• The Transactions of the Korea Information Processing Society
• /
• v.7 no.3
• /
• pp.971-976
• /
• 2000

In this paper a new method for head gesture recognition is proposed. A the first stage, face image data are transformed into low dimensional vectors by principal component analysis (PCA), which utilizes the high correlation between face pose images. The a self organization map(SM) is trained by the transformed face vectors, in such a that the nodes at similar locations respond to similar poses. A sequence of poses which comprises each model gesture goes through PCA and SOM, and the result is stored in the database. At the recognition stage any sequence of frames goes through the PCA and SOM, and the result is compared with the model gesture stored in the database. To improve robustness of classification, probabilistic relaxation labeling(PRL) is used, which utilizes the contextural information imbedded in the adjacent poses.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 1999.10a
• /
• pp.321-332
• /
• 1999

It is important to detect objects movement for obstacle recognition and path searching of UCT(unmanned container transporters) with vision sensor. This paper shows the method to draw out objects and to trace the trajectory of the moving object using a CCD camera and it describes the method to recognize the shape of objects by neural network. We can transform pixel points to objects position of the real space using the proposed viewport. This proposed technique is used by the single vision system based on floor map.

• Journal of KIISE:Software and Applications
• /
• v.32 no.7
• /
• pp.612-624
• /
• 2005

In this paper, we propose a surface-based registration using a gaussian weighted distance map for PET-CT brain image fusion. Our method is composed of three main steps: the extraction of feature points, the generation of gaussian weighted distance map, and the measure of similarities based on weight. First, we segment head using the inverse region growing and remove noise segmented with head using region growing-based labeling in PET and CT images, respectively. And then, we extract the feature points of the head using sharpening filter. Second, a gaussian weighted distance map is generated from the feature points in CT images. Thus it leads feature points to robustly converge on the optimal location in a large geometrical displacement. Third, weight-based cross-correlation searches for the optimal location using a gaussian weighted distance map of CT images corresponding to the feature points extracted from PET images. In our experiment, we generate software phantom dataset for evaluating accuracy and robustness of our method, and use clinical dataset for computation time and visual inspection. The accuracy test is performed by evaluating root-mean-square-error using arbitrary transformed software phantom dataset. The robustness test is evaluated whether weight-based cross-correlation achieves maximum at optimal location in software phantom dataset with a large geometrical displacement and noise. Experimental results showed that our method gives more accuracy and robust convergence than the conventional surface-based registration.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.183-192
• /
• 2023

The remotely sensed data, such as satellite imagery and aerial photos, can be used to extract and detect some objects in the image through image interpretation and processing techniques. Significantly, the possibility for utilizing digital map updating and land monitoring has been increased through automatic object detection since spatial resolution of remotely sensed data has improved and technologies about deep learning have been developed. In this paper, we tried to extract plastic greenhouses into aerial orthophotos by using fully convolutional densely connected convolutional network (FC-DenseNet), one of the representative deep learning models for semantic segmentation. Then, a quantitative analysis of extraction results had performed. Using the farm map of the Ministry of Agriculture, Food and Rural Affairsin Korea, training data was generated by labeling plastic greenhouses into Damyang and Miryang areas. And then, FC-DenseNet was trained through a training dataset. To apply the deep learning model in the remotely sensed imagery, instance norm, which can maintain the spectral characteristics of bands, was used as normalization. In addition, optimal weights for each band were determined by adding attention modules in the deep learning model. In the experiments, it was found that a deep learning model can extract plastic greenhouses. These results can be applied to digital map updating of Farm-map and landcover maps.

• Journal of Advanced Navigation Technology
• /
• v.19 no.6
• /
• pp.484-491
• /
• 2015

Aerial scene is greatly increased by the introduction and supply of the image due to the growth of digital optical imaging technology and development of the UAV. It has been used as the extraction of ground properties, classification, change detection, image fusion and mapping based on the aerial image. In particular, in the image analysis and utilization of deep learning algorithm it has shown a new paradigm to overcome the limitation of the field of pattern recognition. This paper presents the possibility to apply a more wide range and various fields through the segmentation and classification of aerial scene based on the Deep learning(ConvNet). We build 4-classes image database consists of Road, Building, Yard, Forest total 3000. Each of the classes has a certain pattern, the results with feature vector map come out differently. Our system consists of feature extraction, classification and training. Feature extraction is built up of two layers based on ConvNet. And then, it is classified by using the Multilayer perceptron and Logistic regression, the algorithm as a classification process.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.9
• /
• pp.89-95
• /
• 2015

