• The KIPS Transactions:PartB
• /
• v.12B no.2 s.98
• /
• pp.151-156
• /
• 2005

In this paper, we propose feature based character watermarking methods based on geometical features specific to characters of text in document image. The proposed methods can satisfy both data capacity and robustness simultaneously while none of the conventional methods can. According to the characteristics of characters, watermark can be embed or detected through changes of connectivity of the characters, differences of characteristics of edge pixels or changes of area of holes. Experimental results show that our identification techniques are very robust to distortion and have high data capacity.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.5
• /
• pp.1059-1068
• /
• 2017

Even though BioHashing scheme can effectively extract binary string key from analog biometrics templates, it shows lower performance in stolen-token scenario due to dependency of the token. In this paper, to overcome this limitation, we suggest a new method of generating security key from face image and user intervention. Using BioHashing and GPT schemes, our scheme can adjust dependency of PIN for user authentication and generate robust key with sufficient length. We perform various experiments to show performance of the proposed scheme.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.4300-4314
• /
• 2019

With the development of video-related applications, media content has increased dramatically through applications. There is a substantial amount of near-duplicate videos (NDVs) among Internet videos, thus NDVR is important for eliminating near-duplicates from web video searches. This paper proposes a novel NDVR system that supports large-scale retrieval and contributes to the efficient and accurate retrieval performance. For this, we extracted keyframes from each video at regular intervals and then extracted both commonly used features (LBP and HSV) and new image features from each keyframe. A recent study introduced a new image feature that can provide more robust information than existing features even if there are geometric changes to and complex editing of images. We convert a vector set that consists of the extracted features to binary code through a set of hash functions so that the similarity comparison can be more efficient as similar videos are more likely to map into the same buckets. Lastly, we calculate similarity to search for NDVs; we examine the effectiveness of the NDVR system and compare this against previous NDVR systems using the public video collections CC_WEB_VIDEO. The proposed NDVR system's performance is very promising compared to previous NDVR systems.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.3
• /
• pp.464-469
• /
• 2002

In this research, nonvisibility and robustness of image watermarking mixed Key and Logo method were evaluated. The role of the Key was performed by a personal ID of a copyrighter and the logo images were used as the watermark. The standard image of Lena was used for experimental image and binary images of `Park'with size 32${\times}$32 and 64${\times}$64 were used for the watermark, respectively In order to evaluate nonvisibility of the proposed watermarking scheme, PSNR(Peak Signal to Noise Ratio) of the watermarked image was obtained and for robustness reconstructive rates of the reconstructed watermark were obtained from the watermarked image with image transformation of JPEG lossy compression. The experimental results show that nonvisibility is excellent as PSNR of the watermarked image is 93.75dB and the reconstructive rates of the case of 322${\times}$32 watermark was better than the case of the 64${\times}$64 watermark; average 5.9%, 13.9%, 6.5%, and 4.2% in the case of scale-down rates, rotational rates, impulse noise power density, and JPEG lossy compression rates, respectively.

• The KIPS Transactions:PartB
• /
• v.12B no.7 s.103
• /
• pp.729-736
• /
• 2005

In this paper. the proposed method for the digital watermarking is based on the multiresolution wavelet transform. The 1-level Discrete Wavelet Transform(DWT) coefficients of a $2N_{wx}{\times}2N_{wy}$ binary logo image used as a watermarks. The LL band and middle frequency band of the host image that the 3-level DWT has been performed are divided into $N_{wx}{\times}N_{wy}$ size and we use large coefficients at the divided blocks to make threshold. we set the thresholds that completely insert the watermark in each frequency of the host image. The thresholds in each frequency of the host image differ each other. The watermarks where is the same positions are added to the larger coefficients than threshold in the blocks at LL band and middle frequency band in order to prevent the quality deterioration of the host image. The watermarks are inserted in LL band and middle frequency band of the host image. In order to be invisibility of the watermark, the Human Visual System(HVS) is applied to the watermark. We prove the proper embedding method by experiment. We rapidly detect the watermark using this watermarking method. And because the small size watermarks are inserted by HVS, the results confirm the superiority of the proposed method on invisibility and robustness.

