• Smart Structures and Systems
• /
• v.30 no.3
• /
• pp.287-301
• /
• 2022

The machine-vision based structural displacement measurement methods are widely used due to its flexible deployment and non-contact measurement characteristics. The accuracy of vision measurement is directly related to the image resolution. In the field of computer vision, super-resolution reconstruction is an emerging method to improve image resolution. Particularly, the deep-learning based image super-resolution methods have shown great potential for improving image resolution and thus the machine-vision based measurement. In this article, we firstly review the latest progress of several deep learning based super-resolution models, together with the public benchmark datasets and the performance evaluation index. Secondly, we construct a binocular visual measurement platform to measure the distances of the adjacent corners on a chessboard that is universally used as a target when measuring the structure displacement via machine-vision based approaches. And then, several typical deep learning based super resolution algorithms are employed to improve the visual measurement performance. Experimental results show that super-resolution reconstruction technology can improve the accuracy of distance measurement of adjacent corners. According to the experimental results, one can find that the measurement accuracy improvement of the super resolution algorithms is not consistent with the existing quantitative performance evaluation index. Lastly, the current challenges and future trends of super resolution algorithms for visual measurement applications are pointed out.

• Current Optics and Photonics
• /
• v.8 no.3
• /
• pp.270-281
• /
• 2024

Information-hiding technology is introduced into an optical ghost imaging encryption scheme, which can greatly improve the security of the encryption scheme. However, in the current mainstream research on camouflage ghost imaging encryption, information hiding techniques such as digital watermarking can only hide 1/4 resolution information of a cover image, and most secret images are simple binary images. In this paper, we propose an equal-resolution image-hiding encryption scheme based on deep learning and computational ghost imaging. With the equal-resolution image steganography network based on deep learning (ERIS-Net), we can realize the hiding and extraction of equal-resolution natural images and increase the amount of encrypted information from 25% to 100% when transmitting the same size of secret data. To the best of our knowledge, this paper combines image steganography based on deep learning with optical ghost imaging encryption method for the first time. With deep learning experiments and simulation, the feasibility, security, robustness, and high encryption capacity of this scheme are verified, and a new idea for optical ghost imaging encryption is proposed.

• International Journal of Computer Science & Network Security
• /
• v.21 no.12spc
• /
• pp.463-468
• /
• 2021

Single image super-resolution (SISR) is an image processing technique, and its main target is to reconstruct the high-quality or high-resolution (HR) image from the low-quality or low-resolution (LR) image. Currently, deep learning-based convolutional neural network (CNN) image super-resolution approaches achieved remarkable improvement over the previous approaches. Furthermore, earlier approaches used hand designed filter to upscale the LR image into HR image. The design architecture of such approaches is easy, but it introduces the extra unwanted pixels in the reconstructed image. To resolve these issues, we propose novel deep learning-based approach known as Lightweight deep CNN-based approach for Single Image Super-Resolution (LDCSIR). In this paper, we propose a new architecture which is inspired by ResNet with Inception blocks, which significantly drop the computational cost of the model and increase the processing time for reconstructing the HR image. Compared with the other state of the art methods, LDCSIR achieves better performance in terms of quantitively (PSNR/SSIM) and qualitatively.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1995.06a
• /
• pp.91-96
• /
• 1995

In this paper we propose algorithms for high resolution image sequence interpolation. Image sequences, in general, are assumed to have greater amount of information than a still image. By this reason, image sequences can be used to improve the resolution of interpolated image sequences. Therefore the proposed algorithms can be the theoretical basis for interpolating dynamic image sequences. In order to demonstrate the validity of the proposed algorithms, experimental results using both synthetic and real test images are presented.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.299-301
• /
• 1996

Since a standard lens has small sight angle, a fish-eye lens can be used in order to obtain wide sight angle for the robot vision system. In spite of the advantage, the image through the lens has variable resolution; the central information of the lens is of high resolution, but the peripheral information is of low resolution. Owing to this difference of resolution, the variable resolution image should be transformed to a uniform resolution image in order to determine the positions of the objects in the image. In this work, the correction method for the distorted image is presented and the performance is analyzed. Furthermore, the camera with a fish eye lens can be used to determine the real world coordinates. The performance is shown through experiments.

