• Journal of Sensor Science and Technology
• /
• v.15 no.5
• /
• pp.341-346
• /
• 2006

We have fabricated SOI CMOS active pixel image sensor with the pinned photodiode on handle wafer in order to reduce dark currents and improve spectral response. The structure of the active pixel image sensor is 4 transistors APS which consists of a reset and source follower transistor on seed wafer, and is comprised of the photodiode, transfer gate, and floating diffusion on handle wafer. The source of dark current caused by the interface traps located on the surface of a photodiode is able to be eliminated, as we apply the pinned photodiode. The source of dark currents between shallow trench isolation and the depletion region of a photodiode can be also eliminated by the planner process of the hybrid bulk/SOI structure. The photodiode could be optimized for better spectral response because the process of a photodiode on handle wafer is independent of that of transistors on seed wafer. The dark current was about 6 pA at 3.3 V of floating diffusion voltage in the case of transfer gate TX = 0 V and TX=3.3 V, respectively. The spectral response of the pinned photodiode was observed flat in the wavelength range from green to red.

• 전자공학회논문지 IE
• /
• v.44 no.1
• /
• pp.15-19
• /
• 2007

A study to have read does an improvement of an error restoration technology based on the edge direction interpolation that a stop image cared for inside frame correction more than with an image restoration way of a transfer error or with an aim. A way proposed to is based on edge direction detection method of a block utilizing the edge direction which will adjust a part damaged a sweater to a remaining part here. The rest of error pixel used non linear Midian filter for process later data information by the final stage and did interpolation. The examination result shows a good recuperation tendency and low accounts time of a way proposed to realization possibility of a real time image processing.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.27 no.1
• /
• pp.56-74
• /
• 2023

In order to obtain practical and high-quality satellite images containing high-frequency components, a large aperture optical system is required, which has a limitation in that it greatly increases the payload weight. As an attempt to overcome the problem, many multi-aperture optical systems have been proposed, but in many cases, these optical systems do not include high-frequency components in all directions, and making such an high-quality image is an ill-posed problem. In this paper, we use deep learning to overcome the limitation. A deep learning model receives low-quality images as input, estimates the Point Spread Function, PSF, and combines them to output a single high-quality image. We model images obtained from three rectangular apertures arranged in a regular polygon shape. We also propose the Modulation Transfer Function Loss, MTF Loss, which can capture the high-frequency components of the images. We present qualitative and quantitative results obtained through experiments.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.36 no.8
• /
• pp.828-836
• /
• 2012

This study provided the data for the planning of knit apparel by analyzing structural effects of intarsia and jacquard knit on mechanical properties, subjective hand measurements, and preference. Intarsia and 7 types of color jacquard (floating jacquard, normal jacquard, bird's eye jacquard, tubular jacquard, ladder's back jacquard, blister jacquard, and transfer jacquard) were used. The samples (with a gauge of 14) were knitted using 100% wool 2/48's yarn by a Shima Seiki SIG computer knitting machine. Mechanical properties and hand values were measured by a KES-FB system. Subjective hand and favorable images were surveyed based on women in their 20s and 30s. The data were analyzed by a factor analysis, ANOVA and correlation analysis using SPSS 12.0. The subjective hand of intarsia and jacquard knits was categorized into 'thermofeeling', 'weight/flexibility', and 'durability'. The results of the favorable image survey for F/W outer knitwear showed that tubular jacquard was most favorable; however, the transfer jacquard was least favorable. Among the three factors that explain the subjective hand, thermofeeling had a strong influence on the favorable image of consumers. Bird's eye jacquard and tubular jacquard turned out to be most suitable for suits, intarsia and floating jacquard were suitable for cardigans and sweaters, ladder's back jacquard was suitable for hats or mufflers, and transfer jacquard was suitable for home fashion rather than garments.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.489-491
• /
• 2002

The need for video diagnosis in medicine has been increased and real-time transfer of digital video will be an important component in PACS and telemedicine. But, Network environment has certain limitations that the required throughput can not satisfy quality of service (QoS). MPEG-4 ratified as a moving video standard by the ISO/IEC provides very efficient video coding covering the various ranges of low bit-rate in network environment. We implemented MPEG-4 CODEC (coder/decoder) and applied various compression ratios to moving ultrasound images. These images were displayed in random order on a client monitor passed through network. Radiologists determined subjective opinion scores for evaluating clinically acceptable image quality and then these were statistically processed in the t-Test method. Moreover the MPEG-4 decoded images were quantitatively analyzed by computing peak signal-to-noise ratio (PSNR) to objectively evaluate image quality. The bit-rate to maintain clinically acceptable image quality was up to 0.8Mbps. We successfully implemented the adaptive throughput or bit-rate relative to the image quality of ultrasound sequences used MPEG-4 that can be applied for diagnostic performance in real-time.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.1
• /
• pp.34-41
• /
• 2023

