• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.111-114
• /
• 2008

본 논문에서는 고유영상 추출에 기반을 둔 동물표현의 수화인식 기법을 제안하였다. 여기서는 영상으로부터 구조적 특징을 효과적으로 추출하기 위하여 PCA를 이용한 방법을 제안한다. 이는 선형투영 및 차원의 감소에 따른 계산부하의 감소로 인식시간을 줄이기 위함이다. 제안된 기법을 10종류의 240*215 픽셀 동물표현의 수화(160개 : 1명*10종류*16동작)영상을 대상으로 City-block의 분류척도를 이용하여 실험한 결과 우수한 인식성능이 있음을 확인하였다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.3
• /
• pp.451-456
• /
• 2017

Semantic segmentation, which is the most basic and complicated problem in computer vision, classifies each pixel of an image into a specific object and performs a task of specifying a label. MRF and CRF, which have been studied in the past, have been studied as effective methods for improving the accuracy of pixel level labeling. In this paper, we propose a semantic partitioning method that combines CNN, a kind of deep running, which is in the spotlight recently, and CRF, a probabilistic model. For learning and performance verification, Pascal VOC 2012 image database was used and the test was performed using arbitrary images not used for learning. As a result of the study, we showed better partitioning performance than existing semantic partitioning algorithm.

• Journal of the Korea Computer Graphics Society
• /
• v.17 no.4
• /
• pp.11-21
• /
• 2011

This paper proposes a method for decomposing a Hangul glyph of outline fonts into its initial, medial and final components using statistical-structural information. In a font family, the positions of components are statistically consistent and the stroke relationships of a Hangul character reflect its structure. First, we create the component histograms that accumulate the shapes and positions of the same components. Second, we make pixel clusters from character image based on pixel direction probabilities and extract the candidate strokes using position, direction, size of clusters and adjacencies between clusters. Finally, we find the best structural match between candidate strokes and predefined character model by relaxation labeling. The proposed method in this paper can be used for a study on formative characteristics of Hangul font, and for a font classification/retrieval system.

• Journal of the Korea Society of Computer and Information
• /
• v.3 no.3
• /
• pp.17-22
• /
• 1998

As time goes on, that becomes an issue still more for truth from error of a seal in electronic settlement , or in important document in the field of image recognition. But on the other hand image treatment method of a seal have has the weakness until now. It makes indistinct distinction of part that light and darkness is changed sharply as the edge of things. So it has difficult that edge detection is extracted. In this paper, I investigated the pixel in a specific area by using enhanced smothing method and searched a value of frquent occurrence. The value of pixel is substituted and edge detection is extracted. After then it could be classified rightly according as viligence test is dynamically changed. I applied conventional of Yager's generated intersection operator among fuzzy logic operator in ART1 learning Algorithm. Application of suggested ART1 learning algorithm, it results in improved image recognition rate than a case of using the conventional ART1 algorithm

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.3
• /
• pp.29-35
• /
• 2012

In this paper, it is presented the method of image recovering which existing is only pixel processing, but suggesting method is concluding image clustering overlap degree after classfying around unit fixel to crowd pixel. Concluding overlap degree threshold value is after identifying pattern pixel and grasping geometry structure of sample pattern and deduction of deciding function. distinguishing feature space is above four dimension is reason of not visual observation of pattern structure. consideration of distribution structure is distance of center of crowd pixel, the number of each crowd pattern pixel and standard deviation. The over threshold value elimate the overlap image and the downward is recovered and established dynamic image. memory storage deduction of 20% and elevation of 15% performance is estimated in recovery of image.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.4C
• /
• pp.371-379
• /
• 2009

In this paper, we proposed new de-interlacing algorithm for video data using intensity gradient filter and median filter with texture detection in the image block. We first introduce the texture detection. According to texture detection, the current region is determined into smooth region or texture region. In case that the smooth region interpolated by median filter. In addition, in case of the texture region, we calculate missing pixel value using intensity gradient filter. Therefore, we analyze the local region feature using the texture detection and classify each missing pixel into two categories. And then, based on the classification result, a different de-interlacing algorithm is activated in order to obtain the best performance. Experimental results show that the proposed algorithm performs well with a variety of moving sequences compared with conventional intra-field method in the literature.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.4
• /
• pp.211-216
• /
• 2017

