• Proceedings of the KSR Conference
• /
• 2003.10c
• /
• pp.653-658
• /
• 2003

This study is represented a method to give connect to optical cable from accident site and reviewed the method to transmission a moving image to control centre by real time, following the study of image transmission method in copper cable section where is a main line of railroad communication. Concept of network is studied to use cable and equipment effectively, and it's also reviewed technology of digital image transmission system and image evaluation methods, in spite of the pixel of camera and monitor resolution determine quality of image when moving image transferring by point to point. In addition, this study is reviewed checks and considerations of image transmission equipment (codec) with various transmission methods in room test, and then examined and analyzed wire/wireless combined transmission methods at wayside.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.5
• /
• pp.411-414
• /
• 2010

As high quality image is required for digital cameras in recent use, the image stabilization technique has drawn much attention to prevent image degradation from shaky disturbance by users. In this paper, the optical image stabilization (OIS) system for DSLR (Digital Single Lens Reflex) camera is considered. First, the analytic model of an OIS system is presented to demonstrate the mechanism of image destabilization due to unknown disturbance that causes blurry images on CCD sensor. Then, to enhance the stabilization performance, a sliding mode control based on the min-max nonlinear control is introduced. Through the experiments and simulations, the effectiveness of the proposed method will be verified.

• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.835-838
• /
• 2000

Popular methods for extracting a text region in video images are in general based on analysis of a whole image such as merge and split method, and comparison of two frames. Thus, they take long computing time due to the use of a whole image. Therefore, this paper suggests the faster method of extracting a text region without processing a whole image. The proposed method uses line sampling methods, FFT and neural networks in order to extract texts in real time. In general, text areas are found in the higher frequency domain, thus, can be characterized using FFT The candidate text areas can be thus found by applying the higher frequency characteristics to neural network. Therefore, the final text area is extracted by verifying the candidate areas. Experimental results show a perfect candidate extraction rate and about 92% text extraction rate. The strength of the proposed algorithm is its simplicity, real-time processing by not processing the entire image, and fast skipping of the images that do not contain a text.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.37 no.4
• /
• pp.240-250
• /
• 1988

This pc-vision system digitizes/displays 512*512*8 bit pixel image in real time and is capable of the various image processing. This system provides a versatile solution to those users pursuing high performance image processing system compatible with the VME bus, and is general purpose imaging system giving the optimal efficiency for machine vision, medical use and various task. In this paper, Image processing technique has classified image enhancement and image analysis in order to design and implement the pc-vision system. In order to improve processing speed, This system unilizing ROI processing performs point operation, local operation and global operation as well as common arithmetic/logic operation in real time.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1998.05a
• /
• pp.351-358
• /
• 1998

This paper deals with the underwater image transmission system which includes in AUV(Autonomous Underwater Vehicle) Project(that is VORAM(Vehicle for Ocean Research And Monitoring)), developed by KIMM for survey and investigation of a sea-bed through transmitting the underwater image to the mother ship. The system presented in this paper consists of a transducer which has a 136KHz center frequency and it's 10KHz bandwidth, pre-amplifier, $\pi$/4 QPSK(Quadreature Phase Shift Keying) modulation/demodulation method, image compressing method using JPEG technique and modified Stop & protocol. The experimental results of the system is verified to a high performance with 9600 bps for transmitting the underwater image through the basin test. The results of test are also verified which allows to desirable transmission performance compared with the existing developed system and the possibility to put the practical use of survey and investigation. And, the viterbi coding and adaptive equalizer for cancelling the multipath effect are developing for more effective image transmission system. Also, these technique will very effectively adapt to realtime image transmission system.

• The KIPS Transactions:PartB
• /
• v.10B no.1
• /
• pp.73-80
• /
• 2003

In this paper we propose an algorithm which matches the corresponding feature points between the reference image and the search image. We use Harris's corner detector to find the feature points in both image. For each feature point in the reference image, we can extract the candidate matching points as feature points in the starch image which the normalized correlation coefficient goes greater than a threshold. Finally we determine a corresponding feature points among candidate points by using dynamic programming. In experiments we show results that match feature points in synthetic image and real image.

• Journal of Sensor Science and Technology
• /
• v.30 no.5
• /
• pp.286-289
• /
• 2021

Image classification is one of the fundamental applications of computer vision. It enables a system to identify an object in an image. Recently, image classification applications have broadened their scope from computer applications to edge devices. The convolutional neural network (CNN) is the main class of deep learning neural networks that are widely used in computer tasks, and it delivers high accuracy. However, CNN algorithms use a large number of parameters and incur high computational costs, which hinder their implementation in edge hardware devices. To address this issue, this paper proposes a lightweight image classifier that provides good accuracy while using fewer parameters. The proposed image classifier diverts the input into three paths and utilizes different scales of receptive fields to extract more feature maps while using fewer parameters at the time of training. This results in the development of a model of small size. This model is tested on the CIFAR-10 dataset and achieves an accuracy of 90% using .26M parameters. This is better than the state-of-the-art models, and it can be implemented on edge devices.

• The Research Journal of the Costume Culture
• /
• v.21 no.4
• /
• pp.546-561
• /
• 2013

This study investigated how consumers perceive brand image, the consistency between the images of parent brands and extended brands, the consistency of their advertising images, the differences between brand image and advertising image, and how consumers' brand attitudes change based on those differences. An online survey was administered to women in their 20s and 30s who often use cosmetics and are interested in brands. The brands considered in this research were Chanel, Dior, Armani, and Anna Sui, which have extended brands in the clothing and cosmetics areas. In terms of consumers' perception of brand image, it was found that clothing and cosmetic brands were perceived similarly. In addition, significant differences were found in consumers' preferences and purchase intentions of clothing and cosmetic brands, and those whose perceptions of brand image did not change or increased after looking at advertising images had more positive brand attitudes than the group of people who had higher perception of brand image before looking at advertising images. Therefore, in terms of brand extension, it was revealed that the image of a parent brand affected an extended brand, and that the higher was consumers' recognition of brand image through advertising, the more positive was their attitude toward the brand.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.2
• /
• pp.117-137
• /
• 2010

Iris recognition is a biometric technique which uses unique iris patterns between the pupil and sclera. The advantage of iris recognition lies in high recognition accuracy; however, for good performance, it requires the diameter of the iris to be greater than 200 pixels in an input image. So, a conventional iris system uses a camera with a costly and bulky zoom lens. To overcome this problem, we propose a new method to restore a low resolution iris image into a high resolution image using a single image. This study has three novelties compared to previous works: (i) To obtain a high resolution iris image, we only use a single iris image. This can solve the problems of conventional restoration methods with multiple images, which need considerable processing time for image capturing and registration. (ii) By using bilinear interpolation and a constrained least squares (CLS) filter based on the degradation model, we obtain a high resolution iris image with high recognition performance at fast speed. (iii) We select the optimized parameters of the CLS filter and degradation model according to the zoom factor of the image in terms of recognition accuracy. Experimental results showed that the accuracy of iris recognition was enhanced using the proposed method.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.561-566
• /
• 2023

With the development of deep learning, it is possible to solve various computer non-specialized problems such as image processing. However, most image processing methods use only the visual information of the image to process the image. Text data such as descriptions and annotations related to images may provide additional tactile and visual information that is difficult to obtain from the image itself. In this paper, we intend to improve image classification accuracy through a deep learning model that analyzes images and texts using image-text pairs. The proposed model showed an approximately 11% classification accuracy improvement over the deep learning model using only image information.