• Journal of Korea Multimedia Society
• /
• v.23 no.2
• /
• pp.186-203
• /
• 2020

Image-based Virtual Try-On Systems are among the most potential solution for virtual fitting which tries on a target clothes into a model person image and thus have attracted considerable research efforts. In many cases, current solutions for those fails in achieving naturally looking virtual fitted image where a target clothes is transferred into the body area of a model person of any shape and pose while keeping clothes context like texture, text, logo without distortion and artifacts. In this paper, we propose a new improved image-based virtual try-on network system based on keypoints, which we name as KP-VTON. The proposed KP-VTON first detects keypoints in the target clothes and reliably predicts keypoints in the clothes of a model person image by utilizing a dense human pose estimation. Then, through TPS transformation calculated by utilizing the keypoints as control points, the warped target clothes image, which is matched into the body area for wearing the target clothes, is obtained. Finally, a new try-on module adopting Attention U-Net is applied to handle more detailed synthesis of virtual fitted image. Extensive experiments on a well-known dataset show that the proposed KP-VTON performs better the state-of-the-art virtual try-on systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.12
• /
• pp.3274-3292
• /
• 2013

Unsupervised methods for image segmentation are recently drawing attention because most images do not have labels or tags. A topic model is such an unsupervised probabilistic method that captures latent aspects of data, where each latent aspect, or a topic, is associated with one homogeneous region. The results of topic models, however, usually have noises, which decreases the overall segmentation performance. In this paper, to improve the performance of image segmentation using topic models, we propose two topic masks applicable to topic assignments of homogeneous regions obtained from topic models. The topic masks capture the noises among the assigned topic assignments or topic labels, and remove the noises by replacements, just like image masks for pixels. However, as the nature of topic assignments is different from image pixels, the topic masks have properties that are different from the existing image masks for pixels. There are two contributions of this paper. First, the topic masks can be used to reduce the noises of topic assignments obtained from topic models for image segmentation tasks. Second, we test the effectiveness of the topic masks by applying them to segmented images obtained from the Latent Dirichlet Allocation model and the Spatial Latent Dirichlet Allocation model upon the MSRC image dataset. The empirical results show that one of the masks successfully reduces the topic noises.

• Journal of Fashion Business
• /
• v.15 no.5
• /
• pp.87-102
• /
• 2011

The research intends to exploit a strategy method of personal branding improving a personal value for construction of a personal image. As an assessment, the model of construction strategy of personal branding is developed in four steps of a model, construction of personal branding, by using elements of personal image and researching about personal branding strategy of scholars. In order to substantiate a validity of presented model, the case analyses of Martha Stewart. The strategy of four steps for construction of effective personal image is explained below. First step is an analysis of personal brand equity, deciding a direction of the concept of a personal branding through analyzing into a core value and core competence of one. Second step is a personal brand identity, constructing personal specification and identity with elements of personal image by using effective strategy, being able to be perceived to population. Third step is a personal brand positioning, constructing competitive brand image by using analysis of SWOT and strategy STP. Fourth step is a promotion of personal brand, advertising and extending a brand image of one by using a public activity and communication methods such as publication, mass media, and social network. By using the four kinds of processes, constructed strategy of a personal brand will be significant for construction of an effective personal image by having increment of a value and power of the brand.

• Korean Journal of Remote Sensing
• /
• v.39 no.4
• /
• pp.395-407
• /
• 2023

Super-resolution (SR) has great significance in image processing because it enables downstream vision tasks with high spatial resolution. Recently, SR studies have adopted deep learning networks and achieved remarkable SR performance compared to conventional example-based methods. Deep-learning-based SR models generally require low-resolution (LR) images and the corresponding high-resolution (HR) images as training dataset. Due to the difficulties in obtaining real-world LR-HR datasets, most SR models have used only HR images and generated LR images with predefined degradation such as bicubic downsampling. However, SR models trained on simple image degradation do not reflect the properties of the images and often result in deteriorated SR qualities when applied to real-world images. In this study, we propose an image degradation model for HR satellite images based on the modulation transfer function (MTF) of an imaging sensor. Because the proposed method determines the image degradation based on the sensor properties, it is more suitable for training SR models on remote sensing images. Experimental results on HR satellite image datasets demonstrated the effectiveness of applying MTF-based filters to construct a more realistic LR-HR training dataset.

