• Journal of Digital Contents Society
• /
• v.2 no.2
• /
• pp.157-166
• /
• 2001

In this paper we propose a feature vector extraction technique using regression of shape features for the content-based image retrieval system. The proposed technique can reduce the number of dimensions of a feature vector by converting the extracted high-dimensional feature vector into a specific n-dimensional feature vector. This paper shows how to resolve the 'dimensionality curse' problem by reducing the number of dimensions of a feature vector, and shows that the technique is more efficient than the conventional techniques for the practical image retrievals.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.9 no.4
• /
• pp.53-59
• /
• 2009

The purpose of this research is particle shape evaluation of granular soil and aggregate using Digital Image Process(DIP). DIP is very useful to measure the roughness and particle shape of aggregates. Couple of aggregates, like standard sand, two different crushed stones, and two different marine aggregates, have been employed. Shape factor of two different marine aggregates is ranged 0.35 to 0.54. Crushed stone I is that of 0.74 which is highly flat, but standard sand is elongated shape. Especially, two marine aggregate showed a big difference of width and length which meaned a long shape. There is any significant difference of elongation ratio and flakiness for each aggregate with different measuring system, like direct measurement of vernier calipers and DIP method. Within the limited test results, DIP is one of useful to get the particle shape of aggregate with limitation of measuring errors and to apply the particle distribution curve.

• Proceedings of the Korea Database Society Conference
• /
• 1999.06a
• /
• pp.519-523
• /
• 1999

본 연구는 디지털 이미지 데이터에 대한 창작자의 저작권 보호 기술인 watermarking 기술을 연구하였다. 저작권 보호를 위한 정보를 invisible watermark로 삽입하였고, watermarking된 칼라 이미지를 데이터 압축, Filtering, cropping 등과 같은 여러가지 외부 공격에 대한 내구성을 실험하였다. invisible watermark를 삽입하기 위하여 변형된 주파수 변환기법을 이용하였으며, 기존의 PRN(pseudo random number) 방법보다 가시성이 뛰어난 이미지 형태의 로고를 삽입하여 저작권에 대한 확증성을 제고하였다.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.03a
• /
• pp.519-523
• /
• 1999

본 연구는 디지털 이미지 데이터에 대한 창작자의 저작권 보호 기술인 watermarking 기술을 연구하였다. 저작권 보호를 위한 정보를 invisible watermark로 삽입하였고, watermarking된 칼라 이미지를 데이터 압축, Filtering, cropping 등과 같은 여러 가지 외부 공격에 대한 내구성을 실험하였다. Invisible watermark를 삽입하기 위하여 변형된 주파수 변환기법을 이용하였으며, 기존의 PRN(pseudo random number)방법보다 가시성이 뛰어난 이미지 형태의 로고를 삽입하여 저작권에 대한 확증성을 제고하였다.

• The Journal of the Korea Contents Association
• /
• v.15 no.9
• /
• pp.11-20
• /
• 2015

Digital watermarking provides electronic means for proving the copyrights of distributed digital media copies. Research on digital watermarking for images is recently directed toward that for color images extensively used in real life, based on the substantial results in digital watermarking for gray-scale images. Color images have multiple channels, each of which corresponds to a gray-scale image. While there are some watermarking techniques for color images that just apply those for gray-scale images to one channel of the color images, the correlation characteristics between the channels are not considered in them. This paper proposes a zero-watermarking technique that makes keys via combining an image dependent watermark, created through comparing two channels of the color image and copyright watermark scrambled. Due to zero-watermarking, it does not change anything of cover(host) images. Watermark images are robust against some common attacks such as sharpening, blurring, JPEG lossy compression, scaling, and cropping.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.12
• /
• pp.3885-3895
• /
• 2000

The emergence of digital imaging and digital networks has made duplication of original artwork easier. In order to protect these creations, new methods for signing and copyrighting visual data are needed. In the last few years, a large number of schemes have heen proposed for hiding copyright marks and other information in digital image, video, audio and other multimedia objects. In this paper, we propose a technique for embedding the watermark of visually recognizable patterns into the frequency domain of images. The embedded watermark can be retrieved from the decoded sequence witbout knowledge of the original. Because the source image is not required to extract the watermark, one cannot make the fake original that is invertible to watermarking scheme from the waternlarked image. In order to recover the embedded signature data without knowledge of the original, a prediction of the original value of the pixel containing the information is needed. The prediction is based on a averaging of amplitude values in a neighborhood around the pixel itself. Additionally the projxJsed technique could survive several kinds of image processings including JPEG lossy compression.

