• Journal of information and communication convergence engineering
• /
• v.13 no.4
• /
• pp.275-279
• /
• 2015

There are several methods to record three dimensional (3D) information of objects such as lens array based integral imaging, synthetic aperture integral imaging (SAII), computer synthesized integral imaging (CSII), axially distributed image sensing (ADS), and axially distributed stereo image sensing (ADSS). ADSS method is capable of recording partially occluded 3D objects and reconstructing high-resolution slice plane images. In this paper, we present a computational method for depth extraction of partially occluded 3D objects using ADSS. In the proposed method, the high resolution elemental stereo image pairs are recorded by simply moving the stereo camera along the optical axis and the recorded elemental image pairs are used to reconstruct 3D slice images using the computational reconstruction algorithm. To extract depth information of partially occluded 3D object, we utilize the edge enhancement and simple block matching algorithm between two reconstructed slice image pair. To demonstrate the proposed method, we carry out the preliminary experiments and the results are presented.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.48 no.9
• /
• pp.22-30
• /
• 2011

Recently, the rising demand for intelligent video surveillance system leads to high-performance face recognition systems. The solution for low-resolution images acquired by a long-distance camera is required to overcome the distance limits of the existing face recognition systems. For that reason, this paper proposes a hardware design of an image resolution enhancement algorithm for real-time intelligent video surveillance systems. The algorithm is synthesizing a high-resolution face image from an input low-resolution image, with the help of a large collection of other high-resolution face images, called training set. When we checked the performance of the algorithm at 32bit RISC micro-processor, the entire operation took about 25 sec, which is inappropriate for real-time target applications. Based on the result, we implemented the hardware module and verified it using Xilinx Virtex-4 and ARM9-based embedded processor(S3C2440A). The designed hardware can complete the whole operation within 33 msec, so it can deal with 30 frames per second. We expect that the proposed hardware could be one of the solutions not only for real-time processing at the embedded environment, but also for an easy integration with existing face recognition system.

• Phonetics and Speech Sciences
• /
• v.10 no.1
• /
• pp.33-38
• /
• 2018

Although deep neural network-based acoustic models have greatly improved the performance of automatic speech recognition (ASR), reverberation still degrades the performance of distant speech recognition in indoor environments. In this paper, we adopt the DenseNet, which has shown great performance results in image classification tasks, to improve the performance of reverberant speech recognition. The DenseNet enables the deep convolutional neural network (CNN) to be effectively trained by concatenating feature maps in each convolutional layer. In addition, we extend the concept of multi-resolution CNN to multi-resolution DenseNet for robust speech recognition in reverberant environments. We evaluate the performance of reverberant speech recognition on the single-channel ASR task in reverberant voice enhancement and recognition benchmark (REVERB) challenge 2014. According to the experimental results, the DenseNet-based acoustic models show better performance than do the conventional CNN-based ones, and the multi-resolution DenseNet provides additional performance improvement.

• Journal of information and communication convergence engineering
• /
• v.14 no.1
• /
• pp.57-63
• /
• 2016

In generally, the resolution of reconstructed three-dimensional images can be seriously degraded by undesired occlusions in the integral imaging system, because the undesired information of the occlusion overlap the three-dimensional images to be reconstructed. To solve the problem of the undesired occlusion, we present an exemplar-based image restoration method in integral imaging system. In the proposed method, a minimum spanning tree-based stereo matching method is used to remove the region of undesired occlusions in each elemental image. After that, the removed occlusion region of each elemental images are re-established by using the exemplar-based image restoration method. For further improve the performance of the image restoration, the structure tensor is used to solve the filling error cause by discontinuous structures. Finally, the resolution enhanced three-dimensional images are reconstructed by using the restored elemental images. The preliminary experiments are presented to demonstrate the feasibility of the proposed method.

• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.158-168
• /
• 2024

There is hardly any person in modern times who has not taken soft drinks instead of drinking water. The rate of people taking soft drinks being surprisingly high, researchers around the world have cautioned from time to time that these drinks lead to weight gain, raise the risk of non-communicable diseases and so on. Therefore, in this work an image-based tool is developed to monitor the nutritional information of soft drinks by using deep convolutional neural network with transfer learning. At first, visual saliency, mean shift segmentation, thresholding and noise reduction technique, collectively known as 'pre-processing' are adopted to extract the location of drinks region. After removing backgrounds and segment out only the desired area from image, we impose Discrete Wavelength Transform (DWT) based resolution enhancement technique is applied to improve the quality of image. After that, transfer learning model is employed for the classification of drinks. Finally, nutrition value of each drink is estimated using Bag-of-Feature (BoF) based classification and Euclidean distance-based ratio calculation technique. To achieve this, a dataset is built with ten most consumed soft drinks in Bangladesh. These images were collected from imageNet dataset as well as internet and proposed method confirms that it has the ability to detect and recognize different types of drinks with an accuracy of 98.51%.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.30-35
• /
• 2010

