• Journal of KIBIM
• /
• v.11 no.3
• /
• pp.22-33
• /
• 2021

In order to maximize the use of BIM, all data related to individual elements in the model must be correctly assigned, and it is essential to check whether it corresponds to the IFC entity classification. However, as the BIM modeling process is performed by a large number of participants, it is difficult to achieve complete integrity. To solve this problem, studies on semantic integrity verification are being conducted to examine whether elements are correctly classified or IFC mapped in the BIM model by applying an artificial intelligence algorithm to the 2D image of each element. Existing studies had a limitation in that they could not correctly classify some elements even though the geometrical differences in the images were clear. This was found to be due to the fact that the geometrical characteristics were not properly reflected in the learning process because the range of the region to be learned in the image was not clearly defined. In this study, the CRF-RNN-based semantic segmentation was applied to increase the clarity of element region within each image, and then applied to the MVCNN algorithm to improve the classification performance. As a result of applying semantic segmentation in the MVCNN learning process to 889 data composed of a total of 8 BIM element types, the classification accuracy was found to be 0.92, which is improved by 0.06 compared to the conventional MVCNN.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.7
• /
• pp.2246-2253
• /
• 2000

In this paper, we show that one can enhance the performance of blind segmentation of phoneme boundaries by adopting the knowledge of Korean syllabic structure and the regions of voiced/unvoiced sounds. eh proposed method consists of three processes : the process to extract candidate phoneme boundaries, the process to detect boundaries of voiced/unvoiced sounds, and the process to select final phoneme boundaries. The candidate phoneme boudaries are extracted by clustering method based on similarity between two adjacent clusters. The employed similarity measure in this a process is the ratio of the probability density of adjacent clusters. To detect he boundaries of voiced/unvoiced sounds, we first compute the power density spectrum of speech signal in 0∼400 Hz frequency band. Then the points where this paper density spectrum variation is greater than the threshold are chosen as the boundaries of voiced/unvoiced sounds. The final phoneme boundaries consist of all the candidate phoneme boundaries in voiced region and limited number of candidate phoneme boundaries in unvoiced region. The experimental result showed about 40% decrease of insertion rate compared to the blind segmentation method we adopted.

• Phonetics and Speech Sciences
• /
• v.4 no.2
• /
• pp.3-20
• /
• 2012

The purpose of this study was to investigate whether a segmentation unit for a Korean noun is a 'syllable' and whether the process of segmenting spoken words occurs at the lexical level. A syllable monitoring task was administered which required participants to detect an auditorily presented target from visually presented words. In Experiment 1, syllable neighborhood density of high frequency words which can be segmented into both CV-CVC and CVC-VC were controlled. The syllable effect and the neighborhood density effect were significant, and the syllable effect emerged differently depending on the syllable neighborhood density. Similar results were obtained in Experiment 2 where low frequency words were used. The significance of word frequency effect on syllable effect was also examined. The results of Experiments 1 and 2 indicated that the segmentation unit for a Korean noun is indeed a 'syllable', and this process can occur at the lexical level.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.1
• /
• pp.40-48
• /
• 2007

This paper presents a novel texture segmentation method using multilayer perceptron (MLP) networks and Markov random fields in multiscale Bayesian framework. Multiscale wavelet coefficients are used as input for the neural networks. The output of the neural network is modeled as a posterior probability. Texture classification at each scale is performed by the posterior probabilities from MLP networks and MAP (maximum a posterior) classification. Then, in order to obtain the more improved segmentation result at the finest scale, our proposed method fuses the multiscale MAP classifications sequentially from coarse to fine scales. This process is done by computing the MAP classification given the classification at one scale and a priori knowledge regarding contextual information which is extracted from the adjacent coarser scale classification. In this fusion process, the MRF (Markov random field) prior distribution and Gibbs sampler are used, where the MRF model serves as the smoothness constraint and the Gibbs sampler acts as the MAP classifier. The proposed segmentation method shows better performance than texture segmentation using the HMT (Hidden Markov trees) model and HMTseg.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.4
• /
• pp.617-623
• /
• 2018

