in the second round, and 70.98 EA/s in the third round, with an average of 70.86 EA/s in three experiments, and it took about 4 seconds to be reflected in the actual geographic information. From the experimental results, it was confirmed that the walking weak using electric mobility aids can drive safely using new geographic information provided faster than now.

• Journal of Convergence for Information Technology
• /
• v.7 no.6
• /
• pp.143-151
• /
• 2017

The generalized Hough transform(GHough) can be used effectively for detecting and extracting an arbitrary-shaped 2-D model in an input image. However, the main drawbacks of the GHough are both heavy computation and an excessive storage requirement. Thus, most of the researches so far have focused on reducing both the time and space requirement of the GHough. But it is still not clear how well their improved algorithms will perform under various noise in an input image. Thus, this paper proposes a new framework that can measure the performance of the GHough quantitatively. For this purpose, we view the GHough as a detector in signal detection theory and the ROC curve will be used to specify the performance of the GHough. Finally, we show that we can evaluate the GHough under various noise conditions in an input image.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.77-91
• /
• 2022

Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changing over time.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.41-43
• /
• 2022

In order to prevent and block infectious diseases caused by the recent COVID-19 pandemic, non-contact biometric information acquisition and analysis technology is attracting attention. The invasive and attached biometric information acquisition method accurately has the advantage of measuring biometric information, but has a risk of increasing contagious diseases due to the close contact. To solve these problems, the non-contact method of extracting biometric information such as human fingerprints, faces, iris, veins, voice, and signatures with automated devices is increasing in various industries as data processing speed increases and recognition accuracy increases. However, although the accuracy of the non-contact biometric data acquisition technology is improved, the non-contact method is greatly influenced by the surrounding environment of the object to be measured, which is resulting in distortion of measurement information and poor accuracy. In this paper, we propose a context-based bio-signal modeling technique for the interpretation of personalized information (image, signal, etc.) for bio-information analysis. Context-based biometric information modeling techniques present a model that considers contextual and user information in biometric information measurement in order to improve performance. The proposed model analyzes signal information based on the feature probability distribution through context-based signal analysis that can maximize the predicted value probability.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.4
• /
• pp.35-41
• /
• 2001

This paper describes Linear Discriminant Analysis and common vector extraction for speech recognition. Voice signal contains psychological and physiological properties of the speaker as well as dialect differences, acoustical environment effects, and phase differences. For these reasons, the same word spelled out by different speakers can be very different heard. This property of speech signal make it very difficult to extract common properties in the same speech class (word or phoneme). Linear algebra method like BT (Karhunen-Loeve Transformation) is generally used for common properties extraction In the speech signals, but common vector extraction which is suggested by M. Bilginer et at. is used in this paper. The method of M. Bilginer et al. extracts the optimized common vector from the speech signals used for training. And it has 100％ recognition accuracy in the trained data which is used for common vector extraction. In spite of these characteristics, the method has some drawback-we cannot use numbers of speech signal for training and the discriminant information among common vectors is not defined. This paper suggests advanced method which can reduce error rate by maximizing the discriminant information among common vectors. And novel method to normalize the size of common vector also added. The result shows improved performance of algorithm and better recognition accuracy of 2％ than conventional method.

• Journal of Korea Multimedia Society
• /
• v.21 no.4
• /
• pp.450-463
• /
• 2018

Sound based machine fault diagnosis is the process consisting of detecting automatically the damages that affect the machines by analyzing the sounds they produce during their operating time. The collected sounds being inevitably corrupted by random disturbance, the most important part of the diagnosis consists of discovering the hidden elements inside the data that can reveal the faulty patterns. This paper presents a novel feature extraction methodology that combines various digital signal processing and pattern recognition methods for the analysis of the sounds produced by the drills. Using the Fourier analysis, the magnitude spectrum of the sounds are extracted, converted into two-dimensional vectors and uniformly normalized in such a way that they can be represented as 8-bit grayscale images. Histogram equalization is then performed over the obtained images in order to adjust their very poor contrast. The obtained contrast enhanced images will be used as the features of our diagnosis system. Finally, principal component analysis is performed over the image features for reducing their dimensions and a nonlinear classifier is adopted to produce the final response. Unlike the conventional features, the results demonstrate that the proposed feature extraction method manages to capture the hidden health patterns of the sound.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.427-430
• /
• 2007

Many victims and property damages are caused in fires every year. In this paper, flame and smoke detection algorithm by using image processing technique is proposed to early alarm fires. The first decision of proposed algorithms is to check candidate of flame region with its unique color distribution distinguished from artificial lights. If it is not a flame region then we can check to candidate of smoke region by measuring difference of brightness and chroma at present frame. If we just check flame and smoke with only simple brightness and hue, we will occasionally get false alarms. Therefore we also use motion information about candidate of flame and smoke regions. Finally, to determine the flame after motion detection, activity information is used. And in order to determine the smoke, edges detection method is adopted. As a result of simulation with real CCTV video signal, it is shown that the proposed algorithm is useful for early fire recognition.