• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.8
• /
• pp.1941-1947
• /
• 2014

Document image binarization is largely used as previous stage of document recognition. And the result of document recognition is much affected from the result of document image binarization. There were many studies to binarize document images. The results of previous studies for document image binarization is varied according to the state of document images. In this paper, we propose a technique for document image binarization using MSER that is applied to extract objects from an image. At first, raw MSER objects are extracted from a document image. Because the raw MSER objects cannot be used for document image binarization, the extracted raw MSER objects are modified. Then the final MSER objects are used for document image binarization with the contrast image that is extracted from the document image. Experimental results show that the proposed technique is useful for document image binarization.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.25-27
• /
• 2011

본 논문에서는 이미지 블록의 평균 픽셀 값 특성을 양자화 인덱스 변조 기법에 적용하여 이미지 포맷변환에 강인한 정보은닉 기법을 제안한다. 포맷변환에 강인한 이미지 속성은 정규화된 픽셀 히스토그램에 기반하여 분석되며, 그 중 평균 픽셀 값을 통해 정보은닉 알고리즘이 구성된다. 평균 픽셀 값을 양자화 인덱스 변조기법에 적용하기 위한 방안으로 DCT 계수를 정규화 하는 방법이 선택되며, 추출 성공률을 높이기 위해 오류정정부호가 사용된다. 따라서 본 논문의 알고리즘을 통해 결합 이미지가 압축, 사이즈 변화 등의 과정을 거치게 될 경우 발생하는 문제점을 극복할 수 있다.

• Journal of Korea Game Society
• /
• v.13 no.6
• /
• pp.35-42
• /
• 2013

A new compressed image format is proposed to use a large size of image in mobile games without the constraints of hardware specifications such as memory amount, processing power, which encodes each block of a large size image in scan line order. Using the experiments, we show the effectiveness of proposed method compared with a general PNG in terms of compression ratios and required memory in decoding processes. Also, the loading delay can be reduced by decoding only the displaying area of a large image in run-time.

• Journal of Digital Contents Society
• /
• v.5 no.1
• /
• pp.48-53
• /
• 2004

Due to NxN block coding blocking artifacts are exhibited by block-based DCT coding images, primarily at low bit rates. In this letter, we propose the new technique that reduce the blocking artifacts pixels in such images. In the case of combining with list block reconstruction techniques, our algorithm can be also used to improve image qiality. And, the performance of the proposed algorithm is demonstrated experimentally.

• Journal of the Korean Society for Railway
• /
• v.12 no.3
• /
• pp.412-419
• /
• 2009

How to efficiently and accurately detect the damages generated in a structure has become an important issue for structural health monitoring (SHM). Most existing SHM techniques require the baseline data which should be measured before a structure get damaged. Thus, this paper presents a new pitch-catch method-based SHM technique which will not require the baseline data any more. In the proposed SHM technique, the imaging method is also utilized to visualize damage locations. The proposed SHM technique is then validated through the damage detection texts for damaged aluminum plates.

• Journal of IKEEE
• /
• v.27 no.1
• /
• pp.59-64
• /
• 2023

Deep learning can solve various computer vision problems, but it requires a large dataset. Data augmentation technique based on image binarization for constructing large-scale datasets is proposed in this paper. By extracting features using image binarization and randomly placing the remaining pixels, new images are generated. The generated images showed similar quality to the original images and demonstrated excellent performance in deep learning models.

• KIISE Transactions on Computing Practices
• /
• v.22 no.6
• /
• pp.290-295
• /
• 2016

Recently, folksonomy-based image-sharing sites where users cooperatively make and utilize tags of image annotation have been gaining popularity. Typically, these sites retrieve images for a user request using simple text-based matching and display retrieved images in the form of photo stream. However, these tags are personal and subjective and images are not categorized, which results in poor retrieval accuracy and low user satisfaction. In this paper, we propose a categorization scheme for folksonomy images which can improve the retrieval accuracy in the tag-based image retrieval systems. Consequently, images are classified by the semantic similarity using text-information and image-information generated on the folksonomy. To evaluate the performance of our proposed scheme, we collect folksonomy images and categorize them using text features and image features. And then, we compare its retrieval accuracy with that of existing systems.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.555-556
• /
• 2021

In this paper, we propose a malware family classification scheme using malware visualization and transfer learning. The malware can be easily reused or modified. However, traditional malware detection techniques are vulnerable to detecting variants of malware. Malware belonging to the same class are converted into images that are similar to each other. Therefore, the proposed method can classify malware with a deep learning model that has been verified in the field of image classification. As a result of an experiment using the VGG-16 model on the Malimg dataset, the classification accuracy was over 98%.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.35-36
• /
• 2016

본 논문에서는 기존 Bag-of-Visual words (BoW) 접근법에서 반영하지 못한 이미지의 공간 정보를 활용하기 위해서 Spatial Pyramid Matching (SPM) 기법을 Latent Dirichlet Allocation (LDA) 모델에 결합하여 이미지를 분류하는 모델을 제안한다. BoW 접근법은 이미지 패치를 시각적 단어로 변환하여 시각적 단어의 분포로 이미지를 표현하는 기법이며, 기존의 방식이 이미지 패치의 위치정보를 활용하지 못하는 점을 극복하기 위하여 SPM 기법을 도입하는 연구가 진행되어 왔다. 또한 이미지 패치를 정확하게 표현하기 위해서 벡터 양자화 대신 희소 부호화 기법을 이용하여 이미지 패치를 시각적 단어로 변환하였다. 제안하는 모델은 BoW 접근법을 기반으로 위치정보를 활용하는 SPM 을 LDA 모델에 적용하여 시각적 단어의 토픽을 추론함과 동시에 multi-class SVM 분류기를 이용하여 이미지를 분류한다. UIUC 스포츠 데이터를 이용하여 제안하는 모델의 분류 성능을 검증하였다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.04a
• /
• pp.357-360
• /
• 2000

최근에는 텍스트기반 검색 기법의 단점들을 극복하기 위하여 멀티미디어 데이터에서 내용으로 표현되는 특징데이터(Feature data)를 자동으로 추출하여 이를 기반으로 검색을 하는 내용기반 검색기법(Content- Based Retrieval Technique)에 대한 연구가 활발하다. 그러나 내용기반 검색 시스템에서 데이터 수가 무한히 많아질 경우, 찾고자 하는 이미지를 검색하는데 정확성과 시간면에서 효율성이 떨어진다. 따라서 방대한 이미지 데이터를 보다효과적으로 검색하고 저장하기 위해서는 유사성이 높은 이미지들을 서로 묶어 그룹화하고 그룹별 특징을 분석하여 인덱스화 함이 필요하다. 이에 본 논문에서는 그룹화를 위해 각각의 이미지 객체에 대하여 웨이브릿변환 (Wavelet Transform) 기법과 질감 특징( Texture Feature) 값 추출을 통해 그룹간에 가지는 특징값을 분석 비교하였다.