• Journal of Digital Contents Society
• /
• v.10 no.4
• /
• pp.597-604
• /
• 2009

For the improvement of license plate recognition system, correct extraction of a license plate region as well as character recognition is important. In this paper, with the analysis and classification of the error patterns in the process of plate region extraction, we tried to improve the extraction of the region using HoG(histogram of gradient) features and Adaboost. The results show that the HoG feature is robust to the noise and various types of the plates, and also is very effective to extract the region failed before.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.7
• /
• pp.1064-1073
• /
• 2015

In this study, we introduce the pedestrian detection system by using the feature of HOG-PCA and RBFNNs pattern classifier. HOG(Histogram of Oriented Gradient) feature is extracted from input image to identify and recognize a object. And a dimension is reduced for improving performance as well as processing speed by using PCA which is a typical dimensional reduction algorithm. So, the feature of HOG-PCA through the dimensional reduction by using PCA leads to the improvement of the detection rate. FCM clustering algorithm is used instead of gaussian function to apply the characteristic of input data as well and connection weight is used by polynomial expression such as constant, linear, quadratic and modified quadratic. Finally, INRIA person database known as one of the benchmark dataset used for pedestrian detection is applied for the performance evaluation of the proposed classifier. The experimental result of the proposed classifier are compared with those studied by Dalal.

• Journal of Information Processing Systems
• /
• v.10 no.3
• /
• pp.443-458
• /
• 2014

An extreme learning machine (ELM) is a recently proposed learning algorithm for a single-layer feed forward neural network. In this paper we studied the ensemble of ELM by using a bagging algorithm for facial expression recognition (FER). Facial expression analysis is widely used in the behavior interpretation of emotions, for cognitive science, and social interactions. This paper presents a method for FER based on the histogram of orientation gradient (HOG) features using an ELM ensemble. First, the HOG features were extracted from the face image by dividing it into a number of small cells. A bagging algorithm was then used to construct many different bags of training data and each of them was trained by using separate ELMs. To recognize the expression of the input face image, HOG features were fed to each trained ELM and the results were combined by using a majority voting scheme. The ELM ensemble using bagging improves the generalized capability of the network significantly. The two available datasets (JAFFE and CK+) of facial expressions were used to evaluate the performance of the proposed classification system. Even the performance of individual ELM was smaller and the ELM ensemble using a bagging algorithm improved the recognition performance significantly.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.9
• /
• pp.31-37
• /
• 2015

Symmetry is easily found in animals and plants as well as in artificial structures. It is useful not only for human cognitive process but also for image understanding by computer. Application areas include face detection and recognition, indexing of image database, image segmentation and detection, and analysis of medical images. The method used in this paper extracts edges, and the perpendicular bisector of any pair of selected edge points is considered to be a candidate axis of symmetry. The coefficients of the perpendicular bisectors are accumulated in the coefficient space. Axis of symmetry is determined to be the line for which the histogram has maximum value. This method shows good results, but the usefulness of the method is restricted because the amount of computation increases proportional to the square of the number of edges. In this paper, an acceleration method is proposed which performs $2^{2n}$ times faster than the original one. Experiment on 20 test images shows that the proposed method using level-3 image segmentation performs 63.9 times faster than the original method.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.3
• /
• pp.41-47
• /
• 2019

In this paper, we propose a application of conditional generative adversarial network (cGAN) for generation of contrast enhanced computed tomography (CT) image. Two types of CT data which were the enhanced and non-enhanced were used and applied by the histogram equalization for adjusting image intensities. In order to validate the generation of contrast enhanced CT data, the structural similarity index measurement (SSIM) was performed. Prepared generated contrast CT data were analyzed the statistical analysis using paired sample t-test. In order to apply the optimized algorithm for the lymph node cancer, they were calculated by short to long axis ratio (S/L) method. In the case of the model trained with CT data and their histogram equalized SSIM were $0.905{\pm}0.048$ and $0.908{\pm}0.047$. The tumor S/L of generated contrast enhanced CT data were validated similar to the ground truth when they were compared to scanned contrast enhanced CT data. It is expected that advantages of Generated contrast enhanced CT data based on deep learning are a cost-effective and less radiation exposure as well as further anatomical information with non-enhanced CT data.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.72-74
• /
• 2021

Recently, the spread of deep learning environments has increased the importance of dataset generation. Therefore, data is being augmented using GAN for efficient data set generation. However, several problems have been found in data generated using GAN, such as problems that occur in the early stages of learning and pixel breakage occurring in the generated image. In this paper, we intend to implement an image data selection algorithm to solve various problems arising from the existing GAN. The broken image screening algorithm was implemented to analyze the histogram distribution in the image and determine whether to store the generated image according to whether the result value satisfies the specified threshold value.

