• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.469-481
• /
• 2018

DL (Deep Learning) is getting popular in various fields to implement artificial intelligence that resembles human learning and cognition. DL based on complicate structure of the ANN (Artificial Neural Network) requires computing power and computation cost. Variety of DL models with improved performance have been developed with powerful computer specification. The main purpose of this paper is to detect buildings from aerial images and evaluate performance of Mask R-CNN (Region-based Convolutional Neural Network) developed by FAIR (Facebook AI Research) team recently. Mask R-CNN is a R-CNN that is evaluated to be one of the best ANN models in terms of performance for semantic segmentation with pixel-level accuracy. The performance of the DL models is determined by training ability as well as architecture of the ANN. In this paper, we characteristics of the Mask R-CNN with various types of the images and evaluate possibility of the generalization which is the ultimate goal of the DL. As for future study, it is expected that reliability and generalization of DL will be improved by using a variety of spatial information data for training of the DL models.

• Journal of KIISE:Information Networking
• /
• v.30 no.4
• /
• pp.504-512
• /
• 2003

In this paper, we propose a new adaptive dissolve detection method based on the analysis of a dissolve modeling error which is the difference between an ideally modeled dissolve curve with no correlation and an actual dissolve curve including a correlation. The proposed dissolve detection method consists of two steps. First, candidate dissolve regions are extracted using the characteristics of a downward convex parabola, then each candidate region is verified based oil the dissolve modeling error. If the dissolve modeling error for a candidate region is less than a threshold defined by the target modeling error with a target correlation, the candidate region is determined as a resolve region with a lower correlation than the target correlation. The threshold is adaptively determined based on the variances between the candidate regions and the target correlation. By considering the correlation between neighbor scenes, the proposed method is able to be a semantic scene-change detector. The proposed method was tested on various types of data and its performance proved to be more accurate and reliable regardless of variation of variance of test sequences when compared with other commonly use methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2737-2753
• /
• 2013

In this study, we propose a novel salient object detection strategy based on regional contrast and relative spatial compactness. Our algorithm consists of four basic steps. First, we learn color names offline using the probabilistic latent semantic analysis (PLSA) model to find the mapping between basic color names and pixel values. The color names can be used for image segmentation and region description. Second, image pixels are assigned to special color names according to their values, forming different color clusters. The saliency measure for every cluster is evaluated by its spatial compactness relative to other clusters rather than by the intra variance of the cluster alone. Third, every cluster is divided into local regions that are described with color name descriptors. The regional contrast is evaluated by computing the color distance between different regions in the entire image. Last, the final saliency map is constructed by incorporating the color cluster's spatial compactness measure and the corresponding regional contrast. Experiments show that our algorithm outperforms several existing salient object detection methods with higher precision and better recall rates when evaluated using public datasets.

• International Journal of Advanced Culture Technology
• /
• v.5 no.1
• /
• pp.83-89
• /
• 2017

In this paper, we propose an extended method of one-hot Long Short-Term Memory (LSTM) and evaluate the performance on spam filtering task. Most of traditional methods proposed for spam filtering task use word occurrences to represent spam or non-spam messages and all syntactic and semantic information are ignored. Major issue appears when both spam and non-spam messages share many common words and noise words. Therefore, it becomes challenging to the system to filter correct labels between spam and non-spam. Unlike previous studies on information filtering task, instead of using only word occurrence and word context as in probabilistic models, we apply a neural network-based approach to train the system filter for a better performance. In addition to one-hot representation, using term weight with attention mechanism allows classifier to focus on potential words which most likely appear in spam and non-spam collection. As a result, we obtained some improvement over the performances of the previous methods. We find out using region embedding and pooling features on the top of LSTM along with attention mechanism allows system to explore a better document representation for filtering task in general.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.597-599
• /
• 2003

웹 상의 정보는 여러 페이지들에 걸쳐 표현되고 있으나 대부분의 웹 브라우저는 웹 페이지 단위로 정보를 다루고 있기 때문에 사용자는 원하는 정보를 얻기 위해 여러 웹 페이지들을 방문해야 한다. 본 논문에서는 사용자의 요구에 부합되는 정보를 검색해 여러 페이지 상에 흩어져 있는 정보들에 대해 쉽게 이해할 수 있도록 컬렉션 페이지를 제공한다. 컬렉션 페이지는 검색된 웹 페이지들의 링크 관계를 제공하여 페이지들 사이에서의 정보의 구성을 알 수 있게 하고, 관련도 높은 페이지들의 주요 내용을 미리 가져와 보여 줌으로써 정보에 대한 접근성을 높인다. 이를 위해 페이지 안에서 시각적으로 구분되는 동일한 주제의 정보를 담은 블록을 의미 구역으로 정의하고 웹 페이지를 실제 정보의 단위인 의미 구역으로 나누었다. 또한 의미 구역단위의 검색으로 여러 주제의 정보를 담고 있는 웹 페이지에 대한 검색 결과의 정확성을 높인다.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.9-17
• /
• 2020

