• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.2
• /
• pp.398-405
• /
• 2006

We propose a pattern classification model using a selective perception ability of human beings. Generally, human beings recognize an object by putting a selective concentration on it in the region of interest. Much better classification and recognition could be possible by adapting this phenomenon in pattern classification. First, the pattern classification model creates some reference cluster patterns in a usual way. Then it generates an SPM(Selective Perception Map) that reflects the mutual relation of the reference cluster patterns. In the recognition phase, the model applies the SPM as a weight for calculating the distance between an input pattern and the reference patterns. Our experiments show that the proposed classifier with the SPM acquired the better results than other approaches in pattern classification.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2007.11a
• /
• pp.520-529
• /
• 2007

간암은 세계적으로 흔한 악성 종양에 속하지만 우리나라에서 간암은 위암, 폐암 다음으로 높은 사망률을 보이며 이러한 간암은 조기진단이 요구된다. 전문의는 간암의 진단을 위해 조영증강 CT영상을 이용하여 육안으로 간암을 판별하는데, 조영증강 CT영상을 이용한 진단은 주 종양의 진단에는 도움이 되지만 주 종양에서 주위 간 조직으로 전이된 간암들을 판별하는 것은 어려우며 실제로 시술 중에야 전이된 간암의 존재를 알 수 있다. 본 논문에서는 조영증강 CT영상을 이용하여 간과 주 종양을 자동으로 추출한 후, 미세하게 주 종양 주위로 전위된 간암들을 추출하는 방법을 제안하여 전문의를 보조할 수 있는 보조 전문가 시스템으로서의 유용성을 확인하고자한다. 조영증강 CT영상은 흉부에서 5mm간격으로 40 ${\sim}$ 50장정도로 촬영된다. 조영증강 CT영상을 이용하여 간 영역을 추출하기 위해서 간의 형태학적 정보 그리고 명암도와 명암의 분포도를 이용한 양자화 기법 등을 적용하여 추출하며 추출된 간 영역에서 간암의 후보 영역 추출은 간암의 명암도와 형태학적 특징 정보를 이용하여 추출한다. 본 논문에서는 간암의 추출을 위해 맵 상에 흩어져 분포되어 있는 유사 패턴들의 무게 중심을 찾아 하나의 패턴으로 그룹화 하는 개선된 SOM 알고리즘을 제안하여 간암 판별에 적용한 후, 기존의 SOM 알고리즘과 비교 분석한 결과. 본 논문에서 제안된 SOM 알고리즘을 적용한 간암 추출이 더 효율적임을 확인 할 수 있었으며, 전문의가 판별한 것과 비교 분석한 결과, 전문의를 보조할 수 있는 보조 전문가 시스템으로서의 가능성을 확인할 수 있었다.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.12
• /
• pp.849-854
• /
• 2013

In this paper, a system technology-based algorithms and visualization is proposed to show a space data. Also the proposed system provides analysis function with combination of usual map and automatic document generation function to give a useful information for making an important decision based on spatial distributed data. In the proposed method, we employ the heat map analysis to present a suitable color distribution for 2 dimensional map data. The buffering analysis method is also used to define the spatial data access. By using the proposed system, spatial information in a variety of distribution will be easy to identify. Also, if we make a use of automatic document generation function in the proposed algorithm, a lot of time and cost savings are expected to make electronic document which representation of spatial information is required.

• The Journal of the Korea Contents Association
• /
• v.7 no.11
• /
• pp.248-257
• /
• 2007

With the advance of information technology, e-learning is widely used. However, due to the lack of human computer interaction, e-mentoring or blended learning are adopted to complement the drawbacks of e-learning these days. One of the common purposes for adopting these tools is to enhance the interaction level by using bbs or blogs based on e-communities. If the cooperative learning contents management tools that share learners' knowledge in e-learning are provided, interactivity and educational effects can be enhanced. In this paper, a tree-based learning contents construction tool and a community-based cooperative learning contents construction tools that can share the learners' knowledge are proposed. Also, we analyze the influencing factors to the learners by using the proposed tools.