• Journal of Internet Computing and Services
• /
• v.9 no.5
• /
• pp.117-130
• /
• 2008

This paper proposes a stable and robust method to distinct the color similarity for clothes using the LBG algorithm under various light sources, Since the conventional methods, such as the histogram intersection and the accumulated histogram, are profoundly sensitive to the changing of light environments, the distinction of color similarity for the same cloth can be different due to the complicated light sources. To reduce the effects of the light sources, the properties of hue and saturation which consistently sustain the characteristic of the color under the various changes of light sources are analyzed to define the characteristic of the color distribution. In a two-dimensional space determined by the properties of hue and saturation, the LBG algorithm, a non-parametric clustering approach, is applied to examine the color distribution of images for each clothes. The color similarity of images is defined by the average of Euclidean distance between the mapping clusters which are calculated from the result of clustering of both images. To prove the stability of the proposed method, the results of the color similarity between our method and the traditional histogram analysis based methods are compared using a dozen of cloth examples that obtained under different light environments. Our method successively provides the classification between the same cloth image pair and the different cloth image pair and this classification of color similarity for clothe images obtains the 91.6% of success rate.

• Korean Journal of Remote Sensing
• /
• v.23 no.2
• /
• pp.113-117
• /
• 2007

In this paper, we propose a new method for determining automatically the size of the matching window using histogram of the gradient in order to improve the performance of stereo matching using one-meter resolution satellite imagery. For each pixel, we generate Flatness Index Image by calculating the mean value of the vertical or horizontal intensity gradients of the 4-neighbors of every pixel in the entire image. The edge pixel has high flatness index value, while the non-edge pixel has low flatness index value. By using the histogram of the Flatness Index Image, we find a flatness threshold value to determine whether a pixel is edge pixel or non-edge pixel. If a pixel has higher flatness index value than the flatness threshold value, we classify the pixel into edge pixel, otherwise we classify the pixel into non-edge pixel. If the ratio of the number of non-edge pixels in initial matching window is low, then we consider the pixel to be in homogeneous region and enlarge the size of the matching window We repeat this process until the size of matching window reaches to a maximum size. In the experiment, we used IKONOS satellite stereo imagery and obtained more improved matching results than the matching method using fixed matching window size.

• Journal of Korea Multimedia Society
• /
• v.12 no.2
• /
• pp.191-199
• /
• 2009

In this paper, the improved edge extract methods is proposed in order to extract edge. For the correct and fast detect, the binary image using the threshold value is applied for a experiment. For the experimental analysis, we compare the existing edge methods with the improved methods. Hereby, the exist methods are the sobel, robert, and prewitt. and the improved methods use the existing methods which is applied mask variations. The merits of the improved mothods have a result of a little erosion, a apparent edge. Specially, we use the grey image of medical image for the experimental analysis and then apply threshold value for a result image. After that, we acquire a apparent edge. For a quantitative analysis of the each methods, the each images was applied a histogram. As a result, we prove the merit of the improved methods using a analytical graph of the medical images.

• Journal of Korea Multimedia Society
• /
• v.16 no.9
• /
• pp.1044-1056
• /
• 2013

This paper presents an approach for detecting and measuring human skin pigmentation. In the proposed scheme, we extract a skin area by a GMM-EM clustering based skin color model that is estimated from the statistical analysis of training images and remove tiny noises through the morphology processing. A skin area is decomposed into two components of hemoglobin and melanin by an independent component analysis (ICA) algorithm. Then, we calculate the intensities of hemoglobin and melanin by using the projection transformed block coefficient and determine the existence of skin pigmentation according to the global and local distribution of two intensities. Furthermore, we measure the area and density of the detected skin pigmentation. Experimental results verified that our scheme can both detect the skin pigmentation and measure the quantity of that and also our scheme takes less time because of the location histogram.