Hippocampus is a complex brain structure embedded deep into the temporal lobe. Studies have shown that this structure gets affected by neurological and psychiatric disorders and it is a significant landmark for diagnosing neurodegenerative diseases. Hippocampus features play very significant roles in region-of-interest based analysis for disease diagnosis and prognosis. In this study, we have attempted to learn the embeddings of this important biomarker. As conventional metric learning methods for feature embedding is known to lacking in capturing semantic similarity among the data under study, we have trained deep Siamese convolutional neural network for learning metric of the hippocampus. We have exploited Gwangju Alzheimer's and Related Dementia cohort data set in our study. The input to the network was pairs of three-view patches (TVPs) of size 32 × 32 × 3. The positive samples were taken from the vicinity of a specified landmark for the hippocampus and negative samples were taken from random locations of the brain excluding hippocampi regions. We have achieved 98.72% accuracy in verifying hippocampus TVPs.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.787-790
• /
• 2002

의미 기반 영상 검색은 Color, Texture, Region 정보, Spatial Color Distribution등의 저차원 특징 정보와 이미지 데이터에 의미를 부여하기 위해 주서 처리하는 것이 일반적이다. 그리고 부여된 키워드나 시소러스와 같은 어휘 사전을 이용하여 의미기반 정보검색을 수행하고 있지만, 기존의 키워드기반 텍스트 정보검색의 한계를 벗어나지 못하는 문제를 야기 시킨다. 이에 본 논문에서는 시각 데이터에 존재하는 객체들과 그 객체 사이의 개념관계를 Ontology의 한 형태인 WordNet을 이용하여 의미 정보로 표현할 수 있도록 한다. 이를 활용하면 영상 데이터의 자동 주석 시스템이나 검색 시스템에서 인간이 인식하는 개념적인 사고방식에 더욱 접근할 수 있는 결과물을 얻을 수 있을 것이다.

• Journal of Korean Library and Information Science Society
• /
• v.8
• /
• pp.69-96
• /
• 1981

We all know that we can not keep a proper social life without language. Yet language is so much a part of our environment that we hardly realize it is there. The purpose of this study is to provide an understanding of the linguistical aspect of communication process in order to carry out a successful human relations in the operation of libraries. Human development rests upon man's capacity to digest large quantities of knowledge and it is language which allows facts to be communicated, stored, and disseminated. An attempt was made in this study to illustrate the elementary meaning-of-words aspect of communication. In order to share the most commonly agreed meanings in interpersonal communication, a careful study of semantic noises is important. In a constant struggle to meet client needs, staff and administrators, librarian must understand communication dialogues, their messages and be able to read all level of meanings. In order to perform a successful function of the librarian, to act as a link-man or communicator and to cope with its ever growing information, it is suggested that the deep understanding of the following linguistical aspect of communication elements is essential. 1. Characteristics of Language: (1) Words have different meanings to different people. (2) Words vary in the degree of abstraction. (3) Language is incomplete by its nature. (4) Language reflects not only the personality of the individual but also the culture of man's society. 2. Noises in transmitting meanings: (1) Mechanical or Technical noises. (2) Semantic Noises (3) Noises caused by the psychological factors a. attention b. perception, sensation, cognition and perceptual field. 3. Linguistic Stratum Languages differ considerably in vocabulary by the physical and cultural environment setting as well as situation of individual living. There are seven different language stratum which reflects different region, sex, age, profession, special social stratum, academic and tabooed words.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.2
• /
• pp.69-78
• /
• 2006

This paper is concerned with analyzing the images of Korean automobiles using, so called, sensory engineering, which adapts the sensory and subjective assessment of human beings in evaluating the quality of product. The methodology of analysis is suggested in this paper according to the following steps. First, 14 pairs of adjectives, which describe the image of object cars in view of the semantic differential method, are derived from consulting with several expert panels. Nextly, factor analysis is performed in order to obtain the axises, by which the images space of the object automobiles are specified, and then the images of the object automobiles are measured by the coordinate of all the object automobiles in the image space. In this paper, a sensory estimation experiment is performed to a panel consisting with In undergraduate students residing in the region of Daegu. From the result of analysis of this paper, target images, which the automobile manufacturers are intended, are achieved by and large except one company.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.395-409
• /
• 2022

The purpose of this study is to evaluate the classification performance and applicability when land cover datasets constructed for AI training are cross validation to other areas. For study areas, Gyeongsang-do and Jeolla-do in South Korea were selected as cross validation areas, and training datasets were obtained from AI-Hub. The obtained datasets were applied to the U-Net algorithm, a semantic segmentation algorithm, for each region, and the accuracy was evaluated by applying them to the same and other test areas. There was a difference of about 13-15% in overall classification accuracy between the same and other areas. For rice field, fields and buildings, higher accuracy was shown in the Jeolla-do test areas. For roads, higher accuracy was shown in the Gyeongsang-do test areas. In terms of the difference in accuracy by weight, the result of applying the weights of Gyeongsang-do showed high accuracy for forests, while that of applying the weights of Jeolla-do showed high accuracy for dry fields. The result of land cover classification, it was found that there is a difference in classification performance of existing datasets depending on area. When constructing land cover map for AI training, it is expected that higher quality datasets can be constructed by reflecting the characteristics of various areas. This study is highly scalable from two perspectives. First, it is to apply satellite images to AI study and to the field of land cover. Second, it is expanded based on satellite images and it is possible to use a large scale area and difficult to access.