This paper presents a quality enhancement of images by using a histogram equalization based on the symmetric logistic function. The histogram equalization is a simple and effective spatial processing method that it enhances the quality by adjusting the brightness of image. The logistic function that is a sigmoidal nonlinear transformation function, is applied to non-linearly enhance the brightness of the image according to its intensity level frequency. We propose a flexible and symmetrical logistic function by only using the intensity with maximum frequency in an histogram and the total number of pixels. The proposed function decreases the computation load of an exponential function in the traditional logistic function. The proposed method has been applied for equalizing 5 images with a different resolution and histogram distribution. The experimental results show that the proposed method has the superior enhancement performances compared with the source images and the traditional global histogram equalization, respectively.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.237-240
• /
• 2004

In this study, the digital image processing with image enhancement based on homomorphic filtering was performed using geophysical imaging data such as gravity, magnetic data and sub-scenes of satellite images such as LANDSAT, IKONOS, and KOMPSAT. Windows application program for executing homomorphic filtering was designed and newly implemented. In general, homomorphic filtering is technique that is based on Fourier transform, which enhances the contrast of image by removing the low frequencies and amplifying the high frequencies in frequency domain. We can enhance the image selectively using homomorphic filtering as compared with the existing method, which enhance the image totally. Through several experiment using remotely sensed imagery and geophysical image with this program, it is concluded that homomorphic filtering is more effective to reveal distinct characteristics for some complicated and multi-associated features on image data.

• Progress in Medical Physics
• /
• v.19 no.3
• /
• pp.150-156
• /
• 2008

An applied technique of contrast enhancement for X-ray image is proposed which is based on combined enhancement of scaling and wavelet coefficients in discrete wavelet transform space. Conventional contrast enhancement methods such as contrast limited adaptive histogram equalization (CLAHE), multi-scale image contrast amplification (MUSICA) and gamma correction were applied on scaling coefficients to enhance the contrast of an original. In order to enhance the detail as well as reduce the blurring caused by up scaling of contrast modified scale coefficients from lower resolution, the sigmoid manipulation function was used to manipulate wavelet coefficients. The contrast detail mammography (CDMAM) phantom was imaged and processed to measure the image line profile of results and contrast to noise ratio (CNR) comparatively. The proposed technique produced better results than direct application of various contrast enhancement methods on image itself. The proposed method can enhance contrast, and also suppress the amplification of noise components in a single process. It could be useful for various applications in medical, industrial and graphical images where contrast and detail are of importance.

• Journal of Digital Policy
• /
• v.3 no.1
• /
• pp.27-32
• /
• 2024

In this paper, proposes a super resolution method that enhances the quality of results by refining texture features, contrasting each, and utilizing the results as weights. For the improvement of quality, a precise and clear restoration result in details such as boundary areas is crucial in super resolution, along with minimizing unnecessary artifacts like noise. The proposed method constructs a residual block structure with multiple paths and skip-connections for feature estimation in conventional Convolutional Neural Network (CNN)-based super resolution methods to enhance quality. Additional learning is performed for sharpened and blurred image results for further texture analysis. By contrasting each super resolution result and allocating weights through this process, the proposed method achieves improved quality in detailed and smoothed areas of the image. The experimental results of the proposed method, evaluated using the PSNR and SSIM values as quality metrics, show higher results compared to existing algorithms, confirming the enhancement in quality.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.11-19
• /
• 2023

In this paper, it is confirmed that the metrics used to evaluate image quality can be applied to low-light images. Due to the nature of low-illumination images, factors related to light create various noise patterns, and the smaller the amount of light, the more severe the noise. Therefore, in situations where it is difficult to obtain a clean image without noise, the quality of a low-illuminance image from which noise has been removed is often judged by the human eye. In this paper, noise in low-illuminance images for which ground truth cannot be obtained is removed using Noise2Noise, and spatial resolution and radial resolution are evaluated using ISO 12233 charts and colorchecker as metrics such as MTF and SNR. It can be shown that the quality of the low-illuminance image, which has been evaluated mainly for qualitative evaluation, can also be evaluated quantitatively.