• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.7-13
• /
• 2021

Machine vision is a technology that helps the computer as if a person recognizes and determines things. In recent years, as advanced technologies such as optical systems, artificial intelligence and big data advanced in conventional machine vision system became more accurate quality inspection and it increases the manufacturing efficiency. In machine vision systems using deep learning, the image quality of the input image is very important. However, most images obtained in the industrial field for quality inspection typically contain noise. This noise is a major factor in the performance of the machine vision system. Therefore, in order to improve the performance of the machine vision system, it is necessary to eliminate the noise of the image. There are lots of research being done to remove noise from the image. In this paper, we propose an autoencoder based machine vision system to eliminate noise in the image. Through experiment proposed model showed better performance compared to the basic autoencoder model in denoising and image reconstruction capability for MNIST and fashion MNIST data sets.

• The Research Journal of the Costume Culture
• /
• v.17 no.3
• /
• pp.459-471
• /
• 2009

The purpose of the study is to examine the effect of VMD image appropriateness in apparel shopping contexts. Two competing models are utilized. The first model is developed from the emotion-cognition theory which explains that environmental cues(i.e., VMD image appropriateness) generate consumers' emotion, and in turn, consumers' behaviors. The second model is developed based on the cognitive theory of emotions and posits that environmental cues stimulates consumers' cognitive perceptions of retail environments, subsequently influencing consumers' emotional and behavioral response. A 2(VMD image appropriateness: high vs. low) between-subjects factorial design experiment was conducted. Female college students(n=592) participated in the experiment. Using structural equation modeling the study found that the emotion-cognition model better explains the effect of VMD image appropriateness on consumers' emotional, cognitive, and behavioral responses.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.2
• /
• pp.104-110
• /
• 2016

Dense local image descriptors like SIFT are fruitful for capturing salient information about image, shown to be successful in various image-related tasks when formed in bag-of-words representation (i.e., histograms). In this paper we consider to utilize these dense local descriptors in the object tracking problem. A notable aspect of our tracker is that instead of adopting a point estimate for the target model, we account for uncertainty in data noise and model incompleteness by maintaining a distribution over plausible candidate models within the Bayesian framework. The target model is also updated adaptively by the principled Bayesian posterior inference, which admits a closed form within our Dirichlet prior modeling. With empirical evaluations on some video datasets, the proposed method is shown to yield more accurate tracking than baseline histogram-based trackers with the same types of features, often being superior to the appearance-based (visual) trackers.

• Korean Institute of Interior Design Journal
• /
• v.14 no.2 s.49
• /
• pp.217-224
• /
• 2005

The lack of objective decisive criteria and the absence of analyzing tools accrued from the experiments on various types developed from space design process makes it difficult to select and execute alternatives for them. As an attempt of coping with these problems, the aims of this study is to establish space analysis' models and to propose possibility of analyzing models by utilizing the technology of image process. It is now under study in the field of artificial intelligence based on the accomplishment of digital images. This study focused on establishment an analysis model based on accomplished digital images and image processing framework. It helps utilize various processing technologies that are currently in use of image processes, and problems of the study can be supplemented through further follow-up studies. Finally, analysis model can be constructed gradually huge design data in the analogue data to the digital image database and be proposed with index in design or evaluation step.

• Journal of Korea Technology Innovation Society
• /
• v.8 no.spc1
• /
• pp.323-336
• /
• 2005

Digital content industry is growing rapidly because of the property of high-speed networking and greater demand for digital fulltext-image. However, we know the fact that it is many difficulty in production and supply for good quality of content. Hereupon, we suggest digital fulltext-image service framework to protect copyright. More concretely, we propose integrated model and reference model to securely serve digital fulltext-image by recompositing core objects and reconstructing the value-chain structure of digital content industry to framework including the process(from its production (creators or copyrighters) to consumption (users or consumers)). Also, we construct the digital fulltext- image service system based on reference model and reconstruct its interface that occurs between core subjects.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.1085-1088
• /
• 1999

