• KIEAE Journal
• /
• v.3 no.2
• /
• pp.59-66
• /
• 2003

To be the design method supporting aesthetic ability of human, CAAD system should essentially recognize architectural form in the same way of human. In this study, visual perception process of human was analyzed to search proper computational method performing similar step of perception of it. Through the analysis of visual perception, vision was separated to low-level vision and high-level vision. Edge detection and neural network were selected to model after low-level vision and high-level vision. The 24 images of building, tree and landscape were processed by edge detection and trained by neural network. And 24 new images were used to test trained network. The test shows that trained network gives right perception result toward each images with low error rate. This study is on the meaning of artificial intelligence in design process rather than on the design automation strategy through artificial intelligence.

• Journal of Information Processing Systems
• /
• v.9 no.4
• /
• pp.592-601
• /
• 2013

Object segmentation is a challenging task in image processing and computer vision. In this paper, we present a visual attention based segmentation method to segment small sized interesting objects in natural images. Different from the traditional methods, we first search the region of interest by using our novel saliency-based method, which is mainly based on band-pass filtering, to obtain the appropriate frequency. Secondly, we applied the Gaussian Mixture Model (GMM) to locate the object region. By incorporating the visual attention analysis into object segmentation, our proposed approach is able to narrow the search region for object segmentation, so that the accuracy is increased and the computational complexity is reduced. The experimental results indicate that our proposed approach is efficient for object segmentation in natural images, especially for small objects. Our proposed method significantly outperforms traditional GMM based segmentation.

• Journal of information and communication convergence engineering
• /
• v.19 no.3
• /
• pp.180-187
• /
• 2021

In this paper, we present a computational volumetric reconstruction method for three-dimensional (3D) photon counting imaging with enhanced visual quality when low-resolution elemental images are used under photon-starved conditions. In conventional photon counting imaging with low-resolution elemental images, it may be difficult to estimate the 3D scene correctly because of a lack of scene information. In addition, the reconstructed 3D images may be blurred because volumetric computational reconstruction has an averaging effect. In contrast, with our method, the pixels of the elemental image rearrangement technique and a Bayesian approach are used as the reconstruction and estimation methods, respectively. Therefore, our method can enhance the visual quality and estimation accuracy of the reconstructed 3D images because it does not have an averaging effect and uses prior information about the 3D scene. To validate our technique, we performed optical experiments and demonstrated the reconstruction results.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.17 no.4
• /
• pp.91-100
• /
• 2015

The purpose of this study is to analyze the style of check dresses shown in collections from 2011 to 2014 and to extract main expressional words for the development of semantic differential scales of visual images according to the change in silhouette of block check dresses. The results of this study are as follows: 1) 120 check dresses shown in collections were composed of 57 straight silhouette dresses, 38 fitted silhouette dresses, 23 hourglass silhouette dresses, 1 barrel silhouette dress, and 1 atypical silhouette dress. And check pattern mostly used in the current collections a square pattern of block check, tartan check that is a Scotch traditional lattice pattern, a small lattice pattern of gingham check, over check that other check patterns are arranged on check pattern, star-shaped hound tooth check, glen check mixing small pattern and big pattern. The visual image for check dress differs according to changes in the check pattern and silhouette of the dress. 2) Main expressional words of visual images for block check dresses differ greatly depending on the silhouette of dresses. The visual images are ranked in the order of 'graphic', 'simple', 'hard', 'modern' for straight silhouette of block check dresses. The words of 'lively', 'girlish', 'feminine', 'cute' are ranked for hourglass silhouette of block check dresses. And the words of 'confident', 'feminine', 'modern' are marked down for fitted silhouette of block check dresses.

