• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.10
• /
• pp.108-117
• /
• 2015

If typical contrast enhancement algorithms for natural images are applied to X-ray images, they may cause artifacts such as overshooting or produce unnatural visual quality because they do not consider inherent characteristics of X-ray images. In order to overcome such problems, we propose a locally adaptive block-based contrast enhancement algorithm for X-ray images. After we derive a weighted cumulative distribution function for each block, we apply it to each block for contrast enhancement. Then, we obtain images that are removed from block effect by adopting block-based overlapping. In post-processing, we obtain the final image by emphasizing high frequency components. Experimental results show that the proposed block-based contrast enhancement algorithm provides at maximum 5-times higher visual quality than the exiting algorithm in terms of quantitative contrast metric.

• Journal of Korea Multimedia Society
• /
• v.22 no.6
• /
• pp.646-654
• /
• 2019

Image denoising is considered as a key factor for capturing high-quality photos in digital cameras. Thus far, several image denoising methods have been proposed in the past decade. In addition, previous studies either relied on deep learning-based approaches or used the hand-crafted filters. Unfortunately, the previous method mostly emphasized on image denoising regardless of preserving or recovering the detail information in result images. This study proposes an detail extraction network to estimate detail information from a noisy input image. Moreover, the extracted detail information is utilized to enhance the final denoised image. Experimental results demonstrate that the proposed method can outperform the existing works by a subjective measurement.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.237-240
• /
• 2020

The fine-tuned neural network (NN) model for a whole temporal portion in a video does not always yield the best quality (e.g., PSNR) performance over all regions of each frame in the temporal period. For certain regions (usually homogeneous regions) in a frame for super-resolution (SR), even a simple bicubic interpolation method may yield better PSNR performance than the fine-tuned NN model. When there are multiple NN models available at the receivers where each NN model is trained for a group of images having a specific category of image characteristics, the performance of Quality enhancement can be improved by selectively applying an appropriate NN model for each image region according to its image characteristic category to which the NN model was dedicatedly trained. In this case, it is necessary to signal which NN model is applied for each region. This is very advantageous for image restoration and quality enhancement (IRQE) applications at user terminals with limited computing capabilities.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.301-307
• /
• 2024

This study introduces a novel cascade fusion architecture aimed at enhancing thermal images across various scale conditions. The processing of thermal images at multiple scales has been challenging due to the limitations of existing methods that are designed for specific scales. To overcome these limitations, this paper proposes a unified framework that utilizes cascade feature fusion to effectively learn multi-scale representations. Confidence maps from different image scales are fused in a cascaded manner, enabling scale-invariant learning. The architecture comprises end-to-end trained convolutional neural networks to enhance image quality by reinforcing mutual scale dependencies. Experimental results indicate that the proposed technique outperforms existing methods in multi-scale thermal image enhancement. Performance evaluation results are provided, demonstrating consistent improvements in image quality metrics. The cascade fusion design facilitates robust generalization across scales and efficient learning of cross-scale representations.

• The Journal of the Korea Contents Association
• /
• v.9 no.10
• /
• pp.13-21
• /
• 2009

This paper describes research of image enhancement for detection of face area. Typical face recognition algorithms used fixed parameter filtering algorithms to optimize face images for the recognition process. A fixed filtering scheme introduces errors when applied to face images captured in various different environmental conditions. For acquiring face image of good quality from the image including complex background and illumination, we propose a method for image enhancement using the categories based on the image intensity values. When an image is acquired average values of image from sub-window are computed and then compared to training values that were computed during preprocessing. The category is selected and the most suitable image filter method is applied to the image. We used histogram equalization, and gamma correction filters with two different parameters, and then used the most suitable filter among those three. An increase in enrollment of filtered images was observed compared to enrollment rates of the original images.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2004.08a
• /
• pp.432-435
• /
• 2004

The skin color of a human being is the important memory color influencing image quality for color display. Therefore, in this paper, the preferred skin color axis is defined on HSV color space by analyzing some previous research, and the preferred skin color reproduction algorithm is performed by rotating the center axis of skin distribution of an input image to the preferred skin color axis.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.2
• /
• pp.245-249
• /
• 2007

In this paper describes image enhancement technique using deconvolution processing for ultrasonic nondestructive testing. When flaws are detected fur B-scan or C-scan, blurring effect which is caused by the moving intervals of transducer degrades the quality of images. In addition, acquisited images suffer form speckle noise which is caused by the ultrasonic components reflected from the grain boundary of material (1,2). The deconvolution technique can restore sharp peak value or clean image from blurring signal or image. This processing is applied to C-scan image obtained from known specimen. Experimental results show that the deconvolution processing contributes to get improved the quality of C-scan images.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.115-118
• /
• 2004

Images with high resolution are desired and often required in many visual applications. When resolution can not be improved by replacing sensors, either because of cost or hardware physical limits, super resolution image reconstruction method is what can be resorted to. Super resolution image reconstruction method refers to image processing algorithms that produce high quality and high resolution images from a set of low quality and low resolution images. The method is proved to be useful in many practical cases where multiple frames of the same scene can be obtained, including satellite imaging, video surveillance, video enhancement and restoration, digital mosaicking, and medical imaging. The method can be either the frequency domain approach or the spatial domain approach. Much of the earlier works concentrated on the frequency domain formulation, but as more general degradation models were considered, later researches had been almost exclusively on spatial domain formulations. The method in spatial domains has three stages: i) motion estimate or image registration, ii) interpolation onto high resolution grid and iii) deblurring process. The super resolution grid construction in the second stage was discussed in this paper. We applied the Maximum A­Posteriori(MAP) reconstruction method that is one of the major methods in the super resolution grid construction. Based on this method, we reconstructed high resolution images from a set of low resolution images and compared the results with those from other known interpolation methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.5095-5111
• /
• 2019

A multi-rotor Unmanned Aerial Vehicle (UAV) system is developed to solve the manhole cover detection problem for the infrastructure maintenance in the suburbs of big city. The visible light sensor is employed to collect the ground image data and a series of image processing and machine learning methods are used to detect the manhole cover. First, the image enhancement technique is employed to improve the imaging effect of visible light camera. An imaging environment perception method is used to increase the computation robustness: the blind Image Quality Evaluation Metrics (IQEMs) are used to percept the imaging environment and select the images which have a high imaging definition for the following computation. Because of its excellent processing effect the adaptive Multiple Scale Retinex (MSR) is used to enhance the imaging quality. Second, the Single Shot multi-box Detector (SSD) method is utilized to identify the manhole cover for its stable processing effect. Third, the spatial coordinate of manhole cover is also estimated from the ground image. The practical applications have verified the outdoor environment adaptability of proposed algorithm and the target detection correctness of proposed system. The detection accuracy can reach 99% and the positioning accuracy is about 0.7 meters.

• Proceedings of the KIPE Conference
• /
• 2002.11a
• /
• pp.186-189
• /
• 2002

Real-time thermal image is obtained by thermal imaging systems measuring radiant emittence according to law of Plank's blackbody radiation. The histogram of thermal image is not uniform. The signal bands of background and target are separated and grouped in narrow bands. In such a system, contrast enhancement indispensible to distinguish target from background. In this study, plateau histogram equalization using local histogram is proposed for contrast enhancement.