• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.9
• /
• pp.77-83
• /
• 1997

Based on the curve segment grouping, an efficient recognition of round objects form partially occuluded round boundaries is proposed. Curve segments are extracted from an image using a criterion based on the intra-segment curvature and local contrast. During the curve segment extraction the boundaries of pratially occluding and occuluded objects are segmented to different curve segments. The extracted segments of constant intra-segment curvature are grouped to different curve segments. The extracted segments of constant intra-segment curvature are grouped nto a round boundary by the proposed grouping algorithm using inter-segment curvature which gives the relatinships among the curve segments of the same round boundary. The 1st and the 2nd order moments are used for the parameter estimation of the best fitted ellipse with round boundary, and then recognition is perfomed based on the estimated parameters. The proposed scheme processes in segment unit and is more efficient in computational complexity and memory requirements those that of the conventional scheme which processed in pixel units. Experimental results show that the proposed technique is very efficient in recognizing the round object sfrom the real images with apples and pumpkins.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.4E
• /
• pp.21-27
• /
• 1996

In this paper, we propose a discriminative training algorithm for the stochastic segment model (SSM) in continuous speech recognition. As the SSM is usually trained by maximum likelihood estimation (MLE), a discriminative training algorithm is required to improve the recognition performance. Since the SSM does not assume the conditional independence of observation sequence as is done in hidden Markov models (HMMs), the search space for decoding an unknown input utterance is increased considerably. To reduce the computational complexity and starch space amount in an iterative training algorithm for discriminative SSMs, a hybrid architecture of SSMs and HMMs is programming using HMMs. Given the segment boundaries, the parameters of the SSM are discriminatively trained by the minimum error classification criterion based on a generalized probabilistic descent (GPD) method. With the discriminative training of the SSM, the word error rate is reduced by 17% compared with the MLE-trained SSM in speaker-independent continuous speech recognition.

• Journal of KIISE:Databases
• /
• v.32 no.3
• /
• pp.334-343
• /
• 2005

Complex queries such as path alld twig patterns have been the focus of much research on processing XML data. Structural join algorithms use a form of encoded structural information for elements in an XML document to facilitate join processing. Recently, structural join algorithms such as Twigstack and TSGeneric- have been developed to process such complex queries, and they have been shown that the processing costs of the algorithms are linearly proportional to the sum of input data. However, the algorithms have a shortcoming that their processing costs increase with the length of a queery. To overcome the shortcoming, we propose the segment join technique to augment the structural join with structural indexes such as the 1-Index. The SegmentTwig algorithm based on the segment join technique performs joins between a pair of segments, which is a series of query nodes, rather than joins between a pair of query nodes. Consequently, the query can be processed by reading only a query node per segment. Our experimental study shorts that segment join algorithms outperform the structural join methods consistently and considerably for various data sets.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.16 no.4
• /
• pp.537-544
• /
• 2013

This paper proposes a recursive localized Normalized Mutual Information(NMI) algorithm to overcome shortcomings of the conventional NMI algorithm and the localized NMI algorithm which proposed before. The localized NMI algorithm divides images into few fixed size segments and applies NMI algorithm to each segments. By extension, the proposed algorithm uses variable size segments using its characteristic. Dividing each segment recursively, the algorithm selects a suitable segment size and improves a performance of the image registration. Experimental result shows the performance of the proposed algorithm.

• Journal of Korea Multimedia Society
• /
• v.12 no.3
• /
• pp.427-435
• /
• 2009

Users are able to search and read interesting items and hence click hyperlink linked to the item which is detailed content unit such as menu, login, news, video, etc. Small screen like mobile device is very difficult to viewing all web contents at once. Browsing and searching for interesting items by scrolling to left and right or up and down is discomfort to users in small screen. Searching and displaying directly the item preferred by users can reduces difficulty of interface manipulation of mobile device. To archive it, web contents based on desktop will be segmented on a per-item basis which component unit of web contents. Most segment algorithms are based on segment method through analysis of HTML code or mobile size. However, it is difficult to extract item blocks. Because present web content is getting more complicated and diversified in structure and content like web portal services. A web content segment algorithm suggested in this paper is based on extracting item blocks is component units of web contents.