• International Journal of Advanced Culture Technology
• /
• v.11 no.1
• /
• pp.45-54
• /
• 2023

The digital age start in earnest with the widespread use of the Internet. As a digital product, virtual idols bring new value to the design and dissemination of commercial brand images. "Luo Tianyi" is the world's first avatar and VOCALOID voice bank of Chinese. It has a large number of fans in China and is widely used in brand promotion. Therefore, "Luo Tianyi" is taken as the research object. Initially, we investigated the virtual idols through books, literature on the internet and other materials. Then we discussed semiotics and theories related to culture code brand design methodology (CCBD). After that, putting the above theories into practice, combined with brand design cases, we analyzed the strategy of virtual idols in brand promotion and dissemination, at last, we have the conclusion as followed. The results show that the virtual idols, visual symbol of "Luo Tianyi" can express the Index and Symbol corresponding to the brand information according to the characteristics of the brand. As an image of cultural code, "Luo Tianyi" can present three visual images at the same time, which are contemporary, traditional and future. In addition, these three visual images are presented in a strong and weak combination, which has a positive impact on the visual communication of the brand.

• Proceedings of the Optical Society of Korea Conference
• /
• 2003.02a
• /
• pp.56-57
• /
• 2003

We propose the encrytion method using visual cryptography and virtual phase images. The decryption is able to be performed when anyone got all of the keys. Original information is extracted by using Mach-Zehnder interferometer.

• Journal of Internet Computing and Services
• /
• v.11 no.3
• /
• pp.15-24
• /
• 2010

In this paper, we propose an image classification which combines semantic relations of tags with contents of images to improve the satisfaction of image retrieval on application domains as huge image sharing sites. To make good use of image retrieval or classification algorithms on huge image sharing sites as Flickr, they are applicable to real tagged Web images. To classify the Web images by 'bag of visual word' based image content, our algorithm includes training the category model by utilizing the preliminary retrieved images with semantically related tags as training data and classifying the test images based on PLSA. In the experimental results on the Flickr Web images, the proposed method produced the better precision and recall rates than those from the existing method using tag information.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1171-1178
• /
• 2019

This study proposes a deep neural network model based on an encoder-decoder structure for visual dialogs. Ongoing linguistic understanding of the dialog history and context is important to generate correct answers to questions in visual dialogs followed by questions and answers regarding images. Nevertheless, in many cases, a visual understanding that can identify scenes or object attributes contained in images is beneficial. Hence, in the proposed model, by employing a separate person detector and an attribute recognizer in addition to visual features extracted from the entire input image at the encoding stage using a convolutional neural network, we emphasize attributes, such as gender, age, and dress concept of the people in the corresponding image and use them to generate answers. The results of the experiments conducted using VisDial v0.9, a large benchmark dataset, confirmed that the proposed model performed well.

• Journal of Sensor Science and Technology
• /
• v.33 no.2
• /
• pp.78-85
• /
• 2024

We proposed a method for visual place recognition that represents images using objects as visual words. Visual words represent the various objects present in urban environments. To detect various objects within the images, we implemented and used a zero-shot detector based on a large-scale image language model. This zero-shot detector enables the detection of various objects in urban environments without additional training. In the process of creating histograms using the proposed method, frequency-based weighting was applied to consider the importance of each object. Through experiments with open datasets, the potential of the proposed method was demonstrated by comparing it with another method, even in situations involving environmental or viewpoint changes.

• Korean Institute of Interior Design Journal
• /
• v.20 no.2
• /
• pp.167-175
• /
• 2011

This study analyzed the ways of expressing materials to create visual perception spaces in "commercial spaces". The result is as follows. First, it has been discovered that expressing materials in commercial spaces plays an important role in creating various visual perception spaces as well as discriminative spaces, in commercial spaces. Hence, it will be necessary to make a multilateral study on how you can express materials to create visual perception spaces. Second, by referring to earlier studies, four types of space have been deduced as visual perception spaces. These are: "expansion", "central", "borderline" and "decoration" spaces. Third, by considering the space types and characteristics as well as the expressing materials, the criteria for the ways of expressing materials to create visual perception spaces in commercial spaces. Finally, looking at these expression methods, images of "expansion" spaces have most commonly been expressed indistinctly by using the materials and patterns. The profound images of "central" spaces were displayed using the materials and their symbolic images have been shown using the materials and colors. In the "borderline" spaces, the areas have been distinctly segmented or expressed in limited spaces by using the materials and colors. Visual designs were displayed in the "decoration" spaces by using materials from other space fields. All these phenomena have demonstrated that various new materials are being used to create various distinctive designs in commercial spaces. The result of this study shall act as basic reference materials in devising visual designs needed in creating various visual perception spaces.