• Journal of the Korean Institute of Navigation
• /
• v.16 no.3
• /
• pp.77-85
• /
• 1992

Camera arrangement for depth and image correspondence is very important to the computer vision. Two conventional comera arrangements for stereo computer vision are lateral model and axial motion model. In this paper, using the axial motion stereo camera model, the algorithm for camera focal length measurement and the surface smoothness with the radiance-irradiance is proposed fro 3-dimensional image correspondence on stereo computer vision. By adapting the above algorithm, camera focal length can be measured precisely and the resolution of 3-dimensional image correspondence has been improved comparing to that of the axial motion model without the radiance-irradiance relation.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.6
• /
• pp.937-943
• /
• 1990

In this paper, a subband coding scheme using the human visual system(HVS) model for encoding monochrome images is proposed to produce perceptually higher quality images compared with the regular subband coding scheme. The proposed approach first transforms the intensity image to the density image by a point nonlinear transformation. A frequency band dexomposition of the density image is carried out by means of 2-D seaprable quadrature mirror filters, which split the density image spectrum into 16 equall rate subbands. Bits are allocated among the subbands to minimize the weighted mean squar error (WMSE) for differential pulse code modulation(DPCM) coding of the subbands. The weight for each subband is calculated from the modulation transfer function (MTF) of the HVS model at corresponding frequencies. The performances of the proposed approach are evaluated for 256 * 256 monochrome images at the bit rates of 0.5, 0.75 and 1.0 bita per pixel. Computer simulation results indicate that using the HVS model yields more pleasing reconstructed images than regular subband coding approach which does not use HVS model.

• Information Display
• /
• v.15 no.5
• /
• pp.22-32
• /
• 2014

The current research intends to quantify the surround luminance effects on the shape of spatial luminance CSF and to propose an image quality evaluation method that is adaptive to both surround luminance and spatial frequency of a given stimulus. The proposed image quality method extends to a model called SQRI[8]. The non-linear behaviour of the HVS was taken into account by using CSF. This model can be defined as the square root integration of multiplication between display MTF and CSF. It is assumed that image quality can be determined by considering the MTF of the imaging system and the CSF of human observers. The CSF term in the original SQRI model was replaced by the surround adaptive CSF quantified in this study and it is divided by the Fourier transform of a given stimulus. A few limitations of the current work should be addressed and revised in the future study. First, more accurate model predictions can be achievable when the actual display MTF is measured and used instead of the approximation. Then, a further improvement to the model prediction accuracy can be made when chromatic adaptation of the HVS is taken into account[45-46].

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.1
• /
• pp.123-130
• /
• 2000

In this paper, we propose an extracting method of moving object contour using active contour model from image sequences acquired by fixed camera. We use an adaptive background model for robust processing in surrounding conditions. Object segmentation model detects pixels thresholded from local difference image between background and current image and extracts connected regions. Noises in boundary area of moving object we eliminated by morphological filter. The contour of segmented object is corrected by using active contour model for extracting accurate boundary of moving object. We apply the proposed method to highway image sequences and show the results of simulation.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.435-438
• /
• 2003

