• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.129-131
• /
• 2021

본 논문에서는 심층 특징 앙상블을 사용하여 목조 문화재의 변위 현상 중 하나인 배부름 현상을 감지할 수 있는 모델을 제안한다. 우선 총 4개의 서로 다른 사전 학습된 합성 곱 신경망을 사용하여 입력 영상에 대한 심층 특징들을 추출한다. 그 이후 4개의 서로 다른 심층 특징들을 결합하여 하나의 특징 벡터를 생성한다. 그 이후 합쳐진 특징 벡터는 완전 연결 계층의 입력 값으로 들어와서 최종적으로 변위가 존재하는지 아닌지에 대한 예측을 수행하게 된다. 데이터 셋으로는 충주시 근처의 문화재에 방문해서 수집한 목조 문화재 이미지를 가지고 정상 및 비정상으로 구분한 데이터 셋을 사용하였다. 실험 결과 심층 특징 앙상블 기법을 사용한 모델이 앙상블 기법을 사용하지 않은 모델보다 더 좋은 성능을 나타냄을 확인하였다. 이러한 결과로 부터 우리가 제안한 방법이 목재 문화재의 배부름 현상에 대한 변위 검출에 있어서 매우 적합함을 보여준다.

• Journal of IKEEE
• /
• v.18 no.4
• /
• pp.485-494
• /
• 2014

Traffic Sign Recognition(TSR) is an important element in an Advanced Driver Assistance System(ADAS). However, many studies related to TSR approaches only in normal daytime environment because a sign's unique color doesn't appear in poor environment such as night time, snow, rain or fog. In this paper, we propose a new TSR algorithm based on machine learning for daytime as well as poor environment. In poor environment, traditional methods which use RGB color region doesn't show good performance. So we extracted sign characteristics using HoG extraction, and detected signs using a Support Vector Machine(SVM). The detected sign is recognized by a decision tree based on 25 reference points in a Normalized RGB system. The detection rate of the proposed system is 96.4% and the recognition rate is 94% when applied in poor environment. The testing was performed on an Intel i5 processor at 3.4 GHz using Full HD resolution images. As a result, the proposed algorithm shows that machine learning based detection and recognition methods can efficiently be used for TSR algorithm even in poor driving environment.

• Journal of Digital Contents Society
• /
• v.18 no.1
• /
• pp.71-77
• /
• 2017

Virtual advertisement is an advertising technique that using computer graphic in a media production such as a sports image for inserting product image, logo, advertising slogan, etc. Recently, the image insertion of virtual advertisement is actively spreading due to the satisfaction of technical element for the image insertion of virtual advertisement in sports advertisement by increasing of the image processing technology and the computing performance. In addition, image processing technology for automatic insertion has become an important research field in the virtual advertisement field. In this paper, we propose the method of extracting less-informative region by using image processing technique and machine learning to insert a virtual advertisement automatically in sports image. The proposed method analyzes the brightness level of image through the histogram and extracts the less-informative region using the machine learning method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.227-233
• /
• 2019

Recently, along with the recent development of deep learning technique, neural networks are achieving success in computer vision filed. Convolutional neural network have shown outstanding performance in not only for a simple image classification task, but also for tasks with high difficulty such as object segmentation and detection. However many such deep learning models are based on supervised-learning, which requires more annotation labels than image-level label. Especially image semantic segmentation model requires pixel-level annotations for training, which is very. To solve these problems, this paper proposes a weakly-supervised semantic segmentation method which requires only image level label to train network. Existing weakly-supervised learning methods have limitations in detecting only specific area of object. In this paper, on the other hand, we use multi-classifier deep learning architecture so that our model recognizes more different parts of objects. The proposed method is evaluated using VOC 2012 validation dataset.

• Spatial Information Research
• /
• v.21 no.3
• /
• pp.31-43
• /
• 2013

Although the vector map data possesses much higher values than other types of multimedia, the data copyright and the protection against illegal duplication are still far away from the attention. This paper proposes a novel watermarking technique which is both robust to diverse attacks and optimized to a vector map structure. Six approaches are proposed for the design of the watermarking algorithm: point-based approach, building a minimum perimeter triangle, watermark embedding in the length ratio, referencing to the pixel position of the watermark image, grouping, and using the one-way function. Our method preserves the characteristics of watermarking such as embedding effectiveness, fidelity, and false positive rate, while maintaining robustness to all types of attack except a noise attack. Furthermore, our method is a blind scheme in which robustness is independent of the map data. Finally, our method provides a solution to the challenging issue of degraded robustness under severe simplification attacks.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.2
• /
• pp.235-240
• /
• 2015