This paper presents a method for soccer scene analysis and coordinate transformation from scene to ground model using a priori knowledge. First, the ground and spectator regions are separated, and various objects are extracted from the separated ground region. Second, an affine model is used for mapping the object positions on the soccer image into the position on the ground model. Problems regarding holes arising from mapping processing are solved using inverse mapping instead of a usual interpolation method. Experiments are performed on a PC using about 100 RGB images acquired at 240＊640 resolution and 3∼5 frames per second.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.24
• /
• pp.10573-10576
• /
• 2015

Background: Accuracy in feature extraction is an important factor in image classification and retrieval. In this paper, a breast tissue density classification and image retrieval model is introduced for breast cancer detection based on thermographic images. The new method of thermographic image analysis for automated detection of high tumor risk areas, based on two-directional two-dimensional principal component analysis technique for feature extraction, and a support vector machine for thermographic image retrieval was tested on 400 images. The sensitivity and specificity of the model are 100% and 98%, respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.11
• /
• pp.4118-4136
• /
• 2014

To preserve the spatial consistency of low-level features, generalized Riesz-wavelet transform (GRWT) is adopted for fusing multi-modality images. The proposed method can capture the directional image structure arbitrarily by exploiting a suitable parameterization fusion model and additional structural information. Its fusion patterns are controlled by a heuristic fusion model based on image phase and coherence features. It can explore and keep the structural information efficiently and consistently. A performance analysis of the proposed method applied to real-world images demonstrates that it is competitive with the state-of-art fusion methods, especially in combining structural information.

• Korean Institute of Interior Design Journal
• /
• no.37
• /
• pp.110-118
• /
• 2003

Computer simulation is one of the most useful techniques to predict daylighting performance and present visual image. In architectural and interior design practice, the Lightscape is commonly used often to produce persuasive images rather than physically accurate results. Therefore, this study is to validity the Lightscape as daylighting evaluation tool, in particularly performance and realistically visualization. For the purpose, an evaluation test model (12.0m$\times$7.2m$\times$3.0m) of side lighting window with lightshelf was selected. A 1:6 scale plywood physical model was made. Under clear sky condition, illuminance of 84 Interior point were measured. Lightscape was run on a 750 MHz Pentium PC running Windows 2000 under the same sky condition. And a photography image was compared to rendering image. The physical results of interior illuminance were within 8% between the scale model and Lightscape simulation. There were no differences between the photograph image and rendering image by Lightscape in the sight. Lightscape as visualization tool for daylighting performance was validated.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.727-731
• /
• 2003

ASTER image has some advantages for classification such as 15 spectral bands and 15m ${\sim}$ 90m spatial resolution. However, in the classification using general remote sensing image, shadow areas are often classified into water area. It is very difficult to divide shadow and water. Because reflectance characteristics of water is similar to characteristics of shadow. Many land cover items are consisted in one pixel which is 15m spatial resolution. Nowadays, very high resolution satellite image (IKONOS, Quick Bird) and Digital Surface Model (DSM) by air borne laser scanner can also be used. In this study, mixed pixel analysis of ASTER image has carried out using IKONOS image and DSM. For mixed pixel analysis, high accurated geometric correction was required. Image matching method was applied for generating GCP datasets. IKONOS image was rectified by affine transform. After that, one pixel in ASTER image should be compared with corresponded 15×15 pixel in IKONOS image. Then, training dataset were generated for mixed pixel analysis using visual interpretation of IKONOS image. Finally, classification will be carried out based on Linear Mixture Model. Shadow extraction might be succeeded by the classification. The extracted shadow area was validated using shadow image which generated from 1m${\sim}$2m spatial resolution DSM. The result showed 17.2% error was occurred in mixed pixel. It might be limitation of ASTER image for shadow extraction because of 8bit quantization data.