• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.12
• /
• pp.2527-2533
• /
• 2011

In this paper we propose a new pre-processing algorithm applied to multi-view video coding using color compensation algorithm based on image features. Multi-view images have a difference between neighboring frames according to illumination and different camera characteristics. To compensate this color difference, first we model the characteristics of cameras based on frame's feature from each camera and then correct the color difference. To extract corresponding features from each frame, we use Harris corner detection algorithm and characteristic coefficients used in the model is estimated by using Gauss-Newton algorithm. In this algorithm, we compensate RGB components of target images, separately from the reference image. The experimental results with many test images show that the proposed algorithm peformed better than the histogram based algorithm as much as 14 % of bit reduction and 0.5 dB ~ 0.8dB of PSNR enhancement.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.83-90
• /
• 2023

Blurred image is an important factor in lowering image recognition rates in Computer vision. This mainly occurs when the camera is unstablely out of focus or the object in the scene moves quickly during the exposure time. Blurred images greatly degrade visual quality, weakening visibility, and this phenomenon occurs frequently despite the continuous development digital camera technology. In this paper, it replace the modified building module based on the Deep multi-patch neural network designed with convolution neural networks to capture details of input images and Attention techniques to focus on objects in blurred images in many ways and strengthen the image. It measures and assigns each weight at different scales to differentiate the blurring of change and restores from rough to fine levels of the image to adjust both global and local region sequentially. Through this method, it show excellent results that recover degraded image quality, extract efficient object detection and features, and complement color constancy.

• The KIPS Transactions:PartB
• /
• v.14B no.3 s.113
• /
• pp.145-152
• /
• 2007

In this paper, we propose an automatic extraction model for unknown translations and implement an unknown translation extraction system using the proposed model. The proposed model as a phrase-alignment model is incorporated with three models: a phrase-boundary model, a language model, and a translation model. Using the proposed model we implement the system for extracting unknown translations, which consists of three parts: construction of parallel corpora, alignment of Korean and English words, extraction of unknown translations. To evaluate the performance of the proposed system, we have established the reference corpus for extracting unknown translation, which comprises of 2,220 parallel sentences including about 1,500 unknown translations. Through several experiments, we have observed that the proposed model is very useful for extracting unknown translations. In the future, researches on objective evaluation and establishment of parallel corpora with good quality should be performed and studies on improving the performance of unknown translation extraction should be kept up.

• Journal of Broadcast Engineering
• /
• v.22 no.5
• /
• pp.608-617
• /
• 2017

Methods of contrast enhancement have problem such as side effect of over-enhancement with non-gaussian histogram distribution, tradeoff enhancement efficiency against brightness preserving. In order to enhance contrast at various histogram distribution, segmentation to region with gaussian distribution and then enhance contrast each region. First, we segment an image into several regions using GMM(Gaussian Mixture Model)fitting by that k-mean clustering and EM(Expectation-Maximization) in $L^*a^*b^*$ color space. As a result region segmentation, we get the region map and probability map. Then we apply local contrast enhancement algorithm that mean shift to minimum overlapping of each region and preserve brightness histogram equalization. Experiment result show that proposed region based contrast enhancement method compare to the conventional method as AMBE(AbsoluteMean Brightness Error) and AE(Average Entropy), brightness is maintained and represented detail information.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.38 no.8
• /
• pp.62-71
• /
• 2001

This paper presents a design of the real-time digital image enhancement preprocessor for CMOS image sensor. CMOS image sensor offers various advantages while it provides lower-quality images than CCD does. In order to compensate for the physical limitation of CMOS sensor, the spatially adaptive contrast enhancement algorithm was incorporated into the preprocessor with color interpolation, gamma correction, and automatic exposure control. The efficient hardware architecture for the preprocessor is proposed and was simulated in VHDL. It is composed of about 19K logic gates, which is suitable for low-cost one-chip PC camera. The test system was implemented on Altera Flex EPF10KGC503-3 FPGA chip in real-time mode, and performed successfully.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2006.08a
• /
• pp.286-289
• /
• 2006

Temporal dual gamma drive technology employing the 120Hz refresh rate was developed to enhance the off-axis viewing quality in patterned vertical alignment mode. The color shift ${\Delta}u'v'$ from on-axis to off-axis (60 deg.) for pale orange color, (R,G,B) = (196,124,96), was below 0.01, and the power exponent of gamma curve for off-axis viewing angle (60 deg.) was about 1.8, when the gamma curve for on-axis was set with power exponent of 2.4. The off-axis image distortion index was below 0.180 in contrast to the normal case ${\sim}0.23$. To elevate the response speed of liquid crystal in the intra-frame, the voltage below threshold voltage of liquid crystals was used.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.5
• /
• pp.313-322
• /
• 2020

