• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.185-192
• /
• 2004

This paper presents face recognition using vector quantization in the eigenspace of the faces. The existing eigenface method is not enough for representing the variations of faces. For making up for its defects, the proposed method use a clustering of feature vectors by vector quantization in eigenspace of the faces. In the trainning stage, the face images are transformed the points in the eigenspace by eigeface(eigenvetor) and we represent a set of points for each people as the centroids of vector quantizer. In the recognition stage, the vector quantizer finds the centroid having the minimum quantization error between feature vector of input image and centriods of database. The experiments are performed by 600 faces in Faces94 database. The existing eigenface method has minimum 64 miss-recognition and the proposed method has minimum 20 miss-recognition when we use 4 codevectors. In conclusion, the proposed method is a effective method that improves recognition rate through overcoming the variation of faces.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.12-20
• /
• 2011

In this paper, we propose an efficient object detection and classification algorithm for video surveillance applications. Previous researches mainly concentrated either on object detection or classification using particular type of feature e.g., Scale Invariant Feature Transform (SIFT) or Speeded Up Robust Feature (SURF) etc. In this paper we propose an algorithm that mutually performs object detection and classification. We combinedly use heterogeneous types of features such as texture and color distribution from local patches to increase object detection and classification rates. We perform object detection using spatial clustering on interest points, and use Bag of Words model and Naive Bayes classifier respectively for image representation and classification. Experimental results show that our combined feature is better than the individual local descriptor in object classification rate.

• The Journal of the Korea Contents Association
• /
• v.8 no.5
• /
• pp.29-37
• /
• 2008

To transmit video bit stream over low bandwidth such as wireless channel, high compression algorithm like H.264 codec is exploited. In transmitting high compressed video bit-stream over low bandwidth, packet loss causes severe degradation in image quality. In this paper, a new algorithm for recovery of missing or erroneous motion vector is proposed. Considering that the missing or erroneous motion vectors in blocks are closely correlated with those of neighboring blocks. Motion vector of neighboring blocks are clustered according to average linkage algorithm clustering and a representative value for each cluster is determined to obtain the candidate motion vector sets. As a result, simulation results show that the proposed method dramatically improves processing time compared to existing H.264/AVC. Also the proposed method is similar to existing H.264/AVC in terms of visual quality.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.39 no.9
• /
• pp.848-857
• /
• 2011

Vision-based collision avoidance system for air traffic management requires a excellent multiple target detection algorithm under low signal-to-noise ratio (SNR) levels. The track-before-detect (TBD) approaches have significant applications such as detection of small and dim targets from an image sequence. In this paper, two detection algorithms with the TBD approaches are proposed to satisfy the multiple target detection requirements. The first algorithm, based on a dynamic programming approach, is designed to classify multiple targets by using a k-means clustering algorithm. In the second approach, a hidden Markov model (HMM) is slightly modified for detecting multiple targets sequentially. Both of the proposed approaches are used in numerical simulations with variations in target appearance properties to provide satisfactory performance as multiple target detection methods.

• Horticultural Science & Technology
• /
• v.17 no.2
• /
• pp.127-130
• /
• 1999

This study was attempted to develop the algorithm for recognizing fruits acquired from apple tree images with digital camera in sunlight. As the result of L*a*b* color transformation for reducing the effect of sunlight, a* and b* color index were effective to extract apple pixels in tree images and linear discrimination functions with color index a* b* were developed. To recognize fruits from apple pixels, those were classified into 4 patterns according to clustering condition and morphologically filtered. Test results showed that apple fruits unoccluded were exactly recognized, whereas apple fruits occluded with leaves and trunk were miscounted 2 apples on average.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.2
• /
• pp.44-51
• /
• 2009

Text understand in natural images has become an active research field in the past few decades. In this paper, we present an automatic recognition system in Korean signboards with a complex background. The proposed algorithm includes detection, binarization and extraction of text for the recognition of shop names. First, we utilize an elaborate detection algorithm to detect possible text region based on edge histogram of vertical and horizontal direction. And detected text region is segmented by clustering method. Second, the text is divided into individual characters based on connected components whose center of mass lie below the center line, which are recognized by using a minimum distance classifier. A shape-based statistical feature is adopted, which is adequate for Korean character recognition. The system has been implemented in a mobile phone and is demonstrated to show acceptable performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.5
• /
• pp.1155-1163
• /
• 2011

In this paper, we propose a new pre-processing algorithm applied to depth map to improve the coding efficiency. Now, 3DV/FTV group in the MPEG is working for standard of 3DVC(3D video coding), but compression method for depth map images are not confirmed yet. In the proposed algorithm, after dividing the histogram distribution of a given depth map by EM clustering method based on GMM, we classify the depth map into several layered images. Then, we apply different mean shift filter to each classified image according to the existence of background or foreground in it. In other words, we try to maximize the coding efficiency while keeping the boundary of each object and taking average operation toward inner field of the boundary. The experiments are performed with many test images and the results show that the proposed algorithm achieves bits reduction of 19% ~ 20% and computation time is also reduced.

• Korean Journal of Remote Sensing
• /
• v.18 no.6
• /
• pp.369-376
• /
• 2002

This paper presents a method to enhance the performance of supervised classification by separating the spectral signature of the training data sets for each class. Using clustering technique, a training data set is divided into several subsets which show a pattern of the normal distribution with small value of spectral variances. Then a supervised classification is applied with the divided training data set as training data for the temporary subclasses of the original class. The proposed method is applied to a Landsat TM image of Busan area for the applicability test. The result shows that the proposed method produces better classified results than the conventional statistical classification methods. It is expected that the proposed method will reduce the effort and expense for selecting the training data set for each class in an area which has spectrally homogeneous signature.

• Journal of Broadcast Engineering
• /
• v.24 no.4
• /
• pp.580-591
• /
• 2019

This paper focuses on to improving object detection performance using the camera and LiDAR on autonomous vehicle platforms by fusing detected objects from individual sensors through a late fusion approach. In the case of object detection using camera sensor, YOLOv3 model was employed as a one-stage detection process. Furthermore, the distance estimation of the detected objects is based on the formulations of Perspective matrix. On the other hand, the object detection using LiDAR is based on K-means clustering method. The camera and LiDAR calibration was carried out by PnP-Ransac in order to calculate the rotation and translation matrix between two sensors. For Sensor fusion, intersection over union(IoU) on the image plane with respective to the distance and angle on world coordinate were estimated. Additionally, all the three attributes i.e; IoU, distance and angle were fused using logistic regression. The performance evaluation in the sensor fusion scenario has shown an effective 5% improvement in object detection performance compared to the usage of single sensor.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.4
• /
• pp.109-117
• /
• 2019

In modern society, due to various accidents and crime threats committed to an unspecified number of people, individual security awareness is increasing throughout society and various surveillance techniques are being actively studied. Still, there is a decline in robustness due to many problems, requiring higher reliability monitoring techniques. Thus, this paper suggests a real-time change detection technique to complement the low robustness problem in various environments and dynamic/static change detection and to solve the cost efficiency problem. We used the Self-Organizing Map (SOM) applied as a data clustering technique to implement change detection, and we were able to confirm the superiority of noise robustness and abnormal detection judgment compared to the detection technique applied to the existing image surveillance system through simulation in the indoor office environment.