• ETRI Journal
• /
• v.28 no.3
• /
• pp.329-336
• /
• 2006

This paper investigates the problem of protecting multicast sessions in mesh wavelength-division multiplexing (WDM) networks against single link failures, for example, a fiber cut in optical networks. First, we study the two characteristics of multicast sessions in mesh WDM networks with sparse light splitter configuration. Traditionally, a multicast tree does not contain any circles, and the first characteristic is that a multicast tree has better performance if it contains some circles. Note that a multicast tree has several branches. If a path is added between the leave nodes on different branches, the segment between them on the multicast tree is protected. Based the two characteristics, the survivable multicast sessions routing problem is formulated into an Integer Linear Programming (ILP). Then, a heuristic algorithm, named the adaptive shared segment protection (ASSP) algorithm, is proposed for multicast sessions. The ASSP algorithm need not previously identify the segments for a multicast tree. The segments are determined during the algorithm process. Comparisons are made between the ASSP and two other reported schemes, link disjoint trees (LDT) and shared disjoint paths (SDP), in terms of blocking probability and resource cost on CERNET and USNET topologies. Simulations show that the ASSP algorithm has better performance than other existing schemes.

• Journal of KIISE:Information Networking
• /
• v.30 no.3
• /
• pp.448-460
• /
• 2003

In this paper, we propose a network fault recovery algorithm based on a segment restoration scheme to reduce restoration time and restoration resource. The proposed segment restoration scheme is based on network partitioning which divides a large network into several small subnetworks. The restoration performance of the proposed segment restoration scheme depends on the size and the topology of subnetworks. Since most faults can be restored in a subnetwork, restoration time is reduced obviously. We compare and analyze restoration performance according to the size of subnetworks and restoration schemes. From simulation results, the proposed segment restoration scheme has the shortest restoration time compared with other restoration schemes. Especially the restoration performance of the proposed segment restoration scheme is better than the SLSP, which is also a segment-based restoration scheme, in terms of restoration time and required restoration resource capacity.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.10
• /
• pp.83-92
• /
• 2009

In this paper, an extended snake algorithm using color variance energy is proposed for segmenting an interest object in color image. General snake algorithm makes use of energy in image to segment images into a interesting area and background. There are many kinds of energy that can be used by the snake algorithm. The efficiency of the snake algorithm is depend on what kind of energy is used. A general snake algorithm based on active contour model uses the intensity value as an image energy that can be implemented and analyzed easily. But it is sensitive to noises because the image gradient uses a differential operator to get its image energy. And it is difficult for the general snake algorithm to be applied on the complex image background. Therefore, the proposed snake algorithm efficiently segment an interest object on the color image by adding a color variance of the segmented area to the image energy. This paper executed various experiments to segment an interest object on color images with simple or complex background for verifying the performance of the proposed extended snake algorithm. It shows improved accuracy performance about 12.42 %.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.474-477
• /
• 2000

This paper presents an algorithm for simplification of 3D triangular mesh data, based on mesh simplification. The proposed algorithm is first attempt to segment the entire mesh into several parts using the orientation of triangles. Then simplification algorithm is applied to each segment that has similar geometric property. The proposed two step multi-resolution modeling scheme would yield better performance then conventional algorithm like edge collapse technique, since the segmentation step can give global information on the input shape. The experimental results show that the proposed algorithm is performed efficiently.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.4
• /
• pp.125-132
• /
• 2021

As the layers of artificial neural network deepens, and the dimension of data used as an input increases, there is a problem of high arithmetic operation requiring a lot of arithmetic operation at a high speed in the learning and recognition of the neural network (NN). Thus, this study proposes a data dimensionality reduction method to reduce the dimension of the input data in the NN. The proposed Line-segment Feature Analysis (LFA) algorithm applies a gradient-based edge detection algorithm using median filters to analyze the line-segment features of the objects existing in an image. Concerning the extracted edge image, the eigenvalues corresponding to eight kinds of line-segment are calculated, using 3×3 or 5×5-sized detection filters consisting of the coefficient values, including [0, 1, 2, 4, 8, 16, 32, 64, and 128]. Two one-dimensional 256-sized data are produced, accumulating the same response values from the eigenvalue calculated with each detection filter, and the two data elements are added up. Two LFA256 data are merged to produce 512-sized LAF512 data. For the performance evaluation of the proposed LFA algorithm to reduce the data dimension for the recognition of handwritten numbers, as a result of a comparative experiment, using the PCA technique and AlexNet model, LFA256 and LFA512 showed a recognition performance respectively of 98.7% and 99%.