• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.669-672
• /
• 1998

In this paper, w epropose a fast fractal coding method based on correlation coefficients of subblocks in input image. In the proposed method, domain pool is selected based on correlation analysis of input image and the isometry transform for each block is chosen based on the IFS method. To investigate the performance of the proposed method, we compared image quality and encoding time with full search PIFS method and jacquin's PIFS method. Experimental results show that proposed method yields nearly the same performance in PSNR, and its encoding time is reduced for images size of 512*512 compared with full search PIFS method and jacquin's PIFS method.

• Journal of KIISE:Software and Applications
• /
• v.34 no.9
• /
• pp.797-803
• /
• 2007

Adaptive binarization is very important for the camera-based document recognition. This paper proposes a binarization method which can effectively adapt to the variation of image Qualify. Firstly, it analyzes the effect of binarization parameters to the result and proposes a method to measure the image quality. Then, it statistically analyzes the relationship between the image quality and the binarization parameter. Finally, it proposes a binarization method that automatically adapts to the quality of the input image, using the analysis result. The experiment results show that there is a meaningful relationship between the image quality and the binarization parameter, and therefore, the proposed method can effectively adapt to the variation of image quality.

• Archives of design research
• /
• v.16 no.2
• /
• pp.375-384
• /
• 2003

This study is on the strategy for establishing successful corporate brand image, by understanding the need for increasing brand value based on the level of brand recognition. In order to carry this out, the PICS (Product Image Concentration System) is suggested, which includes Brand Image Analysis on a high-level, Product Image Programming based on the result of the image analysis, and Product Image Coherency Assessment and Management, resulting in setting up a guideline for gaining competitive advantage and brand management. Brand Image Analysis is a method that utilizes image association to understand brand disposition by analyzing the association pattern among available visual materials to measure the corporate and brand image inclinations. As the next step, Product Image Programming establishes design philosophy and principles based on the analysis of brand image, and the Visual Programming is a process for visualizing the intended product image direction. Lastly, Product Image Coherency Assessment examines whether to incorporate design philosophy and principles or not to arrive at an agreed evaluation criteria for developing designs coherent with the brand image. The PICS (Product Image Concentration System) is a practical method for increasing a company' competitive advantage and managing brand. The expectation on this system is to provide a guideline for applying brand image in design process more objectively. For further study, diversification of image spectrum based on expressive keywords and comparative analysis on images as well as a product image interpretation program to understand the order of visual materials will be necessary.

• Journal of Korea Foundry Society
• /
• v.21 no.3
• /
• pp.198-203
• /
• 2001

In determining properties of ductile cast iron, it is well known that nodularity plays a significant role. Therefore, the national and/or international standards for ductile cast iron such as KS, ISO, ASTM and JIS have specified some methods for evaluating it. However, most of standards have not recommended the methods using image analyzer which is known as an objective analyzing tool for evaluating microstructure. In this study, a reliable method for evaluating nodularity by image analyzing method was proposed, and the result was compared with that from the common counting method proposed in KS D 4302-1999. It was found that there was a reasonable relationship in nodularities measured by these two methods.

• Journal of electromagnetic engineering and science
• /
• v.3 no.1
• /
• pp.72-76
• /
• 2003

For the purpose of numerically efficient analysis for electrostatic problems, an improved equivalent image method, by which infinite exact image of a point charge in parallel-plate and rectangular conducting structures can be replaced by only a few equivalent images, is considered. Through this study, it is observed that the error is of the order of 0.001 % when the present method is used to evaluate electric potential for a point charge in parallel-plate and rectangular conducting planes.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2821-2823
• /
• 2005

When we deal with the image data through camera lens, much works are necessary for removing image distortions and obtaining accurate informations from the raw data. However, the calibration process is very complicated and requires many trials and errors. In this paper, 3 new approach to image processing is presented by developing a H/W vision system with a tracking camera. Using motor control with encoders the proposed tracking method tells us exact displacements of a moving object. Therefore this method does not require any calibration process for pin cusion. Owing to the mobility one camera covers wide ranges and, by lowering its height, the camera also obtains high resolution of the image. We first introduce the structure of the motion analysis system. Then the construced vision system is investigated by some experiments.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.8
• /
• pp.754-759
• /
• 2007

In this paper, we proposed the Bi-Modal Sensor Fusion Algorithm which is the emotional recognition method that be able to classify 4 emotions (Happy, Sad, Angry, Surprise) by using facial image and speech signal together. We extract the feature vectors from speech signal using acoustic feature without language feature and classify emotional pattern using Neural-Network. We also make the feature selection of mouth, eyes and eyebrows from facial image. and extracted feature vectors that apply to Principal Component Analysis(PCA) remakes low dimension feature vector. So we proposed method to fused into result value of emotion recognition by using facial image and speech.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.10
• /
• pp.1349-1355
• /
• 1999

A power distribution facility map is drawn on cadastral map. Besides, grid lines are added on the map for sectionalization. For automatic recognition of the map, we first extract recognizing regions. In this paper, we propose an extraction method of recognizing regions by partially extending thinned image. The proposed method is consist of three phases, binarization phase, thinning phase and partial extending phase. The first phase generate a binary image using threshold value which is obtained by histogram analysis. The binary image contains many part of recognizing regions, but not all. The second phase generate thinned image which is generated by appling thinning operator to the binary image. And the third phase extends thinned image from terminal point until satisfying termination condition. The proposed method is tested on several power distribution facility maps, and the results are presented.

• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.835-838
• /
• 2000

Popular methods for extracting a text region in video images are in general based on analysis of a whole image such as merge and split method, and comparison of two frames. Thus, they take long computing time due to the use of a whole image. Therefore, this paper suggests the faster method of extracting a text region without processing a whole image. The proposed method uses line sampling methods, FFT and neural networks in order to extract texts in real time. In general, text areas are found in the higher frequency domain, thus, can be characterized using FFT The candidate text areas can be thus found by applying the higher frequency characteristics to neural network. Therefore, the final text area is extracted by verifying the candidate areas. Experimental results show a perfect candidate extraction rate and about 92% text extraction rate. The strength of the proposed algorithm is its simplicity, real-time processing by not processing the entire image, and fast skipping of the images that do not contain a text.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.724-726
• /
• 2003

Currently available image fusion methods are not efficient for fusing the Landsat 7 images. Significant color distortion is one of the major problems. In this paper, using the well-known wavelet based method for data fusion between high-resolution panchromatic and low-resolution multispectral satellite images, we performed Landsat 7 image fusion. Based on the experimental results obtained from this study, we analyzed some reasons for color distortion. A new approach using the biorthogonal wavelets based method for data fusion is presented. This new method has reached an optimum fusion result - with the same spectral resolution as the multispectral image and the same spatial resolution as the panchromatic image with minimum artifacts.