• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.55.2-55
• /
• 2001

The statistical analysis of the feature extraction and the neural networks are proposed to recognize a human face. In the preprocessing step, the normalized skin color map with Gaussian functions is employed to extract the region efface candidate. The feature information in the region of face candidate is used to detect a face region. In the recognition step, as a tested, the 360 images of 30 persons are trained by the backpropagation algorithm. The images of each person are obtained from the various direction, pose, and facial expression, Input variables of the neural networks are the feature information that comes from the eigenface spaces. The simulation results of 30 persons show that the proposed method yields high recognition rates.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.68 no.1
• /
• pp.182-188
• /
• 2019

Autonomous mobile robots need SLAM (simultaneous localization and mapping) to look for the location and simultaneously to make the map around the location. In order to achieve visual SLAM, it is necessary to form an algorithm that detects and extracts feature points from camera images, and gets the camera pose and 3D points of the features. In this paper, we propose MPROSAC algorithm which combines MSAC and PROSAC, and compare the performance of optimization method and the filtering method for feature-based monocular visual SLAM. Sparse Bundle Adjustment (SBA) is used for the optimization method and the extended Kalman filter is used for the filtering method.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.169-171
• /
• 2020

CNN의 중간 단계에서 추출되는 feature를 인코딩했을 때 결과 성능평가에 미치는 영향을 알아보는 실험을 수행하였다. 물체검출(Object detection)과 물체영역분할(Object segmentation)에 대하여 성능평가를 하였으며, 비교를 위해 원본 이미지와 256채널의 feature들을 한 장으로 합친 이미지 두 가지에 대해 인코딩하여 성능 평가를 실시하는 실험을 하여 결과를 도출했다. 실험 결과, 인코딩 시 압축 정도를 약하게 했을 경우 성능이 거의 떨어지지 않거나 심지어는 더 높은 경우도 있다. 하지만 256채널의 feature들에 대하여 인코딩을 하기 때문에 이미지의 용량과 해상도가 높아지는 단점이 있다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.14 no.1
• /
• pp.27-38
• /
• 1996

Non-scale digital map have important role in the field of GIS and other application area which using geographical data in recently against conventional map restricted by scale and information. The main objective of this study is to develope the automated map production system for small scale map in conjuction with generalization techniques in a digital environment. We will intend to develope algorithms and programs for each generalization operators based on specific terrain feature with vector data. This study will be performed aspects related to an data model development of generalization process, focussing on priority for processing sequency with maintaining vector topology, and error analysis for generalized digital data.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.735-739
• /
• 2005

This paper presents a new system to estimate the head pose of human in interactive indoor environment that has dynamic illumination change and large working space. The main idea of this system is to suggest a new morphological feature for estimating head angle from stereo disparity map. When a disparity map is obtained from stereo camera, the matching confidence value can be derived by measurements of correlation of the stereo images. Applying a threshold to the confidence value, we also obtain the specific morphology of the disparity map. Therefore, we can obtain the morphological shape of disparity map. Through the analysis of this morphological property, the head pose can be estimated. It is simple and fast algorithm in comparison with other algorithm which apply facial template, 2D, 3D models and optical flow method. Our system can automatically segment and estimate head pose in a wide range of head motion without manual initialization like other optical flow system. As the result of experiments, we obtained the reliable head orientation data under the real-time performance.

• Journal of the Institute of Convergence Signal Processing
• /
• v.7 no.3
• /
• pp.116-121
• /
• 2006

In this paper, we propose the dimension reduction method of multi-dimension speech feature vector for real-time adaptation procedure in various noisy environments. This method which reduces dimensions non-linearly to map the likelihood of speech feature vector and noise feature vector. The LRT(Likelihood Ratio Test) is used for classifying speech and non-speech. The results of implementation are similar to multi-dimensional speech feature vector. The results of speech recognition implementation of detected speech data are also similar to multi-dimensional(10-order dimensional MFCC(Mel-Frequency Cepstral Coefficient)) speech feature vector.

• The Journal of the Korea Contents Association
• /
• v.9 no.2
• /
• pp.432-438
• /
• 2009

In this paper, we evaluated the performance of the automatic classifier applied for the discrimination of acute alcoholic liver injury and chronic liver fibrosis. The classifier uses the discriminant peaks of the preprocessed Raman spectrum as a feature set. In preprocessing step, we subtract baseline and apply Savitzky-Golay smoothing filter which is known to be useful at preserving peaks. After identifying discriminant peaks from the spectra, we carried out the classification experiments using MAP and neural networks. According to the experimental results, the classifier shows the promising results to diagnosis alcoholic liver injury and chronic liver fibrosis. Classification results over 80% means that the peaks used as a feature set is useful for diagnosing liver disease.

• Journal of KIISE:Software and Applications
• /
• v.31 no.7
• /
• pp.939-948
• /
• 2004

In this paper. we Propose a robust and fast image registration technique for motion correction in brain CT-CT angiography obtained from same patient to be taken at different time. First, the feature points of two images are respectively extracted by 3D edge detection technique, and they are converted to locally weighted 3D distance map in reference image. Second, we search the optimal location whore the cross-correlation of two edges is maximized while floating image is transformed rigidly to reference image. This optimal location is determined when the maximum value of cross-correlation does't change any more and iterates over constant number. Finally, two images are registered at optimal location by transforming floating image. In the experiment, we evaluate an accuracy and robustness using artificial image and give a visual inspection using clinical brain CT-CT angiography dataset. Our proposed method shows that two images can be registered at optimal location without converging at local maximum location robustly and rapidly by using locally weighted 3D distance map, even though we use a few number of feature points in those images.

• Journal of the Korea Convergence Society
• /
• v.9 no.8
• /
• pp.1-8
• /
• 2018

In the field of biometric security such as face and iris recognition, it is essential to extract facial features such as eyes and lips. In this paper, we have studied a method of detecting eye and lip region in face image using faster R-CNN. The faster R-CNN is an object detection method using deep running and is well known to have superior performance compared to the conventional feature-based method. In this paper, feature maps are extracted by applying convolution, linear rectification process, and max pooling process to facial images in order. The RPN(region proposal network) is learned using the feature map to detect the region proposal. Then, eye and lip detector are learned by using the region proposal and feature map. In order to examine the performance of the proposed method, we experimented with 800 face images of Korean men and women. We used 480 images for the learning phase and 320 images for the test one. Computer simulation showed that the average precision of eye and lip region detection for 50 epoch cases is 97.7% and 91.0%, respectively.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.8
• /
• pp.101-112
• /
• 1999

In this paper, the codebook design method of VQ (vector quantization) is proposed an method to extract feature data of image for multimedia information searching. Conventional VQ codebook design methods are unsuitable to extract the feature data of images because they have too much computation time, memory for vector decoding and blocking effects like DCT (discrete cosine transform). The proposed design method is consists of the feature extraction by WT (wavelet transform) and the data group divide method by PCA (principal component analysis). WT is introduced to remove the blocking effect of an image with high compressing ratio. Computer simulations show that the proposed method has the better performance in processing speed than the VQ design method using SOM (self-organizing map).