• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.5
• /
• pp.48-55
• /
• 2009

Prior research works in indoor-outdoor classification have been conducted based on a simple combination of low-level features. However, since there are many challenging problems due to the extreme variability of the scene contents, most methods proposed recently tend to combine the low-level features with high-level information such as the presence of trees and sky. To extract these regions from videos, we need to conduct additional tasks, which may yield the increasing number of feature dimensions or computational burden. Therefore, an efficient indoor-outdoor scene classification method is proposed in this paper. First, the video is divided into the five same-sized blocks. Then we define and use the edge and color orientation histogram (ECOH) descriptors to represent each sub-block efficiently. Finally, all ECOH values are simply concatenated to generated the feature vector. To justify the efficiency and robustness of the proposed method, a diverse database of over 1200 videos is evaluated. Moreover, we improve the classification performance by using different weight values determined through the learning process.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.2
• /
• pp.15-20
• /
• 2000

In this paper, we presents a new MCDI(motion compensated difference image) coding method using CVQ(classifled vector quantization) whoes MCD(motion compensated difference) block is classified by proposed classifier using motion vector and compensated block The variance of MCD block is closely related with the magnitude of motion vector as well as the variance of compensated block, so using this property, we propose a new classifier. This scheme has no side information of the classifier what sub-codebook is selected, and simulation results show that the proposed method exhibits a good performance even when compared with a conventional method that requires classification bits.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.15 no.2
• /
• pp.1-13
• /
• 2013

The study is to provide basic data on improving costume's fitting by developing physical integrated Basic Bodice Block's development for body types of adult women, which is based on setting up body-type information per truncus as fundamental of adult women's top product manufacture in being ready for Mass Customization era. Also, after review on the objectivity and accuracy of fitting information by real wear and virtual wear experiment on body types, not only 3D virtual clothing system was used as way of information provider of Clothing product, but also provided as basic data in order to use effectively on portion of clothing passion in responding to trend of Mass customization in advance. The consequence of the study is as followings. After analyzing significance differences per items on real and virtual wear evaluation, bowed type of type 1 had significance differences on waist measurement and hip circumference in back and side, which would be knowing as not integrated with costume, affecting form of human body according to virtual wear system bended on back region. Also, in side evaluation, every types except straight body type of type 3 appeared significant differences. In virtual wear evaluation, costume's expression with side body types were not similar to real wear until now except straight body types. It would be improvement things from 3D virtual wear system in advance.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.12
• /
• pp.46-54
• /
• 1998

In this paper we propose a fast adaptive image restoration filter using DCT-based block classification for reducing block artifacts in compressed images. In order to efficiently reduce block artifacts, edge direction of each block is classified by using the DCT coefficients, and the constrained least square (CLS) on the observation that the quantization operation in a series of coding process is a nonlinear and many-to-one mapping operator. And then we propose an approximated version of constrained optimization technique as a restoration process for removing the nonlinear and space-varying degradation operator. For real-time implementation, the proposed restoration filter can be realized in the form of a truncated FIR filter, which is suitable for postprocessing reconstructed images in HDTV, DVD, or video conference systems.

• The KIPS Transactions:PartB
• /
• v.13B no.6 s.109
• /
• pp.585-590
• /
• 2006

Although motion estimation Plays an important role in digital video compression, complex search procedure is required to find an optimal motion vector. To reduce the search time, the search start point should be set up properly md efficient search pattern is needed. If the overall motion of the torrent block can be predicted, motion estimation can be performed efficiently. In this paper. block types are classified using candidate vectors and the motion activity of the block is predicted which leads to the search start point close to the optimal motion vector. The proposed method proves to be about 1.5$\sim$7 times faster than existing methods with about 0.02$\sim$0.2(dB) improvement of picture quality in images with large movements.