Active Safety system is requested on the market of the medium and heavy duty commercial vehicle over 4.5ton beside the market of passenger car with advancement of the digital equipment proportionally. Unlike the passenger car, the mounting position of camera in case of the medium and heavy duty commercial vehicle is relatively high, it is disadvantaged conditions for lane recognition in contradiction to passenger car. In this work, we show the method of lane recognition through the Sobel edge, based on the spatial domain processing, Hough transform and color conversion correction. Also we suggest the low error method of front vehicles recognition in order to reduce the detection error through Haar-like, Adaboost, SVM and Template matching, etc., which are the object recognition methods by frontal camera vision. It is verified that the reliability over 98% on lane recognition is obtained through the vehicle test.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.71-77
• /
• 2014

In this paper, we propose an improved numeric character recognition method which can recognize numeric characters well under low-illuminated and shade-illuminated environment. The LN(Local Normalization) preprocessing method is used in order to enhance low-illuminated and shade-illuminated image quality. The reading area is detected using line segment information extracted from the illumination-normalized meter images, and then the three-phase procedures are performed for segmentation of numeric characters in the reading area. Finally, an efficient hybrid classifier is used to classify the segmented numeric characters. The proposed numeric character classifier is a combination of multi-layered feedforward neural network and template matching module. Robust heuristic rules are applied to classify the numeric characters. Experiments using meter image database were conducted. Meter image database was made using various kinds of meters under low-illuminated and shade-illuminated environment. The experimental results indicates the superiority of the proposed numeric character recognition method.

• The KIPS Transactions:PartB
• /
• v.14B no.6
• /
• pp.407-412
• /
• 2007

The performance of ultrasonic testing systems for industrial or medical purpose largely depends on the performance of ultrasonic transducers. Generally, the information about an ultrasonic transducer performance characteristics are expressed by the ultrasonic R/F signal back from a reflector and its frequency characteristics in the data sheet provided by manufacturers. In case of focused ultrasonic transducers, the two pieces of information can, however, hardly assure that the focused ultrasonic transducer would produce well-focused C-scan images. Therefore, we propose the measured size of focal spot and the reconstructed shape of effective focal zone in the focused sound field as novel measures for the performance evaluation of the focused ultrasonic transducers. The process of getting the both measures of the transducers is conducted by the implemented software including sound field scanning and virtual 3D reconstruction functions which requires the echo of a point reflector. The proposed method could, otherwise impossible in the existing method, effectively and simply distinguish superior ones among many transducers made in the same specification and be also used to detect the performance degradation due to the aging of the transducers. Eventually, the quality of performance of the ultrasonic testing systems for industrial or medical purpose is secured.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.8
• /
• pp.385-392
• /
• 2016

Market analysis for a business plain is required for the success in the modern world. Most important part in this analysis is pedestrian traffic counting. A traditional way for this is counting it in person. However, it causes high labor costs and mistakes. This paper proposes an automatic algorithm to measure the pedestrian traffic count using images with webcam. The proposed algorithm is composed of two parts: pedestrian area detection and movement tracking. In pedestrian area detection, moving blobs are extracted and pedestrian areas are detected using HoG features and Adaboost algorithm. In movement tracking, multi-level matching and false positive removal are applied to track pedestrian areas and count the pedestrian traffic. Multi-level matching is composed of 3 steps: (1) the similarity calculation between HoG area, (2) the similarity calculation of the estimated position with Kalman filtering, and (3) the similarity calculation of moving blobs in the pedestrian area detection. False positive removal is to remove invalid pedestrian area. To analyze the performance of the proposed algorithm, a comparison is performed with the previous human area detection and tracking algorithm. The proposed algorithm achieves 83.6% accuracy in the pedestrian traffic counting, which is better than the previous algorithm over 11%.

• The Journal of Engineering Geology
• /
• v.30 no.1
• /
• pp.17-30
• /
• 2020

An optical televiewer is a geophysical logging device that produces continuous high-resolution full-azimuth images of a borehole wall using a light-emitting-diode and a complementary metal-oxide semiconductor image sensor to provide valuable information on subsurface discontinuities. Recently, borehole imaging logging has been applied in many fields, including ground subsidence monitoring, rock mass integrity evaluation, stress-induced fracture detection, and glacial annual-layer measurements in polar regions. Widely used commercial borehole imaging logging systems typically have limitations depending on equipment specifications, meaning that it is necessary to clearly verify the scope of applications while maintaining appropriate quality control for various borehole conditions. However, it is difficult to directly check the accuracy, implementation, and reliability for outcomes, as images derived from an optical televiewer constitute in situ data. In this study, we designed and constructed a modular fractured borehole model having similar conditions to a borehole environment to report unprecedented results regarding reliable data acquisition and processing. We investigate sonde magnetometer accuracy, color realization, and fracture resolution, and suggest data processing methods to obtain accurate aperture measurements. The experiment involving the fractured borehole model should enhance not only measurement quality but also interpretations of high-resolution and reliable optical imaging logs.