• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• 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.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.5
• /
• 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
• /
• 2009.10a
• /
• 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
• /
• v.25 no.2
• /
• 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%.

• Smart Media Journal
• /
• v.2 no.1
• /
• 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.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.4
• /
• 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.

• Electronics and Telecommunications Trends
• /
• v.37 no.5
• /
• 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.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.1
• /
• 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.

• Proceedings of the KSR Conference
• /
• 2008.11b
• /
• pp.1069-1077
• /
• 2008

The railway abrasion measurement system have to satisfy two conditions to increase the measurement accuracy as follows. The laser region which is projected on the rail have to be extracted without the geometrical distortion. The mapping of the acquired laser region data on the rail profile have to be processed exactly. But, the conventional railway abrasion measurement system is deeply effected by the foreign substance( dust, rainwater, and so on ) on the railway or the sensitive response characteristic of the laser to the external measurement circumstance, and then the measurement errors arise from above factors. When the laser region is projected on the rail extracts from the acquired image, the interference of the light with the same frequency as the laser system occurs the serious problems. In the process of the mapping between the railway profile and the extracted laser region, the measurement accuracy is very highly effected by the geometrical distortion and the abnormal variation. In this Paper, we propose the novel method to increase the accuracy of the railway abrasion measurement dramatically. we designed and manufactured the high precision and fast image processing board with DSP Core and FPGA to measure the railway abrasion. The image processing board has the capability that the image of 1024X1280 from camera can be processed with the speed of 480 frame/sec. And, we apply the image processing algorithm base on the wavelet to extract the laser region is projected on the rail exactly. Finally, we developed high precision railway abrasion measurement system with the error range less than +/-0.5mm by which 2D image data is covered 3D data and mapped on the rail profile using the camera model and the perspective transform.

• Current Optics and Photonics
• /
• v.1 no.2
• /
• 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.