• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -1
• /
• pp.281-284
• /
• 2002

Error resilience for image coding is an important component of multimedia communication system. Error resilience schemes address loss recovery from the compression perspective. Multiple description coding (MDC) is one of the error resilience techniques promising for robust video transmission. It is the way to achieve tradeoff description such as scalar quantization, correlating transform and the quantized frame expansion. In this paper, we consider Multiple Description Scalar Quantization (MDSQ) to wavelet domain. Conventional MDSQ schemes considered description with equal weights in each sub-bands. But, we can see that the each sub-bands is unequal contribution to whole image quality. Therefore, we experiment the multiple design MDSQ table to make probability of zero index high, which gives high efficiency in arithmetic symbol coder. We also compare our proposed method with the conventional methods and show improved performance in terms of redundancy-rate-distortion.

• 전기학회논문지
• /
• 제65권5호
• /
• pp.888-894
• /
• 2016

In this paper, we describe a method for precisely measuring the abrasion of the railway using an image processing technique. To calculate the wear of the rails, we provided a method for accurately matching the standard rail profile data and the profile data acquired by the rail inspection vehicle. After the lens distortion correction and the perspective transformation of the measured profile data, we used ICP Algorithm for accurate profile data matching with the reference profile extracted from the standard rail drawing. We constructed the prototype of the Rail Profile Measurement System for High-speed Railway and the experimental result on the three type of the standard rail used in Korea showed the excellent profile matching accuracy within 0.1mm.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2009년도 9th International Meeting on Information Display
• /
• pp.1546-1549
• /
• 2009

In recent studies on tone reproduction with the objective of reproducing natural looking colors in digital images, an integrated multi-scale retinex (IMSR) has produced great naturalness in the resulting images. Most methods, including IMSR, work in RGB or quasi-RGB color spaces. As such, this produces hue distortion from the perspective of the human visual system. Accordingly, this paper proposes the hue preserved multi-scale Retinex (HPMSR) method to obtain a high contrast and naturalness. The proposed method enhanced the $L^*$ and saturation values in CIELAB color space. As a result, the visibility in dark shadows in the resulting images was improved.

• Journal of Information Technology Applications and Management
• /
• 제25권2호
• /
• pp.41-52
• /
• 2018

This paper presents a method for accurate camera self-calibration based on SIFT Feature Detection and image quality assessment. We performed image quality assessment to select high quality images for the camera self-calibration process. We defined high quality images as those that contain little or no blur, and have maximum contrast among images captured within a short period. The image quality assessment includes blur detection and contrast assessment. Blur detection is based on the statistical analysis of energy and standard deviation of high frequency components of the images using Discrete Cosine Transform. Contrast assessment is based on contrast measurement and selection of the high contrast images among some images captured in a short period. Experimental results show little or no distortion in the perspective view of the images. Thus, the suggested method achieves camera self-calibration accuracy of approximately 93%.

• 스마트미디어저널
• /
• 제2권1호
• /
• pp.31-36
• /
• 2013

A robust and efficient text extraction is very important for an accuracy of Optical Character Recognition (OCR) systems. Natural scene images with degradations such as uneven illumination, perspective distortion, complex background and multi color text give many challenges to computer vision task, especially in text extraction. In this paper, we propose a method for extraction of the text in signboard images based on a combination of mean shift algorithm and weighting scheme of hue and saturation in HSI color space for clustering algorithm. The number of clusters is determined automatically by mean shift-based density estimation, in which local clusters are estimated by repeatedly searching for higher density points in feature vector space. Weighting scheme of hue and saturation is used for formulation a new distance measure in cylindrical coordinate for text extraction. The obtained experimental results through various natural scene images are presented to demonstrate the effectiveness of our approach.

• 반도체디스플레이기술학회지
• /
• 제19권4호
• /
• pp.112-115
• /
• 2020

Trump cards are used in variable games in households such as poker and blackjack. In many cases, it is able to be helpful to algorithmically identify the playing cards from camera views. In this paper, we provide an approach that detects and identifies the playing card using template matching scheme, and evaluate the results of the provided implementation. For ideal cases, the implemented system provides a 100% success rate for card identification correct. However, non-ideal case of perspective distortion is estimated with 70% success ratio. This work aims to evaluate the effectiveness of augmented reality user interface for an entertainment application like playing card games.