A large volume of data will improve the robustness of deep learning models and avoid overfitting problems. In automatic tongue segmentation, the availability of annotated tongue images is often limited because of the difficulty of collecting and labeling the tongue image datasets in reality. Data augmentation can expand the training dataset and increase the diversity of training data by using label-preserving transformations without collecting new data. In this paper, augmented tongue image datasets were developed using seven augmentation techniques such as image cropping, rotation, flipping, color transformations. Performance of the data augmentation techniques were studied using state-of-the-art transfer learning models, for instance, InceptionV3, EfficientNet, ResNet, DenseNet and etc. Our results show that geometric transformations can lead to more performance gains than color transformations and the segmentation accuracy can be increased by 5% to 20% compared with no augmentation. Furthermore, a random linear combination of geometric and color transformations augmentation dataset gives the superior segmentation performance than all other datasets and results in a better accuracy of 94.98% with InceptionV3 models.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.5
• /
• pp.263-272
• /
• 2008

The proposed system can achieve more safety of RFID system with the 2-step authentication procedures for the enhancement about the security of general RFID systems. After it has authenticated RFID tag, additionally, the proposed system extract the characteristic information in the user image for acquisition of the additional authentication information of the user with the camera. In this paper, the system which was proposed more enforce the security of the automatic entrance and exit authentication system with the cognitive characters of RFID tag and the extracted characteristic information of the user image through the camera. The RFID system which use the active tag and reader with 2.4GHz bandwidth can recognize the tag of RFID in the various output manner. Additionally, when the RFID system have errors. the characteristic information of the user image is designed to replace the RFID system as it compare with the similarity of the color, outline and input image information which was recorded to the database previously. In the experimental result, the system can acquire more exact results as compared with the single authentication system when it using RFID tag and the information of color characteristics.

• Journal of Broadcast Engineering
• /
• v.16 no.4
• /
• pp.584-595
• /
• 2011

Recently, RGB images and depth maps have been supplied to academic fields. The depth maps are utilized to the generation of stereoscopic images in the diverse formats according to the users' preference. A variety of methods that use depth maps have been introduced so far. One of applications is a medical field. In this area, the improvement of the perceptual quality of 2D medical images has gained much interest. In this paper, we propose a novel scheme that expands the conventional method to 3D stereoscopic image, thereby achieving the perceptual depth quality improvement as well as 3D stereoscopic perception enhancement at the same time. For this, contrast transformation as well as depth darkening are proposed and their performance is validated through the subjective test. Subjective experiments peformed for stereoscopic enhancement as well as visual fatigue validate that the proposed method achieves better 3D perception than the usage of the original stereoscopic image and suggests the limitation in terms of the visual fatigue.

• Journal of Korean Neurosurgical Society
• /
• v.59 no.6
• /
• pp.584-589
• /
• 2016

Objective : A rare subtype of meningioma, sclerosing meningioma is not included in the current World Health Organization classification of meningiomas and is classified into the category of other morphological variation subtypes. Sclerosing meningioma is often misdiagnosed to other non-benign meningioma or malignant neoplasm, so it is important to diagnose sclerosing type correctly. We analyzed the radiological and clinical characteristics of a series of sclerosing meningiomas. Methods : Twenty-one patients who underwent surgery in one institute with a histopathologically proven sclerosing meningioma were included from 2006 to 2014. Eighteen tumors were diagnosed as a pure sclerosing-type meningioma, and 3 as mixed type. Magnetic resonance image was taken for all patients including contrast enhancement image. Computed tomography (CT) scan was taken for 16 patients. One neuroradiologist and 1 neurosurgeon reviewed all images retrospectively. Results : In the all 16 patients with preoperative CT images, higher attenuation was observed in the meningioma than in the brain parenchyma, and calcification was observed in 11 (69%). In 15 of the 21 patients (71%), a distinctive very low signal intensity appeared as a dark color in T2-weighted images. Nine of these 15 tumors (60%) exhibited heterogeneous enhancement, and 6 (40%) exhibited homogeneous enhancement that was unlike the homogeneous enhancing pattern shown by conventional meningiomas. Ten patients had a clear tumor margin without peritumoral edema. Conclusion : Although these peculiar radiological characteristics are not unique to sclerosing meningioma, we believe that they are distinctive features that may be helpful for distinguishing sclerosing meningioma from other subtypes.