• Journal of Advanced Navigation Technology
• /
• v.18 no.1
• /
• pp.44-49
• /
• 2014

In recent, watermarking technology have been paying attention to methods avoiding illegal use and reproduce of digital contents. Then, in order to protect the right of digital contents, a watermark image is inserted into original images. In different watermarking methods, several technologies using Ant Colony Algorithm have been studied. In this paper, we propose a watermarking method using a discrete optimization method in the ants colony algorithm. This proposed method resembls the process that ants follow the pheromone traps to find out food. And when a watermark image is inserted into original images, the proposed method considers the deployment of obstacles or the balance between cells in the entire digital image. Simulation results show that the proposed method is increased in robustness of watermarked image and is decreased in the perceptibility of watermarking compared to the previous methods.

• Convergence Security Journal
• /
• v.18 no.3
• /
• pp.53-59
• /
• 2018

In this paper, we propose a hierarchical image classification scheme for efficient object image classification. In the non-hierarchical image classification, which classifies the existing whole images at one time, it showed that objects with relatively similar shapes are not recognized efficiently. Therefore, in this paper, we introduce the image classification method in the hierarchical structure which attempts to classify object images hierarchically. Also, we introduce to the efficient class structure and algorithms considering the scalability that can occur when a deep learning image classification is applied to an actual system. Such a scheme makes it possible to classify images with a higher degree of confidence in object images having relatively similar shapes.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.16 no.1
• /
• pp.64-77
• /
• 2012

In this study, the crack detecting system with digital image processing techniques based on the mathematical morphology method was developed to detect cracks in concrete structures. In the developed system, the image combining technique of reconstructing multiple images as an entire single image considering efficient management of analysis results was applied as an additional module. The developed system was verified through a field test with the cracked concrete culvert and the crack width of 0.2 mm was able to be detected in the 40m span. In the image analysis, the difference between calculated crack width and actual crack width were less than 0.08mm. For image combination in the stitching test of pattern images, the stitched image was identical with the original picture of entire subject in the visual perception level.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.765-768
• /
• 2003

금속이나 암석에 음각(陰角)으로 각인된 문자나 그림들은 날씨나 주변 빛 환경에 따라 시각으로 입력되는 정보에 큰 차이를 보인다. 이를 이미지검출장치를 통해 읽어드려 디지털 이미지 신호로 만들고자 할 때는 더욱 그 정도가 심하여 대상체가 위치하는 빛 환경이나 검출기 특성에 각별한 신경을 써야한다. 자연광이나 전구 그리고 기후나 날씨에 의해 조성되는 빛 환경은 조도(照度), 조사각도(照射角度), 그림자 및 대상체 표면 상태 등이 중요한 결정 인자들이다. 빛 환경이 디지털 이미지 질(質)에 끼치는 영향을 최소화하기 위한 실험실 차원의 빛환경조정실을 구축하였다. 외부 유입 광선을 모두 차단하고 지향성이 있는 조명에 의해서만 대상체에 빛이 조사되도록 하고 디지털 카메라로 대상체의 이미지를 담았다. 음각 문자를 새긴 샘플석문(石文)을 제작하고 실험실 안의 정량화된 빛환경 하에서 석문의 이미지를 취득하였다. 전처리 과정을 통해 노이즈를 제거하고 이미지의 질을 향상시켰다. 처리된 이미지를 분석하여 문자영역과 바탕영역의 신호패턴을 추출한 다음 룩업 테이블, 조도 레벨 슬라이징, 중첩의 원리 및 Morphology 등의 기법을 알고리즘화하여 2진 형태의 음각문자를 판독 및 복원하는데 성공하였다.