• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.10
• /
• pp.76-88
• /
• 1997

Based on the principles described in Part I, we have implemented a working prototype vision system using a feature structure called an LSG (local surface group) for generating object hypotheses. In order to verify an object hypothesis, we estimate the view of the hypothesized model object and render the model object for the computed view. The object hypothesis is then verified by finding additional features in the scene that match those present in the rendered image. Experimental results on synthetic and real range images show the effectiveness of the indexing scheme.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1771-1774
• /
• 2003

Image segmentation is very important technique as preprocessing. It is used for various applications such as object recognition, computer vision, object based image compression. In this paper, a method which segments the multidimensional image using a hierarchical histogram approach, is proposed. The hierarchical histogram approach is a method that decomposes the multi-dimensional situation into multi levels of 1 dimensional situations. It has the advantage of the rapid and easy calculation of the histogram, and at the same time because the histogram is applied at each level and not as a whole, it is possible to have more detailed partitioning of the situation.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.6
• /
• pp.379-383
• /
• 2015

This paper presents an approach to detect object distance with the use of the recently developed low-cost Kinect sensor. The technique is based on Kinect color depth-image processing and can be used to design various computer-vision applications, such as object recognition, video surveillance, and autonomous path finding. The proposed technique uses keypoint feature detection in the Kinect depth image and advantages of depth pixels to directly obtain the feature distance in the depth images. This highly reduces the computational overhead and obtains the pixel distance in the Kinect captured images.

• The Journal of the Korea Contents Association
• /
• v.11 no.12
• /
• pp.619-628
• /
• 2011

Normally vision-based 3D human pose recognition technology is used to method for convey human gesture in HCI(Human-Computer Interaction). 2D pose model based recognition method recognizes simple 2D human pose in particular environment. On the other hand, 3D pose model which describes 3D human body skeletal structure can recognize more complex 3D pose than 2D pose model in because it can use joint angle and shape information of body part. In this paper, we describe a development of interactive game contents using pose recognition interface that using 3D human body joint information. Our system was proposed for the purpose that users can control the game contents with body motion without any additional equipment. Poses are recognized comparing current input pose and predefined pose template which is consist of 14 human body joint 3D information. We implement the game contents with the our pose recognition system and make sure about the efficiency of our proposed system. In the future, we will improve the system that can be recognized poses in various environments robustly.

• Journal of the HCI Society of Korea
• /
• v.10 no.2
• /
• pp.45-55
• /
• 2015

In recent years, keypoint recognition and tracking technologies are considered as crucial task in many practical systems for markerless augmented reality. The keypoint recognition and technologies are widely studied in many research areas, including computer vision, robot navigation, human computer interaction, and etc. Moreover, due to the rapid growth of mobile market related to augmented reality applications, several effective keypoint-based matching and tracking methods have been introduced by considering mobile embedded systems. Therefore, in this paper, we extensively analyze the recent research trends on keypoint-based recognition and tracking with several core components: keypoint detection, description, matching, and tracking. Then, we also present one of our research related to mobile augmented reality, named mobile tour guide system, by real-time recognition and tracking of tour maps on mobile devices.

• Journal of Multimedia Information System
• /
• v.6 no.4
• /
• pp.225-234
• /
• 2019

Deep learning has become increasingly popular in both academic and industrial areas nowadays. Various domains including pattern recognition, Computer vision have witnessed the great power of deep neural networks. However, current studies on deep learning mainly focus on quality data sets with balanced class labels, while training on bad and imbalanced data set have been providing great challenges for classification tasks. We propose in this paper a method of data analysis-based data reduction techniques for selecting good and diversity data samples from a large dataset for a deep learning model. Furthermore, data sampling techniques could be applied to decrease the large size of raw data by retrieving its useful knowledge as representatives. Therefore, instead of dealing with large size of raw data, we can use some data reduction techniques to sample data without losing important information. We group PCB characters in classes and train deep learning on the ResNet56 v2 and SENet model in order to improve the classification performance of optical character recognition (OCR) character classifier.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.3
• /
• pp.1264-1274
• /
• 2015

Human action recognition received many interest in the computer vision community. Most of the existing methods focus on either construct robust descriptor from the temporal domain, or computational method to exploit the discriminative power of the descriptor. In this paper we explore the idea of using local action attributes to form an action descriptor, where an action is no longer characterized with the motion changes in the temporal domain but the local semantic description of the action. We propose an novel framework where introduces local action attributes to represent an action for the final human action categorization. The local action attributes are defined for each body part which are independent from the global action. The resulting attribute descriptor is used to jointly model human action to achieve robust performance. In addition, we conduct some study on the impact of using body local and global low-level feature for the aforementioned attributes. Experiments on the KTH dataset and the MV-TJU dataset show that our local action attribute based descriptor improve action recognition performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.771-789
• /
• 2019

Text detection has been a popular research topic in the field of computer vision. It is difficult for prevalent text detection algorithms to avoid the dependence on datasets. To overcome this problem, we proposed a novel unsupervised text detection algorithm inspired by bootstrap learning. Firstly, the text candidate in a novel form of superpixel is proposed to improve the text recall rate by image segmentation. Secondly, we propose a unique text sample selection model (TSSM) to extract text samples from the current image and eliminate database dependency. Specifically, to improve the precision of samples, we combine maximally stable extremal regions (MSERs) and the saliency map to generate sample reference maps with a double threshold scheme. Finally, a multiple kernel boosting method is developed to generate a strong text classifier by combining multiple single kernel SVMs based on the samples selected from TSSM. Experimental results on standard datasets demonstrate that our text detection method is robust to complex backgrounds and multilingual text and shows stable performance on different standard datasets.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.6_1
• /
• pp.693-698
• /
• 2021

As technology advances, there is increasing need for research in different fields where this technology is applied. On of the most researched topic in computer vision is Human activity recognition (HAR), which has widely been implemented in various fields which include healthcare, video surveillance and education. We therefore present in this paper a human activity recognition system based on scale and rotation while employing the Kinect depth sensors to obtain the human skeleton joints. In contrast to previous approaches that use joint angles, in this paper we propose that each limb has an angle with the X, Y, Z axes which we employ as feature vectors. The use of the joint angles makes our system scale invariant. We further calculate the body relative direction in the egocentric coordinates in order to provide the rotation invariance. For the system parameters, we employ 8 limbs with their corresponding angles each having the X, Y, Z axes from the coordinate system as feature vectors. The extracted features are finally trained and tested with the Long short term memory (LSTM) Network which gives us an average accuracy of 98.3%.

• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.411-427
• /
• 2022

Digging historical and cultural information from seals in ancient books is of great significance. However, ancient Chinese seal samples are scarce and carving methods are diverse, and traditional digital image processing methods based on greyscale have difficulty achieving superior segmentation and recognition performance. Recently, some deep learning algorithms have been proposed to address this problem; however, current neural networks are difficult to train owing to the lack of datasets. To solve the afore-mentioned problems, we proposed an SEL-RefineMask which combines selector of feature pyramid network (SEL-FPN) with RefineMask to segment and recognize seals. We designed an SEL-FPN to intelligently select a specific layer which represents different scales in the FPN and reduces the number of anchor frames. We performed experiments on some instance segmentation networks as the baseline method, and the top-1 segmentation result of 64.93% is 5.73% higher than that of humans. The top-1 result of the SEL-RefineMask network reached 67.96% which surpassed the baseline results. After segmentation, a vision transformer was used to recognize the segmentation output, and the accuracy reached 91%. Furthermore, a dataset of seals in ancient Chinese books (SACB) for segmentation and small seal font (SSF) for recognition were established which are publicly available on the website.