A townscape has been a main factor in urban-development problems in Japan. In the townscape, keeping harmony with environment is a common goal. But useful and meaningful goals are expressing individuality and impression of the town in the townscape. In this paper, we propose the colony planning support system system to improve the townscape. The system finds propositional colour combinations based on three elements, town image, colour harmony, and cost. The targets of this model are mostly townscapes in residential areas that already exist, In this paper, we introduce the construction of a Kansei evaluation model to quantify the impression. First, we conducted computer-based evaluational experiments for 20 subjects using the SD method to clarify the relationship between town image and street colours. We chose 16 adjective words related to town image and prepared 100 colour picture samples for the evaluation. After the experiments, we constructed the model using a neural network for each word. We chose 62 experimental results for the training data of the neural network and 20 results for the testing data. Each colour in the data was selected to have unique hue, brightness or saturation attributes, After the construction, we tested the model for accuracy. We input the testing data into the constructed model and calculated errors between the output from the model and the experimental results. Testing of the model showed that the model worked well for more than 80％ of the samples. The model demonstrated influences of colours on the town image.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.1-19
• /
• 2018

Large amount of data is now available for research and business sectors to extract knowledge from it. This data can be in the form of unstructured data such as audio, text, and image data and can be analyzed by deep learning methodology. Deep learning is now widely used for various estimation, classification, and prediction problems. Especially, fashion business adopts deep learning techniques for apparel recognition, apparel search and retrieval engine, and automatic product recommendation. The core model of these applications is the image classification using Convolutional Neural Networks (CNN). CNN is made up of neurons which learn parameters such as weights while inputs come through and reach outputs. CNN has layer structure which is best suited for image classification as it is comprised of convolutional layer for generating feature maps, pooling layer for reducing the dimensionality of feature maps, and fully-connected layer for classifying the extracted features. However, most of the classification models have been trained using online product image, which is taken under controlled situation such as apparel image itself or professional model wearing apparel. This image may not be an effective way to train the classification model considering the situation when one might want to classify street fashion image or walking image, which is taken in uncontrolled situation and involves people's movement and unexpected pose. Therefore, we propose to train the model with runway apparel image dataset which captures mobility. This will allow the classification model to be trained with far more variable data and enhance the adaptation with diverse query image. To achieve both convergence and generalization of the model, we apply Transfer Learning on our training network. As Transfer Learning in CNN is composed of pre-training and fine-tuning stages, we divide the training step into two. First, we pre-train our architecture with large-scale dataset, ImageNet dataset, which consists of 1.2 million images with 1000 categories including animals, plants, activities, materials, instrumentations, scenes, and foods. We use GoogLeNet for our main architecture as it has achieved great accuracy with efficiency in ImageNet Large Scale Visual Recognition Challenge (ILSVRC). Second, we fine-tune the network with our own runway image dataset. For the runway image dataset, we could not find any previously and publicly made dataset, so we collect the dataset from Google Image Search attaining 2426 images of 32 major fashion brands including Anna Molinari, Balenciaga, Balmain, Brioni, Burberry, Celine, Chanel, Chloe, Christian Dior, Cividini, Dolce and Gabbana, Emilio Pucci, Ermenegildo, Fendi, Giuliana Teso, Gucci, Issey Miyake, Kenzo, Leonard, Louis Vuitton, Marc Jacobs, Marni, Max Mara, Missoni, Moschino, Ralph Lauren, Roberto Cavalli, Sonia Rykiel, Stella McCartney, Valentino, Versace, and Yve Saint Laurent. We perform 10-folded experiments to consider the random generation of training data, and our proposed model has achieved accuracy of 67.2% on final test. Our research suggests several advantages over previous related studies as to our best knowledge, there haven't been any previous studies which trained the network for apparel image classification based on runway image dataset. We suggest the idea of training model with image capturing all the possible postures, which is denoted as mobility, by using our own runway apparel image dataset. Moreover, by applying Transfer Learning and using checkpoint and parameters provided by Tensorflow Slim, we could save time spent on training the classification model as taking 6 minutes per experiment to train the classifier. This model can be used in many business applications where the query image can be runway image, product image, or street fashion image. To be specific, runway query image can be used for mobile application service during fashion week to facilitate brand search, street style query image can be classified during fashion editorial task to classify and label the brand or style, and website query image can be processed by e-commerce multi-complex service providing item information or recommending similar item.