• Journal of Industrial Technology
• /
• v.21 no.B
• /
• pp.67-74
• /
• 2001

According as the patterns of PCB (Printed Circuit Board) become denser and complicated, quality and accuracy of PCB influence the performance of final product. It's attempted to obtain trust of 100% about all of parts. Because human inspection in mass-production manufacturing facilities are both time-consuming and very expensive, the automation of visual inspection has been attempted for many years. Thus, automatic visual inspection of PCB is required. In this paper, we used an algorithm which compares the reference PCB patterns and the input PCB patterns are separated an object and a scene by filtering and edge detection. And than compare two image using pattern matching algorithm. We suggest an defect inspection algorithm in PCB pattern, to be satisfied low cost, high speed, high performance and flexibility on the basis of $640{\times}480$ binary pattern.

• International Journal of Contents
• /
• v.14 no.1
• /
• pp.1-6
• /
• 2018

Text, as one of the most influential inventions of humanity, has played an important role in human life since ancient times. The rich and precise information embodied in text is very useful in a wide range of vision-based applications such as the text data extracted from images that can provide information for automatic annotation, indexing, language translation, and the assistance systems for impaired persons. Therefore, natural-scene text detection with active research topics regarding computer vision and document analysis is very important. Previous methods have poor performances due to numerous false-positive and true-negative regions. In this paper, a fully-convolutional-network (FCN)-based method that uses supervised architecture is used to localize textual regions. The model was trained directly using images wherein pixel values were used as inputs and binary ground truth was used as label. The method was evaluated using ICDAR-2013 dataset and proved to be comparable to other feature-based methods. It could expedite research on text detection using deep-learning based approach in the future.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.12
• /
• pp.651-658
• /
• 2000

This paper presents a new method to extract traffic information such as number of passing vehicles and average speed by a pair of stereo road images. The whole process consists of the extraction of vehicles and the tracking of the extracted vehicles. For the extraction of vehicles, the outline of each vehicle is obtained by using binary region growing technique applied to disparity map based on multi-resolution stereo matching. The Kalman filter tracking algorithm is applied to the extracted vehicle outlines to determine the flow of vehicles. Experimental results show that the proposed method significantly improved recognition rate of vehicles over the conventional methods-frame difference and background elimination methods.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.385-388
• /
• 2000

본 논문에서는 영상처리 기법 중 하나인 이진 영상에 대한 골격화를 이용한 새로운 형상 기술자를 제안한다. 내용기반 영상 검색에서 형상을 이용하는 것은 가장 우세하고 인간이 가장 쉽게 인지할수 있는 방법 중의 하나이다. 형상을 이용한 검색을 위해 서는 인간이 인지하는 형상에 대한 정보를 간략화시킬 수 있는 기술자가 필요하다. 본 논문에서 제안하는 골격을 이용한 형상 기술자는 물체의 중요한 정보 중 하나인 골격을 영상 검색에 이용함으로써 기존의 물체가 갖고 있는 복잡한 형상 정보들을 여러개의 직선의 조합으로 간략하게 표현하고 이를 검색에 사용하는 것이다. 이를 위해서 단순한 골격화 외의 다른 형태학적 영상 처리를 이용하여 효과적인 직선 추출을 위한 여건을 마련한다. 그리고 근사화된 직선들이 추출되면 스케일에 대해 정규화 하여 골격을 이루는 직선들의 양 끝점을 형상 기술자로 얻을 수 있다. 각 특징벡터에 대한 정합은 각각의 회전에 대해 유클리디안 거리를 이용한다. 실험 결과, 제안된 방법이 자세한 부분보다는 대략적인 형상 검색과 동일한 카테고리의 데이타 집합에서 부분적인 변화에 대해 우수한 성능을 나타낸다는 것을 알 수 있다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.476-479
• /
• 2003

The Rough transform (HT) is often used for extracting global features in binary images, for example curve and line segments, from local features such as single pixels. The HT is useful due to its insensitivity to missing edge points and occlusions, and robustness in noisy images. However, it possesses some disadvantages, such as time and memory consumption due to the number of input data and the selection of an optimal and efficient resolution of the accumulator space can be difficult. Another problem of the HT is in the difficulty of peak detection due to the discrete nature of the image space and the round off in estimation. In order to resolve the problem mentioned above, a possibilistic C-means approach to clustering [1] is used to cluster neighboring peaks. Several experimental results are given.