In this paper, we propose a novel seamless video composition method based on shape matching and Poisson equation. Video composition method consists of video segmentation process and video blending process. In the video segmentation process, the user first sets a trimap for the first frame, and then performs a grab-cut algorithm. Next, considering that the performance of video segmentation may be reduced if the color, brightness and texture of the object and the background are similar, the object region segmented in the current frame is corrected through shape matching between the objects of the current frame and the previous frame. In the video blending process, the object of source video and the background of target video are blended seamlessly using Poisson equation, and the object is located according to the movement path set by the user. Simulation results show that the proposed method has better performance not only in the naturalness of the composite video but also in computational time.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.125-132
• /
• 2012

This paper proposes an automatic object segmentation and background composition method for video communication over consumer mobile phones. The object regions were extracted based on the motion and color variance of the first two frames. To combine the motion and variance information, the Euclidean distance between the motion boundary pixel and the neighboring color variance edge pixels was calculated, and the nearest edge pixel was labeled to the object boundary. The labeling results were refined using the morphology for a more accurate and natural-looking boundary. The grow-cut segmentation algorithm begins in the expanded label map, where the inner and outer boundary belongs to the foreground and background, respectively. The segmented object region and a new background image stored a priori in the mobile phone was then composed. In the background composition process, the background motion was measured using the optical-flow, and the final result was synthesized by accurately locating the object region according to the motion information. This study can be considered an extended, improved version of the existing background composition algorithm by considering motion information in a video. The proposed segmentation algorithm reduces the computational complexity significantly by choosing the minimum resolution at each segmentation step. The experimental results showed that the proposed algorithm can generate a fast, accurate and natural-looking background composition.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.4
• /
• pp.524-534
• /
• 1995

Image segmentation is a process of partitioning of an image into different regions that have similar properties. It is an old and difficult problem. They have developed many image segmentation systems and have studied to evaluate the existing segmentation systems. However, evaluation of image segmentation systems is very difficult in nature. In this paper, we propose the evaluation criteria that evaluate image segmentation systems automatically. In order to overcome the drawbacks of using only a single evaluation criterion, we have incorporated four evaluation criteria, that is, boundary difference, boundary consistency, region uniformity, and region difference. As the experimental results show, our evaluation criteria performs very well.

• The Journal of the Acoustical Society of Korea
• /
• v.31 no.4
• /
• pp.266-272
• /
• 2012

Speaker segmentation is a process of automatically detecting the speaker boundary points in the audio data. Speaker segmentation methods are divided into two categories depending on whether they use a prior knowledge or not: One is the model-based segmentation and the other is the metric-based segmentation. In this paper, we introduce the eigenvoice-based speaker weight distance method and compare it with the representative metric-based methods. Also, we employ and compare the Euclidean and cosine similarity functions to calculate the distance between speaker weight vectors. And we verify that the speaker weight distance method is computationally very efficient compared with the method directly using the distance between the speaker adapted models constructed by the eigenvoice technique.

• The Journal of the Acoustical Society of Korea
• /
• v.10 no.4
• /
• pp.5-11
• /
• 1991

This paper suggests a segmentation method of speech signal into phonemic units. The suggested segmentation system is speaker-independent and performed without anyprior information of speech signal. In segmentation process, we first divide input speech signal into purevoiced region and not pure voiced speech regions. After then we apply the second algorithm which segments each region into the detailed phonemic units by using the voiced detection parameters, i.e., the time variation of 0th LPC cepstrum coefficient parameter and the ZCR parameter. Types of speech, used to prove the availability of segmentation algorithm suggested in this paper, are the vocabulary composed of isolated words and continuous words. According to the experiments, the successful segmentation rate for 507 phonemic units involved in the total vocabulary is 91.7%.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.37 no.3
• /
• pp.45-52
• /
• 2000

In this study, we propose the image segmentation algorithm for facial region segmentation. The proposed algorithm separates the mean image of low frequency band from the differential image of high frequency band in order to make a boundary using HWT, and then we reduce the isolation pixels, projection pixels, and overlapped boundary pixels from the low frequency band. Also the boundaries are detected and simplified by the proposed boundary detection algorithm, which are cleared on the thinning process of 1 pixel unit. After extracting facial image boundary by using the proposed algorithm, we make the mask and segment facial image through matching original image. In the result of facial region segmentation experiment by using the proposed algorithm, the successive facial segmentation have 95.88% segmentation value.