• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.07a
• /
• pp.51-54
• /
• 2016

In computer vision especially in image processing, it has become popular to apply deep convolutional networks for supervised learning. Convolutional networks have shown a state of the art results in classification, object recognition, detection as well as semantic segmentation. However, supervised learning has two major disadvantages. One is it requires huge amount of labeled data to get high accuracy, the second one is to train so much data takes quite a bit long time. On the other hand, unsupervised learning can handle these problems more cheaper way. In this paper we show efficient way to learn features for classification in an unsupervised way. The network trained layer-wise, used backpropagation and our network learns features from unlabeled data. Our approach shows better results on Caltech-256 and STL-10 dataset.

• 한국데이터정보과학회:학술대회논문집
• /
• 2003.10a
• /
• pp.249-258
• /
• 2003

K-means clustering has been widely used in many applications, such that pattern analysis or recognition, data analysis, image processing, market research and so on. It can identify dense and sparse regions among data attributes or object attributes. But k-means algorithm requires many hours to get k clusters that we want, because it is more primitive, explorative. In this paper we propose a new method of k-means clustering using the grid-based sample. It is more fast than any traditional clustering method and maintains its accuracy.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.2 s.95
• /
• pp.68-73
• /
• 1999

Generally, most of machining processes are done according to the dimention of the draft made by CAD. However, there are many cases that a sample is given without the draft because of the simplicity of the shape in the machining of 2D objects. To cut the same shape as the given sample, this paper proposes the method to extract the geometric information about a large sample using the robot vision and to draw the demensional draft for the machining. Because the resolution of one frame in the vision system is too low, it is necessary to set up a camera according to the desired resolution and to capture the image moving along the contour. And the overall outline can be compounded of the sequentially captured images. In the experiment, we compared the product after the cutting with the original sample and found that the size of two objects was coincided within the allowed error bound.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.644-647
• /
• 1996

In this study the theoretical minimum resolution analysis of an active vision system using laser range finder is performed for surrounding recognition and 3D data acquisition in unknown environment. The laser range finder consists of a slitted laser beam generator, a scanning mechanism, CCD camera, and a signal processing unit. A laser beam from laser source is slitted by a set of cylindrical lenses and the slitted laser beam is emitted up and down and rotates by the scanning mechanism. The image of laser beam reflected on the surface of an object is engraved on the CCD array. In the result, the resolution of range data in laser range finder is depend on distance between lens center of CCD camera and light emitter, view and beam angles, and parameters of CCD camera.

• Journal of information and communication convergence engineering
• /
• v.13 no.3
• /
• pp.197-204
• /
• 2015

In this paper, we present an algorithm for the detection of illegally parked vehicles based on a combination of some image processing algorithms. A digital camera is fixed in the illegal parking region to capture the video frames. An adaptive Gaussian mixture model (GMM) is used for background subtraction in a complex environment to identify the regions of moving objects in our test video. Stationary objects are detected by using the pixel-level features in time sequences. A stationary vehicle is detected by using the local features of the object, and thus, information about illegally parked vehicles is successfully obtained. An automatic alarm system can be utilized according to the different regulations of different illegal parking regions. The results of this study obtained using a test video sequence of a real-time traffic scene show that the proposed method is effective.

• 한국데이터정보과학회:학술대회논문집
• /
• 2003.05a
• /
• pp.77-88
• /
• 2003

Cluster analysis has been widely used in many applications, such that data analysis, pattern recognition, image processing, etc. But clustering requires many hours to get clusters that we want, because it is more primitive, explorative and we make many data an object of cluster analysis. In this paper we propose a new clustering method, 'Clustering algorithm using a center of gravity for grid-based sample'. It is more fast than any traditional clustering method and maintains accuracy. It reduces running time by using grid-based sample and keeps accuracy by using representative point, a center of gravity.

• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2002.05a
• /
• pp.273-277
• /
• 2002

This paper describes an optimal synthesis method of binary neural network(BNN) for an approximation problem of a circular region and synthetic image having four class using a newly proposed learning algorithm. Our object is to minimize the number of connections and neurons in hidden layer by using a Newly Expanded and Truncated Learning Algorithm(NETLA) based on the multilayer BNN. The synthesis method in the NETLA is based on the extension principle of Expanded and Truncated Learning (ETL) learning algorithm using the multilayer perceptron and is based on Expanded Sum of Product (ESP) as one of the boolean expression techniques. The number of the required neurons in hidden layer can be reduced and fasted for learning pattern recognition.. The superiority of this NETLA to other algorithms was proved by simulation.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.639-642
• /
• 1999

There exist geometrically invariant relations in single-view images under a specific geometrical structure. This invariance may be utilized for 3D object recognition. Two types of invariants are compared in terms of the robustness to the variation of the feature points. Deviation of the invariant relations are measured by adding random noise to the feature point location. Zhu’s invariant requires six points on adjacent planes having two sets of four coplanar points, whereas the Kaist method requires four coplanar points and two non-coplanar points. Experimental results show that the latter method has the advantage in choosing feature points while suffering from weak robustness to the noise.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.3
• /
• pp.66-76
• /
• 1995

In this research, a mesh connected VLSI structure is proposed for the real time computation of the generalized Hough transform(GHT). The purpose of the research is to design a generalized Hough transformer that can be realized as a single chip processor. The GHT has been modified to yield a highly parallel structure consisting of simple processing elements(PEs) and communication networks. In the proposed structure, the GHT can be computed by first assigning an image pixel to a PE and performing shift and add operations. The result of the CAD circuit simulation shows that it can be computed in the time proportional to the number of pixels in the pattern. In addition to the Hough transformer, the peak detector has been designed to reduce 1)the number of the I/O operations between the transformer and the host computer and 2) the host computer's burden for peak detection by transmitting only the local peaks detected from the transformed accumulator. It is expected that the proposed single chip Hough transformer with peak detector makes a fast and inexpensive edge based object recognition systems possible for many industrial and military applications.

• 한국데이터정보과학회:학술대회논문집
• /
• 2004.04a
• /
• pp.51-60
• /
• 2004

K-means clustering is an iterative algorithm in which items are moved among sets of clusters until the desired set is reached. K-means clustering has been widely used in many applications, such as market research, pattern analysis or recognition, image processing, etc. It can identify dense and sparse regions among data attributes or object attributes. But k-means algorithm requires many hours to get k clusters that we want, because it is more primitive, explorative. In this paper we propose a new method of k-means clustering using a center of gravity for grid-based sample. It is more fast than any traditional clustering method and maintains its accuracy.