This paper proposes image processing techniques that improve usability and performance in a diagnostic system of the contrast-enhanced ultrasonography. For a methodology for visualizing diagnostic parameter data in an ultrasonic medical image, an expression of transition time data with successive pixel values and a method of generating a lesion diagnostic parameter image with four categorized values are presented. We also introduce a MRF-based image enhancement technique to eliminate noises from generated parametric images. Such parametric image generation technique can overcome the difficulty of discriminating dynamic change in patterns in the ultrasonography. The technique clarifies the contour of the region in the original image and facilitates visual determination of the characteristics of the lesion through four colors. With regard to this MRF-based image enhancement, we define the energy function of consecutive pixel values and develop a technique to optimize it, and the usability of the proposed theory is examined through experiments with medical images.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.2
• /
• pp.47-52
• /
• 2016

The used digital images in the smart device and small displayer has been a downscaled image. In this paper, the detection of the downscaling image forgery is proposed using the feature vector according to the pixel value's gradients. In the proposed algorithm, AR (Autoregressive) coefficients are computed from pixel value's gradients of the image. These coefficients as the feature vectors are used in the learning of a SVM (Support Vector Machine) classification for the downscaling image forgery detector. On the performance of the proposed algorithm, it is excellent at the downscaling 90% image forgery compare to MFR (Median Filter Residual) scheme that had the same 10-Dim. feature vectors and 686-Dim. SPAM (Subtractive Pixel Adjacency Matrix) scheme. In averaging filtering ($3{\times}3$) and median filtering ($3{\times}3$) images, it has a higher detection ratio. Especially, the measured performances of all items in averaging and median filtering ($3{\times}3$), AUC (Area Under Curve) by the sensitivity and 1-specificity is approached to 1. Thus, it is confirmed that the grade evaluation of the proposed algorithm is 'Excellent (A)'.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1919-1925
• /
• 2022

In this paper, we propose an image-to-image translation approach based on the conditional generative adversarial network for semantic segmentation. Semantic segmentation is the task of clustering parts of an image together which belong to the same object class. Unlike the traditional pixel-wise classification approach, the proposed method parses an input RGB image to its corresponding semantic segmentation mask using a pixel regression approach. The proposed method is based on the Pix2Pix image synthesis method. We employ residual connections-based convolutional neural network architectures for both the generator and discriminator architectures, as the residual connections speed up the training process and generate more accurate results. The proposed method has been trained and tested on the NYU-depthV2 dataset and could achieve a good mIOU value (49.5%). We also compare the proposed approach to the current methods in semantic segmentation showing that the proposed method outperforms most of those methods.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_2
• /
• pp.1107-1115
• /
• 2019

Satellite data play a major role in supporting knowledge about forest fire by delivering rapid information to map areas damaged. This study, we used 7 Sentinel-2A images to detect change area in forests of Sokcho on April 4, 2019. The process of classify forest fire severity used 7 levels from Sentinel-2A dNBR(differenced Normalized Burn Ratio). In the process of classifying forest fire damage areas, the study selected three areas with high regrowth of vegetation level and conducted a detailed spatial analysis of the areas concerned. The results of dNBR analysis, regrowth of coniferous forest was greater than broad-leaf forest, but NDVI showed the lowest level of vegetation. This is the error of dNBR classification of dNBR. The results of dNBR time series, an area of forest fire damage decreased to a large extent between April 20th and May 3rd. This is an example of the regrowth by developing rare-plants and recovering broad-leaf plants vegetation. The results showed that change area was detected through the change detection of danage area by forest category and the classification errors of the coniferous forest were reached through the comparison of NDVI and dNBR. Therefore, the need to improve the precision Korean forest fire damage rating table accompanied by field investigations was suggested during the image classification process through dNBR.