• Journal of Broadcast Engineering
• /
• v.26 no.5
• /
• pp.608-620
• /
• 2021

Recent deep learning-based face super-resolution (FSR) works showed significant performances by utilizing facial prior knowledge such as facial landmark and dictionary that reflects structural or semantic characteristics of the human face. However, most of these methods require additional processing time and memory. To solve this issue, this paper propose an efficient FSR models using knowledge distillation techniques. The intermediate features of teacher network which contains dictionary information based on major face regions are transferred to the student through adversarial multi-scale features distillation. Experimental results show that the proposed model is superior to other SR methods, and its effectiveness compare to teacher model.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.819-834
• /
• 2022

Artificial Intelligence (AI) techniques have been effectively used for image classification, object detection, and image segmentation. Along with the recent advancement of computing power, deep learning models can build deeper and thicker networks and achieve better performance by creating more appropriate feature maps based on effective activation functions and optimizer algorithms. This review paper examined technical and academic trends of Convolutional Neural Network (CNN) and Transformer models that are emerging techniques in remote sensing and suggested their utilization strategies and development directions. A timely supply of satellite images and real-time processing for deep learning to cope with disaster monitoring will be required for future work. In addition, a big data platform dedicated to satellite images should be developed and integrated with drone and Closed-circuit Television (CCTV) images.

• Journal of Digital Contents Society
• /
• v.18 no.8
• /
• pp.1635-1640
• /
• 2017

In this paper, a hierarchical image tree model for weather classification is defined in a single outdoor image, and a weather classification algorithm using image intensity and k-mean segmentation image is proposed. In the first level of the hierarchical image tree model, the indoor and outdoor images are distinguished. Whether the outdoor image is daytime, night, or sunrise/sunset image is judged using the intensity and the k-means segmentation image at the second level. In the last level, if it is classified as daytime image at the second level, it is finally estimated whether it is sunny or foggy image based on edge map and fog rate. Some experiments are conducted so as to verify the weather classification, and as a result, the proposed method shows that weather features are effectively detected in a given image.

• Journal of Intelligence and Information Systems
• /
• v.15 no.2
• /
• pp.49-59
• /
• 2009

Contents-based image retrieval methods are in general more objective and effective than text-based image retrieval algorithms since they use color and texture in search and avoid annotating all images for search. SIM(Self-organizing Image browsing Map) is one of contents-based image retrieval algorithms that uses only browsable mapping results obtained by SOM(Self Organizing Map). However, SOM may have an error in selecting the right BMU in learning phase if there are similar nodes with distorted color information due to the intensity of light or objects' movements in the image. Such images may be mapped into other grouping nodes thus the search rate could be decreased by this effect. In this paper, we propose an improved SIM that uses HSV color model in extracting image features with color quantization. In order to avoid unexpected learning error mentioned above, our SOM consists of two layers. In learning phase, SOM layer 1 has the color feature vectors as input. After learning SOM Layer 1, the connection weights of this layer become the input of SOM Layer 2 and re-learning occurs. With this multi-layered SOM learning, we can avoid mapping errors among similar nodes of different color information. In search, we put the query image vector into SOM layer 2 and select nodes of SOM layer 1 that connects with chosen BMU of SOM layer 2. In experiment, we verified that the proposed SIM was better than the original SIM and avoid mapping error effectively.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.8
• /
• pp.187-195
• /
• 2013

Most of former studies for car license plate detection restrict the image acquisition environment. The aim of this research is to diminish the restrictions by proposing a new method of using SIFT and neural network. SIFT can be used in diverse situations with less restriction because it provides size- and rotation-invariance and large discriminating power. SIFT extracted from the license plate image is divided into the internal(inside class) and the external(outside class) ones and the classifier is trained using them. In the proposed method, by just putting the various types of license plates, the trained neural network classifier can process all of the types. Although the classification performance is not high, the inside class appears densely over the plate region and sparsely over the non-plate regions. These characteristics create a local feature map, from which we can identify the location with the global maximum value as a candidate of license plate region. We collected image database with much less restriction than the conventional researches. The experiment and evaluation were done using this database. In terms of classification accuracy of SIFT keypoints, the correct recognition rate was 97.1%. The precision rate was 62.0% and recall rate was 50.2%. In terms of license plate detection rate, the correct recognition rate was 98.6%.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.5
• /
• pp.512-520
• /
• 2019

It is quite useful to represent speeches visually for learners who study foreign languages as well as the hearing impaired who cannot directly hear speeches, and a number of researches have been presented in the literature. They remain, however, at the level of representing the characteristics of speeches using colors or showing the changing shape of lips and mouth using the animation-based representation. As a result of such approaches, those methods cannot tell the users how far their pronunciations are away from the standard ones, and moreover they make it technically difficult to develop such a system in which users can correct their pronunciation in an interactive manner. In order to address these kind of drawbacks, this paper proposes a speech visualization model based on the relative distance between the user's speech and the standard one, furthermore suggests actual implementation directions by applying the proposed model to the visualization of Korean vowels. The method extract three formants F1, F2, and F3 from speech signals and feed them into the Kohonen's SOM to map the results into 2-D screen and represent each speech as a pint on the screen. We have presented a real system implemented using the open source formant analysis software on the speech of a Korean instructor and several foreign students studying Korean language, in which the user interface was built using the Javascript for the screen display.