• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.11
• /
• pp.5555-5567
• /
• 2018

State-of-art instance segmentation networks are successful at generating 2D segmentation mask for region proposals with highest classification score, yet 3D object segmentation task is limited to geocentric embedding or detector of Sliding Shapes. To this end, we propose an amodal 3D instance segmentation network called A3IS-CNN, which extends the detector of Deep Sliding Shapes to amodal 3D instance segmentation by adding a new branch of 3D ConvNet called A3IS-branch. The A3IS-branch which takes 3D amodal ROI as input and 3D semantic instances as output is a fully convolution network(FCN) sharing convolutional layers with existing 3d RPN which takes 3D scene as input and 3D amodal proposals as output. For two branches share computation with each other, our 3D instance segmentation network adds only a small overhead of 0.25 fps to Deep Sliding Shapes, trading off accurate detection and point-to-point segmentation of instances. Experiments show that our 3D instance segmentation network achieves at least 10% to 50% improvement over the state-of-art network in running time, and outperforms the state-of-art 3D detectors by at least 16.1 AP.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.5
• /
• pp.983-989
• /
• 2006

Current emigration and immigration control inspects passports by the naked eye, registers them by manual input, and compares them with items of database. In this paper, we propose the method to recognize information codes of passports. The proposed passport recognition method extracts character-rows of information codes by applying sobel operator, horizontal smearing, and contour tracking algorithm. The extracted letter-row regions is binarized. After a CDM mask is applied to them in order to recover the individual codes, the individual codes are extracted by applying vertical smearing. The recognizing of individual codes is performed by the RBF network whose hidden layer is applied by ART 2 algorithm and whose learning between the hidden layer and the output layer is applied by a generalized delta learning method. After a photo region is extracted from the reference of the starting point of the extracted character-rows of information codes, that region is verified by the information of luminance, edge, and hue. The verified photo region is certified by the classified features by the ART 2 algorithm. The comparing experiment with real passport images confirmed the good performance of the proposed method.

• Journal of Information Display
• /
• v.13 no.1
• /
• pp.17-20
• /
• 2012

The current panels for liquid crystal display (LCD) TV sets are all characterized by pins placed on two sides. To manufacture one type of panel, a dedicated mask is needed, and the production line should be started once. Moreover, the whole panel needs to be removed if a dead pixel is found. If the panel, however, will first be fabricated with pins placed on four sides and then divided by a cross-cut into four equal-sized panels with pins placed on two sides, one set of masks can be used to manufacture two types of LCD panels, which was referred to by the authors as dual mode. In this paper, the concept of the dual mode and its differences from the conventional way of producing panels are introduced. Its advantages in boosting production efficiency, improving the product's good rate, and lowering the production cost are also described based on case studies. Of particular importance is the fact that the dual mode is very suitable for the trial production of very-large-area LCD TV sets.

• Journal of the Korean Society of Costume
• /
• v.67 no.1
• /
• pp.1-21
• /
• 2017

The Korean folk drama is one of the traditional art performances of Korean folklore, and it is usually characterized by mask dances. An investigation on the costume of Korean folk drama is of great historical significance because they present the variety of typical costume according to the characters. The Sandae-Nori drama of Seoul Gyeong-gi province which was designated as im- portant culture property, has the closest form to general Korean folk costume. The usual characters have their typical costume and reflect the costume of the latter Choson Dynasty period. The costumes are used as a tool of the drama to indicate the character, and the impression of the dance. The costume of the Korean folk drama is made to indicate the character because it is for the play. What is more, the costume of the Sandae-Nori drama of Seoul Gyeong-gi province shows the general aspect of folk costume of the world, which remains as the symbol of the traditional culture and shows more decoration and visibility.

• Journal of Korea Multimedia Society
• /
• v.22 no.2
• /
• pp.136-145
• /
• 2019

The crowded environment of a domestic pig farm is highly vulnerable to the spread of infectious diseases such as foot-and-mouth disease, and studies have been conducted to automatically analyze behavior of pigs in a crowded pig farm through a video surveillance system using a camera. Although it is required to correctly separate occluding pigs for tracking each individual pigs, extracting the boundaries of the occluding pigs fast and accurately is a challenging issue due to the complicated occlusion patterns such as X shape and T shape. In this study, we propose a fast and accurate method to separate occluding pigs not only by exploiting the characteristics (i.e., one of the fast deep learning-based object detectors) of You Only Look Once, YOLO, but also by overcoming the limitation (i.e., the bounding box-based object detector) of YOLO with the test-time data augmentation of rotation. Experimental results with two-pigs occlusion patterns show that the proposed method can provide better accuracy and processing speed than one of the state-of-the-art widely used deep learning-based segmentation techniques such as Mask R-CNN (i.e., the performance improvement over Mask R-CNN was about 11 times, in terms of the accuracy/processing speed performance metrics).