• 전자통신동향분석
• /
• 제37권5호
• /
• pp.22-32
• /
• 2022

Optical character recognition is a primary technology required in different fields, including digitizing archival documents, industrial automation, automatic driving, video analytics, medicine, and financial institution, among others. It was created in 1928 using pattern matching, but with the advent of artificial intelligence, it has since evolved into a high-performance character recognition technology. Recently, methods for detecting curved text and characters existing in a complicated background are being studied. Additionally, deep learning models are being developed in a way to recognize texts in various orientations and resolutions, perspective distortion, illumination reflection and partially occluded text, complex font characters, and special characters and artistic text among others. This report reviews the recent deep learning-based text detection and recognition methods and their various applications.

• 반도체디스플레이기술학회지
• /
• 제21권1호
• /
• pp.22-26
• /
• 2022

This paper proposes a new method for the recognition of road surface marks and numbers. The proposed method designates a region of interest on the road surface without first detecting a lane. The road surface markings are extracted by location and size using a connection component analysis. Distortion due to the perspective effect is minimized by normalizing the size of the road markings. The road surface marking of the connected component is recognized by matching it with the stored road marking templates. The proposed method is implemented using C language in Raspberry Pi 4 system with a camera module for a real-time image processing. The system was fixedly installed in a moving vehicle, and it recorded a video like a vehicle black box. Each frame of the recorded video was extracted, and then the proposed method was tested. The results show that the proposed method is successful for the recognition of road surface marks and numbers.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2008년도 추계학술대회 논문집
• /
• pp.1069-1077
• /
• 2008

레이저와 카메라를 이용한 레일 마모도 측정 시스템은 정확한 마모도 측정을 위하여 레일에 조사된 레이저의 영역을 왜곡 없이 획득하고 이를 레일 단면과 정밀하게 일치시키는 과정이 매우 중요하다. 그러나 기존의 레일 마모도 측정 시스템은 빗물 등의 레일 위에 이물질이 있을 경우와 온도와 같은 측정 환경에 민감하게 반응하는 레이저의 특성으로 인하여 오차가 발생할 수 있으며 특히 외부에서 유입되는 태양광, 등과 같이 레일에 조사된 레이저와 같은 파장을 가지는 빛의 간섭에 의하여 레일에 조사된 레이저 영역 추출에 한계를 가진다. 또한, 2차원 상의 좌표 값으로 표현되는 추출된 레이저 영역을 레일단면에 맵핑시키는 과정에서 발생하는 기하학적 왜곡과 변형으로 측정 정밀도에 대한 한계가 발생하는 문제점을 가지고 있다. 본 논문에서는 레일 마모도 측정을 위하여 카메라로부터 입력되는 1메가급 해상도의 영상을 초당 480 프레임의 속도로 실시간 처리할 수 있는 DSP와 FPGA가 탑재된 고성능 영상처리보드를 개발하고 이를 기반으로 각 프레임에 대한 2D 영상 데이터를 3차원 상의 데이터로 맵핑함으로써 정밀한 레일 마모도 측정 방법을 제안하고자 한다. 획득한 영상으로부터 레일에 조사된 레이저의 영역을 정확하게 추출하기 위하여 웨이브렛 기반의 영상 알고리즘을 적용하고 2차원 상의 좌표값으로 표현된 레이저 영역을 카메라 모델과 투시 변환을 이용하여 레일의 단면에 정확하게 위치시킴으로서 ${\pm}0.5mm$ 이하의 오차범위를 가지는 고정밀 레일 마모도 측정 시스템을 개발하였다.

• Current Optics and Photonics
• /
• 제1권2호
• /
• pp.157-162
• /
• 2017

In large liquid crystal displays, the image quality in an oblique viewing direction is a crucial issue. From this perspective, 8-domain polymer-stabilized vertical alignment (PS-VA) mode has been developed to suppress the color shift in oblique viewing directions, compared to that in 4-domain PS-VA mode. To realize the 8-domain PS-VA, the four domains in a pixel are each divided into two regions, such that applying different electric potentials result in different tilt angles in these two regions, while keeping four azimuthal directions in each domain. However, applying different voltages in a pixel causes drawbacks, such as requiring additional processes to construct a capacitor and a transistor, which will further reduce the aperture ratio. Here we propose a different approach to form the 8-domain, by controlling surface polar anchoring energy and the width of patterned electrodes in two regions of a pixel. As a result, the gamma-distortion index (GDI), measured at an azimuthal angle of $0^{\circ}$, is reduced by about 23% and 8%, compared to that of a conventional 4-domain at polar angles of $30^{\circ}$ and $60^{\circ}$ respectively.