• Journal of Ubiquitous Convergence Technology
• /
• v.1 no.1
• /
• pp.18-22
• /
• 2007

Multi-Instance Learning(MIL) performs well to deal with inherently ambiguity of images in multimedia retrieval. In this paper, an effective framework for Contented-Based Image Retrieval(CBIR) with MIL techniques is proposed, the effective mechanism is based on the image segmentation employing improved Mean Shift algorithm, and processes the segmentation results utilizing mathematical morphology, where the goal is to detect the semantic concepts contained in the query. Every sub-image detected is represented as a multiple features vector which is regarded as an instance. Each image is produced to a bag comprised of a flexible number of instances. And we apply a few number of MIL algorithms in this framework to perform the retrieval. Extensive experimental results illustrate the excellent performance in comparison with the existing methods of CBIR with MIL.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.724-726
• /
• 2003

Currently available image fusion methods are not efficient for fusing the Landsat 7 images. Significant color distortion is one of the major problems. In this paper, using the well-known wavelet based method for data fusion between high-resolution panchromatic and low-resolution multispectral satellite images, we performed Landsat 7 image fusion. Based on the experimental results obtained from this study, we analyzed some reasons for color distortion. A new approach using the biorthogonal wavelets based method for data fusion is presented. This new method has reached an optimum fusion result - with the same spectral resolution as the multispectral image and the same spatial resolution as the panchromatic image with minimum artifacts.

• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.67-75
• /
• 2023

Recently, many studies have been conducted on ways to utilize AI technology in NIDS (Network Intrusion Detection System). In particular, CNN-based NIDS generally shows excellent performance. CNN is basically a method of using correlation between pixels existing in an image. Therefore, the method of generating an image is very important in CNN. In this paper, the performance comparison of CNN-based NIDS according to the image generation method was performed. The image generation methods used in the experiment are a direct conversion method and a one-hot encoding based method. As a result of the experiment, the performance of NIDS was different depending on the image generation method. In particular, it was confirmed that the method combining the direct conversion method and the one-hot encoding based method proposed in this paper showed the best performance.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.187-192
• /
• 2006

Image fusion techniques are widely used to integrate a lower spatial resolution multispectral image with a higher spatial resolution panchromatic image. However, the existing techniques either cannot avoid distorting the image spectral properties or involve complicated and time-consuming decomposition and reconstruction processing in the case of wavelet transform-based fusion. In this study a simple spectral preserve fusion technique: the Smoothing Filter-based Replacement(SFR) is proposed based on a simplified solar radiation and land surface reflection model. By using a ratio between a higher resolution image and its low pass filtered (with a smoothing filter) image, spatial details can be injected to a co-registered lower resolution multispectral image minimizing its spectral properties and contrast. The technique can be applied to improve spatial resolution for either colour composites or individual bands. The fidelity to spectral property and the spatial quality of SFM are convincingly demonstrated by an image fusion experiment using IKONOS panchromatic and multispectral images. The visual evaluation and statistical analysis compared with other image fusion techniques confirmed that SFR is a better fusion technique for preserving spectral information.

• The KIPS Transactions:PartB
• /
• v.10B no.7
• /
• pp.823-828
• /
• 2003

The main objective of this paper is to provide a methodology of feature extraction using shape of image objects for content-based image retrieval. The shape of most real-life objects is irregular, and hence there is no universal approach to quantify the shape of an arbitrary object. In particular. electronic catalogs contain many image objects for their products. In this paper, we perform feature extraction based on individual objects in images rather than on the whole image itself, since our method uses a shape-based approach of objects using RLC lines within an image. Experiments show that shape parameters distinctly represented image objects and provided better classification and discrimination among image objects in an image database compared to Texture.

• Journal of the Optical Society of Korea
• /
• v.6 no.4
• /
• pp.156-160
• /
• 2002

In this paper, we propose an improved optical security system using three phase-encoded images and the principle of interference. This optical system based on a Mach-Zehnder interferometer consists of one phase-encoded virtual image to be encrypted and two phase-encoded images, en-crypting image and decrypting image, where every pixel in the three images has a phase value of '0'and'$\pi$'. The proposed encryption is performed by the multiplication of an encrypting image and a phase-encoded virtual image which dose not contain any information from the decrypted im-age. Therefore, even if the unauthorized users steal and analyze the encrypted image, they cannot reconstruct the required image. This virtual image protects the original image from counterfeiting and unauthorized access. The decryption of the original image is simply performed by interfering between a reference wave and a direct pixel-to-pixel mapping image of the en crypted image with a decrypting image. Computer simulations confirmed the effectiveness of the proposed optical technique for optical security applications.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.2
• /
• pp.85-92
• /
• 2017

This paper presents a dehazing method based on a fuzzy membership function and variational method. The proposed algorithm consists of three steps: i) estimate transmission through a pixel-based operation using a fuzzy membership function, ii) refine the transmission using an L1-norm-based regularization method, and iii) obtain the result of haze removal based on a hazy image formation model using the refined transmission. In order to prevent color distortion of the sky region seen in conventional methods, we use a trapezoid-type fuzzy membership function. The proposed method acquires high-quality images without halo artifacts and loss of color contrast.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.6
• /
• pp.2317-2337
• /
• 2015

Cryptography provides an effective solution to secure the communication over public networks. The communication over public networks that includes electronic commerce, business and military services, necessitates the requirement of simple and robust encryption techniques. In this paper, a novel image encryption method which employs calligraphy based hybrid scan and random number is presented. The original image is scrambled by pixel position permutation with calligraphy based diagonal and novel calligraphy based scan patterns. The cipher image is obtained by XORing the scrambled image with random numbers. The suggested method resists statistical, differential, entropy, and noise attacks which have been demonstrated with a set of standard images.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.6
• /
• pp.445-449
• /
• 2009

In this paper, we propose a computationally efficient multi GPU accelerated image registration technique to correct the motion difference between the pre-contrast CT image and post-contrast CTA image. Our method consists of two steps: multi GPU based image registration and a cerebrovascular visualization. At first, it computes a similarity measure considering the parallelism between both GPUs as well as the parallelism inside GPU for performing the voxel-based registration. Then, it subtracts a CT image transformed by optimal transformation matrix from CTA image, and visualizes the subtracted volume using GPU based volume rendering technique. In this paper, we compare our proposed method with existing methods using 5 pairs of pre-contrast brain CT image and post-contrast brain CTA image in order to prove the superiority of our method in regard to visual quality and computational time. Experimental results show that our method well visualizes a brain vessel, so it well diagnose a vessel disease. Our multi GPU based approach is 11.6 times faster than CPU based approach and 1.4 times faster than single GPU based approach for total processing.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.9
• /
• pp.1448-1455
• /
• 1990

In this paper, a range image segmentation method is proposed. This method consists of an initial segmentation stage by discontinuous edge detection and surface type labeling based on the sign of the principal curvatures. Initially type labeled image is oversegmented, this image is merged via stepwise optimal region merging stage based on polynomial function approxiamtion. The successful segmentation results are presented for two synthetic range images with noise and a real-world ERIM range image.