• Journal of Korea Multimedia Society
• /
• v.25 no.5
• /
• pp.685-694
• /
• 2022

The goal of few-shot semantic segmentation is to build a network that quickly adapts to novel classes with extreme data shortage regimes. Most existing few-shot segmentation methods leverage single or multiple prototypes from extracted support features. Although there have been promising results for natural images, these methods are not directly applicable to the aerial image domain. A key factor in few-shot segmentation on aerial images is to effectively exploit information that is robust against extreme changes in background and object scales. In this paper, we propose a Mask-Guided Attention module to extract more comprehensive support features for few-shot segmentation in aerial images. Taking advantage of the support ground-truth masks, the area correlated to the foreground object is highlighted and enables the support encoder to extract comprehensive support features with contextual information. To facilitate reproducible studies of the task of few-shot semantic segmentation in aerial images, we further present the few-shot segmentation benchmark iSAID-, which is constructed from a large-scale iSAID dataset. Extensive experimental results including comparisons with the state-of-the-art methods and ablation studies demonstrate the effectiveness of the proposed method.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.6
• /
• pp.309-317
• /
• 2022

In this paper, we propose a machine learning-based copy-move forgery detection network with dual branches. Because the rotation or scaling operation is frequently involved in copy-move forger, the conventional convolutional neural network is not effectively applied in detecting copy-move tampering. Therefore, we divide the input into rotation-invariant and scaling-invariant features based on the wavelet coefficients. Each of the features is input to different branches having the same structure, and is fused in the combination module. Each branch comprises feature extraction, correlation, and mask decoder modules. In the proposed network, VGG16 is used for the feature extraction module. To check similarity of features generated by the feature extraction module, the conventional correlation module used. Finally, the mask decoder model is applied to develop a pixel-level localization map. We perform experiments on test dataset and compare the proposed method with state-of-the-art tampering localization methods. The results demonstrate that the proposed scheme outperforms the existing approaches.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.1-9
• /
• 2020

In this paper, we propose a model that performs more natural facial attribute editing by utilizing mask information in the hair and hat region. STGAN, one of state-of-the-art research of facial attribute editing, has shown results of naturally editing multiple facial attributes. However, editing hair-related attributes can produce unnatural results. The key idea of the proposed method is to additionally utilize information on the face regions that was lacking in the existing model. To do this, we apply three ideas. First, hair information is supplemented by adding hair ratio attributes through masks. Second, unnecessary changes in the image are suppressed by adding cycle consistency loss. Third, a hat segmentation network is added to prevent hat region distortion. Through qualitative evaluation, the effectiveness of the proposed method is evaluated and analyzed. The method proposed in the experimental results generated hair and face regions more naturally and successfully prevented the distortion of the hat region.

• Journal of the Korean Society of Safety
• /
• v.36 no.1
• /
• pp.18-25
• /
• 2021

In many developed countries, such as South Korea, efficiently maintaining the aging infrastructures is an important issue. Currently, inspectors visually inspect the infrastructure for maintenance needs, but this method is inefficient due to its high costs, long logistic times, and hazards to the inspectors. Thus, in this paper, a novel crack inspection approach for concrete bridges is proposed using integrated image processing techniques. The proposed approach consists of four steps: (1) training a deep learning model to automatically detect cracks on concrete bridges, (2) acquiring in-situ images using a drone, (3) generating orthomosaic images based on 3D modeling, and (4) detecting cracks on the orthmosaic image using the trained deep learning model. Cascade Mask R-CNN, a state-of-the-art instance segmentation deep learning model, was trained with 3235 crack images that included 2415 hard negative images. We selected the Tancheon overpass, located in Seoul, South Korea, as a testbed for the proposed approach, and we captured images of pier 34-37 and slab 34-36 using a commercial drone. Agisoft Metashape was utilized as a 3D model generation program to generate an orthomosaic of the captured images. We applied the proposed approach to four orthomosaic images that displayed the front, back, left, and right sides of pier 37. Using pixel-level precision referencing visual inspection of the captured images, we evaluated the trained Cascade Mask R-CNN's crack detection performance. At the coping of the front side of pier 37, the model obtained its best precision: 94.34%. It achieved an average precision of 72.93% for the orthomosaics of the four sides of the pier. The test results show that this proposed approach for crack detection can be a suitable alternative to the conventional visual inspection method.

• (The) Research of the performance art and culture
• /
• no.37
• /
• pp.327-363
• /
• 2018

Bhutan's mask dance drama, Cham is performed in the festival of Tshechu. Originating from the 17th century, Tschechu is a religious ritual as well as a traditional festival held to commemorate the birth of Padmasambhava, who spread Buddhism in the kingdom of Bhutan. Bhutanese Cham and Tibetan Cham share similar traits in their content of , , and in their characters of Pawo and Pamo. Meanwhile, , , , , , , , are distinctive performances of Bhutanese cham. Moreover, the clown character Atsara in Bhutanese cham is a character that does not appear in the Tibetan Cham. Atsara, a humorous character, can be identified by its use of a long phallus ornament on the head or by a distorted face mask with a phallus in its hand. Bhutanese Cham, originally from Tibet, is a religious mask dance drama handed down in Lamaism temples. In later generations, new performances reflective of Bhutan's history, myth, legends, and religion were added in large amount. Thus, the Cham of Bhutan now has very independent and characteristic aspects.