In recent years, as the range of human activities has increased, the introduction of alien species has become frequent. Among them, raccoons have been designated as harmful animals since 2020. Raccoons are similar in size and shape to raccoon dogs, so they generally need to be distinguished in capturing them. To solve this problem, we use VGG19, ResNet152V2, InceptionV3, InceptionResNet and NASNet, which are CNN deep learning models specialized for image classification. The parameters to be used for learning are pre-trained with a large amount of data, ImageNet. In order to classify the raccoon and raccoon dog datasets as outward features of animals, the image was converted to grayscale and brightness was normalized. Augmentation methods were applied using left and right inversion, rotation, scaling, and shift to create sufficient data for transfer learning. The FCL consists of 1 layer for the non-augmented dataset while 4 layers for the augmented dataset. Comparing the accuracy of various augmented datasets, the performance increased as more augmentation methods were applied.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.290-306
• /
• 2024

To treat the novel COronaVIrus Disease (COVID), comparatively fewer medicines have been approved. Due to the global pandemic status of COVID, several medicines are being developed to treat patients. The modern COVID medicines development process has various challenges, including predicting and detecting hazardous COVID medicine responses. Moreover, correctly predicting harmful COVID medicine reactions is essential for health safety. Significant developments in computational models in medicine development can make it possible to identify adverse COVID medicine reactions. Since the beginning of the COVID pandemic, there has been significant demand for developing COVID medicines. Therefore, this paper presents the transferlearning methodology and a multilabel convolutional neural network for COVID (MLCNN-COV) medicines development model to identify negative responses of COVID medicines. For analysis, a framework is proposed with five multilabel transfer-learning models, namely, MobileNetv2, ResNet50, VGG19, DenseNet201, and Inceptionv3, and an MLCNN-COV model is designed with an image augmentation (IA) technique and validated through experiments on the image of three-dimensional chemical conformer of 17 number of COVID medicines. The RGB color channel is utilized to represent the feature of the image, and image features are extracted by employing the Convolution2D and MaxPooling2D layer. The findings of the current MLCNN-COV are promising, and it can identify individual adverse reactions of medicines, with the accuracy ranging from 88.24% to 100%, which outperformed the transfer-learning model's performance. It shows that three-dimensional conformers adequately identify negative COVID medicine responses.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.215-218
• /
• 2013

In this paper, we proposed a method for enhancement of color images with sky regions. The input image is converted into HSV space and then sky and non-sky regions are separated. For sky region, saturation enhancement is performed for each pixel based on the enhancement factor calculated from the average saturation of its local neighborhood. On the other hand, for the non-sky region, the enhancement is applied only on the luminance value (V) component of the HSV color image, which is performed in two steps. The luminance enhancement, which is also called as dynamic range compression, is carried out using nonlinear transfer function. Again, each pixel is further enhanced for the adjustment of the image contrast depending upon the center pixel and its neighborhood pixel values. At last, the original H and V component image and enhanced S component image for the sky region, and original H and S component image and enhanced V component image for the non-sky region are converted back to RGB image.

• Journal of Korea Multimedia Society
• /
• v.21 no.10
• /
• pp.1195-1202
• /
• 2018

Artificial neural network is widely used for its excellent performance and implementability. However, traditional neural network needs to learn the system from scratch, with the addition of new input data, the variation of the observation environment, or the change in the form of input/output data. To resolve such a problem, the technique of transfer learning has been proposed. Transfer learning constructs a newly developed target system partially updating existing system and hence provides much more efficient learning process. Until now, transfer learning is mainly studied in the field of image processing and is not yet widely employed in acoustic data processing. In this paper, focusing on the scalability of transfer learning, we apply the concept of transfer learning to the problem of guitar chord classification and evaluate its performance. For this purpose, we build a target system of convolutional neutral network (CNN) based 48 guitar chords classification system by applying the concept of transfer learning to a source system of CNN based 24 guitar chords classification system. We show that the system with transfer learning has performance similar to that of conventional system, but it requires only half the learning time.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2000.04a
• /
• pp.133-137
• /
• 2000

In this paper, We study on converting data transfer using Image processing method. In the program's code consist of outline trace, noise filtering methode, pont data smoothing, algorithm. We use those Algorithm to create Vectorized data file format from image data. This result can be utilized as a base part for development of Automatic recognition for mechanical drawings.