• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.1
• /
• pp.104-115
• /
• 2001

A new content-based color image retrieval method integrating the features of the color adjacency and the gradient is proposed in this paper. As the most used feature of color image, color histogram has its own advantages that it is invariant to the changes in viewpoint and the rotation of the image etc., and the computation of the feature is simple and fast. However, it is difficult to distinguish those different images having similar color distributions using histogram-based image retrieval, because the color histogram is generated on uniformly quantized colors and the histogram itself contains no spatial information. And another shortcoming of the histogram-based image retrieval is the storage of the features is usually very large. In order to prevent the above drawbacks, the gradient that is the largest color difference of neighboring pixels is calculated in the proposed method instead of the uniform quantization which is commonly used at most histogram-based methods. And the color adjacency information which indicates major color composition feature of an image is extracted and represented as a binary form to reduce the amount of feature storage. The two features are integrated to allow the retrieval more robust to the changes of various external conditions.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.5 s.305
• /
• pp.137-144
• /
• 2005

In this paper, the extraction method of the edge histogram directly using wavelet coefficients in the wavelet domain for JPEG2000 images is proposed. MPEG-7 Edge Histogram Descriptor(EHD) extracts edge histogram in the spacial domain. This algorithm has much multiplication and addition for the edge extraction because it needs the decoding processing. However because the proposed algorithm extracts the edge histogram in the wavelet domain, it doesn't need the decoding processing and it decreases multiplication and addition. The Discrete Wavelet Transform(DWT) is a standard transform in JPEG2000. The proposed algorithm uses Le Gall 5/3 filter in JPEG2000 and odd coefficients in LH2 and HL2 sub-band. The edge direction can be decided to use rate of HL2 and LH2 odd coefficients. According to experiments, there is no difference of the efficiency between EHD and the proposed algorithm And the proposed algorithm is much better than EHD for multiplication and addition in the edge extraction of images.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.2
• /
• pp.71-78
• /
• 2021

In order to classify a target image in a cluster of images, the difference in brightness between the object and the background is mainly concerned, which is not easy to classify if the shape of the object is blurred and the sharpness is low. However, there are a few studies attempted to solve these problems, and there is still the problem of not properly distinguishing between wrong pattern and right pattern images when applied to actual data analysis. In this paper, we propose an algorithm that classifies 3D films into sharp and blurry using the width of the pixel values histogram. This algorithm determines the width of the right and wrong images based on the width of the pixel distributions. The larger the width histogram, the sharp the image, while the shorter the width histogram the blurry the image. Experiments show that the proposed algorithm reflects that the characteristics of these histograms allows classification of all wrong images and right images. To determine the reliability and validity of the proposed algorithm, we compare the results with the other obtained from preprocessed 3D films. We then trained the 3D films using few-shot learning algorithm for accurate classification. The experiments verify that the proposed algorithm can perform higher without complicated computations.

• The Journal of Korean Society for Radiation Therapy
• /
• v.22 no.2
• /
• pp.85-95
• /
• 2010

Purpose: The degradation of an image quality and error of the beam dose calculation can be caused because the metal artifact is generated during the CT simulation of head and neck patient. The usability of the gantry tilt scan for reducing the metal artifact tries to be appraised. Materials and Methods: The inferior $20^{\circ}$ gantry tilt scan was made in order to reduce the metal artifact and $0^{\circ}$ reconstruction image was acquired. The AAPM CT performance Phantom was used in order to compare the CT number of the reconstructed image and Original image. the difference of volume was compared by using the acrylic phantom. The homogeneity of the CT number was evaluated the Intensity volume Histogram (IVH) as in order to evaluate an influence by the metal artifact. A dose was evaluated as the Dose Volume Histogram (DVH). Results: in the comparison of the CT number and volume, the difference showed up less than 0.5%. As to the comparison of IVH, in the gantry tilt scan, influence by an artifact was reduced and the homogeneity of the CT number was improved. The comparison of DVH result reduced the mean dose error of the both sides parotid 0.2~6%. Conclusion: In the Head & Neck radiation therapy, It is difficult and to distinguish tumor and normal tissue and the error of dose is generated by the metal artifact. The delineation of the exact organization was possible if the Gantry tilt scan was used. The CT number homogeneity was improved and the error of dose could be reduced. The Gantry tilt scan confirmed in the Head & Neck radiation therapy to be very useful in the exact radiation therapy.

• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.1049-1052
• /
• 2000

In this paper, an efficient method to find cut in the MPEG stream data is proposed. For this purpose, histogram difference and pixel difference is considered as a noise signal. The signal is then filtered out by a median filter to make the frame difference larger. The frame difference obtained in this way is classified into cut frame and non-cut frame by the 2-means clustering without using any threshold value. To improve the classification ratio, a back-propagation neural network is constructed, where outputs of 2-means clustering are used as the inputs of the network. The simulation results demonstrate the performance of the proposed methods.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.4
• /
• pp.250-257
• /
• 2011

In this paper, we proposed the method detecting multiple pedestrians using motion information and SVM(Support Vector Machine) from a moving camera image. First, we detect moving pedestrians from both the difference image and the projection histogram which is compensated for the camera ego-motion using corresponding feature sets. The difference image is simple method but it is not detected motionless pedestrians. Thus, to fix up this problem, we detect motionless pedestrians using SVM The SVM works well particularly in binary classification problem such as pedestrian detection. However, it is not detected in case that the pedestrians are adjacent or they move arms and legs excessively in the image. Therefore, in this paper, we proposed the method detecting motionless and adjacent pedestrians as well as people who take excessive action in the image using motion information and SVM The experimental results on our various test video sequences demonstrated the high efficiency of our approach as it had shown an average detection ratio of 94% and False Positive of 2.8%.

• The KIPS Transactions:PartD
• /
• v.10D no.7
• /
• pp.1171-1176
• /
• 2003

In this paper, we propose an effective bar code detection algorithm using the feature analysis and the labeling. After computing the direction of pixels using four line operators, we obtain the histogram about the direction of pixels by a block unit. We calculate the difference between the maximum value and the minimum value of the histogram and consider the block that have the largest difference value as the block of the bar code region. We get the line passing by the bar code region with the selected block but detect blocks of interest to get the more accurate line. The largest difference value is used to decide the threshold value to obtain the binary image. After obtaining a binary image, we do the labeling about the binary image. Therefore, we find blocks of interest in the bar code region. We calculate the gradient and the center of the bar code with blocks of interest, and then get the line passing by the bar code and detect the bar code. As we obtain the gray level of the line passing by the bar code, we grasp the information of the bar code.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.9B
• /
• pp.1742-1754
• /
• 1999

In this paper, we propose a rate control scheme, using histogram based rate-distortion (R-D) estimation, which produces a consistent picture quality between consecutive frames. The histogram based R-D estimation used in our rate control scheme offers a closed-form mathematical model that enable us to predict the bits and the distortion generated from an encoded frame at a given quantization parameter (QP) and vice versa. The most attractive feature of the R-D estimation is low complexity of computing the R-D data because its major operation is just to obtain a histogram or weighted histogram of DCT coefficients from an input picture. Furthermore, it is accurate enough to be applied to the practical video coding. Therefore, the proposed rate control scheme using this R-D estimation model is appropriate for the applications requiring low delay and low complexity, and controls the output bit-rate ad quality accurately. Our rate control scheme ensures that the video buffer do not underflow and overflow by satisfying the buffer constraint and, additionally, prevents quality difference between consecutive frames from exceeding certain level by adopting the distortion constraint. In addition, a consistent considering the maximum tolerance BER of the voice service. Also in Rician fading channel of K=6 and K=10, considering CLP=$10^{-3}$ as a criterion, it is observed that the performance improment of about 3.5 dB and 1.5 dB is obtained, respectively, in terms of $E_b$/$N_o$ by employing the concatenated FEC code with pilot symbols.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.149-150
• /
• 2012

This paper presents a shot boundary detection method based on the global decision tree that allows for extraction of boundaries of high variations occurring due to camera breaks from frame difference values. For a start, difference values between frames are calculated through local X2-histogram and normalization. Next, the distances between difference values are calculated through normalization.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.10
• /
• pp.2552-2562
• /
• 1996

In this paper, we propose a segmentation algorithm that can reliably separate moving objects from noisy background in the image sequance received from a camera at the fixed position. The proposed algorithm consists of three processes:generation of the difference image between the input image and the reference image, multilevel quantization of the difference image, and multistagemerging in the quantized image. The quantization process requantizes the difference image based on the multiple threshold values determined bythe histogram analysis. The merging starts from the seed region which created by using the highest threshold value and ends when termination conditions are met. the proposed method has been tested with various real imge sequances containing intruders. The test results show that the proposed algorithm can detect moving objects like intruders very effectively in the noisy environment.