• Journal of Digital Contents Society
• /
• v.18 no.7
• /
• pp.1323-1331
• /
• 2017

Despite the fact that the copyright has grown into a large-scale business, there are many constant problems especially in image copyright. In this study, we propose an automatic object extraction and classification system for the scanned educational book image by combining document image processing and intelligent information technology like deep learning. First, the proposed technology removes noise component and then performs a visual attention assessment-based region separation. Then we carry out grouping operation based on extracted block areas and categorize each block as a picture or a character area. Finally, the caption area is extracted by searching around the classified picture area. As a result of the performance evaluation, it can be seen an average accuracy of 83% in the extraction of the image and caption area. For only image region detection, up-to 97% of accuracy is verified.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.3
• /
• pp.77-83
• /
• 2012

As web pages provide various services, the distribution of malware via the web pages is being also increased. Malware can make personal information leak, system mal-function and system be zombie. To protect this damages, we should block the malicious web pages. Because the malicious codes embedded in web pages are obfuscated or transformed, it is difficult to detect them using signature-based approaches which are used by current anti-virus software. To overcome this problem, we extracted features to classify malicious web pages and benign ones by analyzing web pages. And we propose a classification method using SVM which is widely used in machine learning. Experimental results show that the proposed method is better than other methods. The proposed method could classify malicious web pages correctly and be helpful to block the distribution of malicious codes.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.3
• /
• pp.289-294
• /
• 2002

A valid speech-sound block can be classified to provide important information for speech recognition. The classification of the speech-sound block comes from the MRA(multi-resolution analysis) property of the DWT(discrete wavelet transform), which is used to reduce the computational time for the pre-processing of speech recognition. The merging algorithm is proposed to extract valid speech-sounds in terms of position and frequency range. It needs some numerical methods for an adaptive DWT implementation and performs unvoiced/voiced classification and denoising. Since the merging algorithm can decide the processing parameters relating to voices only and is independent of system noises, it is useful for extracting valid speech-sounds. The merging algorithm has an adaptive feature for arbitrary system noises and an excellent denoising SNR(signal-to-nolle ratio).

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.3
• /
• pp.880-894
• /
• 1997

In this paper,we propose a new algorithm to perform DCT(Discrete Cosine Transform) withn the area reduced by prdeicting position of quantization coefficients to be zero.This proposed algorithm not only decreases the enoding time and the decoding time by reducing computation amount of FDCT(Forward DCT)and IDCT(Inverse DCT) but also increases comprossion ratio by performing each diffirent horizontal- vereical zig-zag scan assording to the calssified block size for each block on the huffiman coeing.Traditional image coding method performs the samd DCT computation and zig-zag scan over all blocks,however this proposed algorthm reduces FDCT computation time by setting to zero insted of computing DCT for quantization codfficients outside classfified block size on the encoding.Also,the algorithm reduces IDCT computation the by performing IDCT for only dequantization coefficients within calssified block size on the decoding.In addition, the algorithm reduces Run-Length by carrying out horizontal-vertical zig-zag scan approriate to the slassified block chraateristics,thus providing the improverment of the compression ratio,On the on ther hand,this proposed algorithm can be applied to 16*16 block processing in which the compression ratio and the image resolution are optimal but the encoding time and the decoding time take long.Also,the algorithm can be extended to motion image coding requirng real time processing.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.185-207
• /
• 2022

Recently, with the development of deep learning technology, researches to apply a deep learning algorithm to analyze unstructured data such as text and images are being actively conducted. Text classification has been studied for a long time in academia and industry, and various attempts are being performed to utilize data characteristics to improve classification performance. In particular, a hierarchical relationship of labels has been utilized for hierarchical classification. However, the top-down approach mainly used for hierarchical classification has a limitation that misclassification at a higher level blocks the opportunity for correct classification at a lower level. Therefore, in this study, we propose a methodology for classifying hierarchical data using the autoencoder-based deeply supervised network that high-level classification does not block the low-level classification while considering the hierarchical relationship of labels. The proposed methodology adds a main classifier that predicts a low-level label to the autoencoder's latent variable and an auxiliary classifier that predicts a high-level label to the hidden layer of the autoencoder. As a result of experiments on 22,512 academic papers to evaluate the performance of the proposed methodology, it was confirmed that the proposed model showed superior classification accuracy and F1-score compared to the traditional supervised autoencoder and DNN model.