• Korean Journal of Remote Sensing
• /
• v.25 no.6
• /
• pp.517-529
• /
• 2009

Many satellite image fusion techniques have been developed in order to produce a high resolution multispectral (MS) image by combining a high resolution panchromatic (PAN) image and a low resolution MS image. Heretofore, most high resolution image fusion techniques have used IKONOS and QuickBird images. Recently, GeoEye-1, offering the highest resolution of any commercial imaging system, was launched. In this study, we have experimented with GeoEye-1 images in order to evaluate which fusion algorithms are suitable for these images. This paper presents compares and evaluates the efficiency of five image fusion techniques, the $\grave{a}$ trous algorithm based additive wavelet transformation (AWT) fusion techniques, the Principal Component analysis (PCA) fusion technique, Gram-Schmidt (GS) spectral sharpening, Pansharp, and the Smoothing Filter based Intensity Modulation (SFIM) fusion technique, for the fusion of a GeoEye-1 image. The results of the experiment show that the AWT fusion techniques maintain more spatial detail of the PAN image and spectral information of the MS image than other image fusion techniques. Also, the Pansharp technique maintains information of the original PAN and MS images as well as the AWT fusion technique.

• Korean Journal of Remote Sensing
• /
• v.23 no.6
• /
• pp.547-552
• /
• 2007

This study presents an approach to reconstruct high-resolution imagery for multispectral imagery of low-resolution using panchromatic imagery of high-resolution. The proposed scheme reconstructs a high-resolution image which agrees with original spectral values. It uses a linear model of high-and low- resolution images and consists of two stages. The first one is to perform a global estimation of the least square error on the basis of a linear model of low-resolution image associated with high-resolution feature, and next local correction then makes the reconstructed image locally fit to the original spectral values. In this study, the new method was applied to KOMPSAT-1 EOC image of 6m and LANDSAT ETM+ of 30m, and an 1m RGB image was also generated from 4m IKONOS multispectral data. The results show its capability to reconstruct high-resolution imagery from multispectral data of low-resolution.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.6
• /
• pp.117-124
• /
• 2008

The approaches to overcome the limited spatial resolution and the limited dynamic range of image sensors have been studied independently. A high resolution image is reconstructed from multiple low resolution observations and a wide dynamic range image is reconstructed from differently exposed multiple low dynamic range in es based on signal processing approach. In practical situations, it is reasonable to address them in a unified context because the recorded image suffers from limitations of both spatial resolution and dynamic range. In this paper, the image acquisition process including limited spatial resolution and limited dynamic range is modelled. With the image acquisition model, the response function of the imaging system is estimated and the single image of which spatial resolution and dynamic range are simultaneously enhanced is obtained. Experimental results indicate that the proposed algorithm outperforms the conventional approaches that perform the high resolution and wide dynamic range reconstruction sequentially with respect to both objective and subjective criteria.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.18-21
• /
• 2008

Lee (2008) proposed the pansharpening method to reconstruct at the higher resolution the multispectral images which agree with the spectral values observed from the sensor of the lower resolution values. It outperformed over several current techniques for the statistical analysis with quantitative measures, and generated the imagery of good quality for visual interpretation. However, if a small object stretches over two adjacent pixels with different spectral characteristics at the lower resolution, the pixels of the object at the higher resolution may have different multispectral values according to their location even though they have a same intensity in the panchromatic image of higher resolution. To correct this problem, this study employed an iterative technique similar to the image restoration scheme of Point-Jacobian iterative MAP estimation. The effect of pansharpening on image segmentation/classification was assessed for various techniques. The method was applied to the IKONOS image acquired over the area around Anyang City of Korea.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.263-265
• /
• 2003

The computation cost of image registration is affected by searching data size and space. This paper proposes an efficient image registration algorithm that uses multi-resolution wavelet decomposed image to reduce the data size search. The algorithm determines the correlation detection at low resolution on low-pass sub bands of wavelet and generate mask for higher resolution as part of a coarse to fine registration algorithm. The correlation matching is defined for coarse resolution similarity measurement, while mutual information (MI) is used at fine resolution. The results show that the new efficient mask-based algorithm improves computational efficiency and yields robust and consistent image registration results.