In this paper, we propose a real-time two-dimensional bar code detection system even at long range using a vision technique. We first perform short-range detection, and then long-range detection if the short-range detection is not successful. First, edge map generation, image binarization, and connect component labeling (CCL) are performed in order to select a region of interest (ROI). After interpolating the selected ROI using bilinear interpolation, a location symbol pattern is detected as the same as for short-range detection. Finally, the symbol pattern is arranged by applying inverse perspective transformation to localize bar codes. Experimental results demonstrate that the proposed system successfully detects bar codes at two or three times longer distance than existing ones even at indoor environment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.9C
• /
• pp.1258-1268
• /
• 2004

We propose a new fast, algorithm which is used for detecting frontal face in the frequency domain based on human skin-color using OCT coefficient of dynamic image compression and skin color information. The region where each pixel has a value of skin-color were extracted from U and V value based on DCT coefficient obtained in the process of Image compression using skin-color map in the Y, U, V color space A morphological filter and labeling method are used to eliminate noise in the resulting image We propose the algorithm to detect fastly human face that estimate the directional feature and variance of luminance block of human skin-color Then Extraction of face was completed adaptively on both background have the object analogous to skin-color and background is simple in the proposed algorithm The performance of face detection algorithm is illustrated by some simulation results earned out on various races We confined that a success rate of 94 % was achieved from the experimental results.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.3
• /
• pp.600-611
• /
• 1996

Recently, neural network-based speech recognition has been studied to utilize the adaptivity and learnability of neural network models. However, conventional neural network models have difficulty in the co-articulation processing and the boundary detection of similar phonmes of the Korean speech. Also, in case of using one phonotopic map, learning speed may dramatically increase and inaccuracies may be caused because homogeneous learning and recognition method should be applied for heterogenous data. Hence, in this paper, a neural net typewriter has been designed using a hierarchical self-organizing classifier(HSOC), and related algorithms are presented. This HSOC, during its learing stage, distributed phoneme data on hierarchically structured multiple phonotopic maps, using Kohonen's self-organizing feature maps(SOFM). Presented and experimented in this paper were the algorithms for deciding the number of maps, map sizes, the selection of phonemes and their placement per map, an approapriate learning and preprocessing method per map. If maps are divided according to a priorlinguistic knowledge, we would have difficulty in acquiring linguistic knowledge and how to alpply it(e.g., processing extended phonemes). Contrarily, our HSOC has an advantage that multiple phonotopic maps suitable for given input data are self-organizable. The resulting three korean phonotopic maps are optimally labelled and have their own optimal preprocessing schemes, and also confirm to the conventional linguistic knowledge.

• Tunnel and Underground Space
• /
• v.11 no.1
• /
• pp.64-71
• /
• 2001

The purpose of this study is to develop rail rockfall and landslide information system to manage spatial database using GIS. For this, a spatial database containing information such as railroad, map, topographic analysis, meteorological data, and rockfall has been constructed for 2.5 km or 5 km buffer zone from the Kyungchun, Youngdong, Jungang, Taebak and Jungsun Rairoad where risk of landslide occurrence potential is high. For management of the spatial database, railroad rockfall and landslide information system has been developed. The information system consists of view, table, chart, layout and project environment. The functions provided in the system are data conversion, editing, labeling, zoom in and out, map making, graphic editing, text DB management, charting, on-line help as well as input, retrieve and output of spatial database. The system was developed using ArcView script language Avenue, and consisted of pull-down menus and icons for easy use. The spatial database and the information system can be used to rockfall and landslide management and analysis near the railroad as basic data and tool.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.2
• /
• pp.101-112
• /
• 1995

In order to construct a feature map-based phoneme classification system for speech recognition, two procedures are usually required. One is clustering and the other is labeling. In this paper, we present a phoneme classification system based on the Kohonen's Self-Organizing Feature Map (SOFM) for clusterer and labeler. It is known that the SOFM performs self-organizing process by which optimal local topographical mapping of the signal space and yields a reasonably high accuracy in recognition tasks. Consequently, SOFM can effectively be applied to the recognition of phonemes. Besides to improve the performance of the phoneme classification system, we propose the learning algorithm combined with the classical K-mans clustering algorithm in fine-tuning stage. In order to evaluate the performance of the proposed phoneme classification algorithm, we first use totaly 43 phonemes which construct six intra-class feature maps for six different phoneme classes. From the speaker-dependent phoneme classification tests using these six feature maps, we obtain recognition rate of $87.2\%$ and confirm that the proposed algorithm is an efficient method for improvement of recognition performance and convergence speed.