• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.515-518
• /
• 2019

Semantic segmentation has remained as a challenging problem in the field of computer vision. Given the immense power of Convolution Neural Network (CNN) models, many complex problems have been solved in computer vision. Semantic segmentation is the challenge of classifying several pixels of an image into one category. With the help of convolution neural networks, we have witnessed prolific results over the time. We propose a convolutional neural network model which uses Fully CNN with deconvolutional pixel layers. The goal is to create a hierarchy of features while the fully convolutional model does the primary learning and later deconvolutional model visually segments the target image. The proposed approach creates a direct link among the several adjacent pixels in the resulting feature maps. It also preserves the spatial features such as corners and edges in images and hence adding more accuracy to the resulting outputs. We test our algorithm on Karlsruhe Institute of Technology and Toyota Technologies Institute (KITTI) street view data set. Our method achieves an mIoU accuracy of 92.04 %.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.131-140
• /
• 2023

Network security situational awareness systems helps in better managing the security concerns of a network, by monitoring for any anomalies in the network connections and recommending remedial actions upon detecting an attack. An Intrusion Detection System helps in identifying the security concerns of a network, by monitoring for any anomalies in the network connections. We have proposed a CRF based IDS system using genetic search feature selection algorithm for network security situational awareness to detect any anomalies in the network. The conditional random fields being discriminative models are capable of directly modeling the conditional probabilities rather than joint probabilities there by achieving better classification accuracy. The genetic search feature selection algorithm is capable of identifying the optimal subset among the features based on the best population of features associated with the target class. The proposed system, when trained and tested on the bench mark NSL-KDD dataset exhibited higher accuracy in identifying an attack and also classifying the attack category.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.9
• /
• pp.2867-2875
• /
• 2000

In this paper, we discuss the implementation of automatic internet text categorization system. A categorization algorithm is designed and the system is implemented by back propagation learning model. Internet documents are collected according to the established categories and tested by Chi-squre ($\chi^2$) for the document leaning, and the category features are extracted. The sets of learning and separating vector are productt>d by these features. As a result of experimental evaluation, we show that this system is more improved in the performance of automatic categorization than the nearest neigbor method.

• Tuberculosis and Respiratory Diseases
• /
• v.68 no.2
• /
• pp.67-73
• /
• 2010

Background: In previous study, most patients with bronchial anthracofibrosis (BAF) were non-miners, and non-occupational old aged females. However, the clinical significance of BAF in patients with coal workers' pneumoconiosis (CWP) is unknown. Methods: Among patients with CWP who transferred to our hospital for an evaluation of associated pulmonary diseases, 32 patients who had undergone a bronchofibroscopy (BFS) and chest computed tomography (CT) examination were evaluated for the association of the BAF using a retrospective chart review. Results: Nine of the 32 CWP patients (28%) were complicated with BAF. Four of the 16 simple CWP patients (25%) were complicated with BAF. According to the International Labor Organization (ILO) classification by profusion, 2 out of 3 patients in category 1, 1 out of 8 patients in category 2 and 1 out of 3 patients in category 3 were complicated with BAF. Five out of 16 complicated CWP patients were complicated with BAF. Three out of 7 patients in type A and 2 out of 5 patients in type C were complicated with BAF. CWP patients with BAF had significantly greater multiple bronchial thickening and multiple mediastinal or hilar lymph node enlargement than the CWP patients without BAF. There was no difference in the other clinical features between the CWP patients with BAF and those without BAF. Conclusion: Many CWP patients were complicated with BAF. The occurrence of BAF was not associated with the severity of CWP progression. Therefore, a careful evaluation of the airway with a bronchoscopy examination and chest CT is warranted for BAF complicated CWP patients who present with respiratory symptoms and signs, even ILO class category 1 simple CWP patients.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.13 no.3
• /
• pp.149-163
• /
• 2011

Hanjisa(Korean paper yarn), a new material made from the traditional Korean paper, has been developed through local R&D efforts, reflecting the current trend highly valuing environmental friendly. This new material is considered suitable for the 21C lifestyle and culture pursuing improved quality of human life and the environment. Therefore, this study aims to widely make known the originality and functions of the environmentally friendly Korean paper yarn, as well as to increase its commercial value. Furthermore, a new category of apparel design is presented by studying painting dyeing based on transformational tuck techniques and wax resist dyeing with formative features of repeated lines and rhythms of shells in order to implement three-dimensional and decorative artistic expressions. The texture of the Korean cotton paper yarn was particularly suitable to employ tuck and dyeing techniques Which express formative features of shell. Also, the material was useful for expressing the three-dimensional feelings with repeated curves and cross sections of shells. Moreover, paraffin resist dyeing and stitch techniques were used in order to avoid monotony and the images of shells visually materialized. Through the results stated above, this study could explore how to overcome obstacles to globalization of the Korean modern apparel such as its uniqueness, limit of materials or absense of internationality by applying modern design to the Korean paper fabrics. In the future, it is expected that more manufactures could produce and supply the new materials so as to make widely known the originality of the Korean paper fabrics and develop the material into a popular organic product fitting the modern lifestyle.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.8
• /
• pp.77-86
• /
• 2014

Mobile devices are generally using app images which are artificially designed. Accordingly, this paper presents adjusting device brightness based on app image categorization for enhancing the visibility under various light condition. First, the proposed method performed two prior subjective tests under various lighting conditions for selecting features of app images concerning visibility and for selecting satisfactory range of device brightness for each app image. Then, the relationship between selected features of app image and satisfactory range of device brightness is analyzed. Next, app images are categorized by using two features of average brightness of app image and distribution ratio of advanced colors that are related to satisfaction range of device brightness. Then, optimal device brightness for each category is selected by having the maximum frequency of satisfaction device brightness. Experimental results show that the categorized app images with optimal device brightness have high satisfaction ratio under various light conditions.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.2 no.1
• /
• pp.32-44
• /
• 1999

Texture features can be incorporated in classification procedure to resolve class confusions. However, there have been few application-oriented studies made to evaluate the relative powers of texture analysis methods in a particular environment. This study evaluates the increases in the land-cover classification accuracy of the SPOT HRV multispectral data of Pusan Metropolitan area from texture processing. Twenty-four texture measures were derived from the SPOT HRV band 3 image. Each of these features were used in combination with the three spectral images in the classification of 10 land-cover classes. Supervised training and a Gaussian maximum likelihood classifier were used in the classification. It was found that while entropy produces the best empirical results in terms of the overall classification, other texture features can also largely improve the classification accuracies obtained by the use of the spectral images only. With the inclusion of texture, the classification for each category improves. Specially, urban built-up areas had much increase in accuracy. The results indicate that texture size 5 by 5 and 7 by 7 may be suitable at land cover classification of Pusan Metropolitan area.

• Journal of Korea Multimedia Society
• /
• v.16 no.7
• /
• pp.870-878
• /
• 2013

In this paper, we propose a novel fingerprint classification method to enhance the accuracy and efficiency of the fingerprint identification system, one of biometrics systems. According to the previous researches, fingerprints can be categorized into the several patterns based on their pattern of ridges and valleys. After construction of fingerprint database based on their patters, fingerprint classification approach can help to accelerate the fingerprint recognition. The reason is that classification methods reduce the size of the search space to the fingerprints of the same category before matching. First, we suggest a method to extract region of interest (ROI) which have real information about fingerprint from the image. And then we propose a feature extraction method which combines gray level co-occurrence matrix (GLCM) and wavelet features. Finally, we compare the performance of our proposed method with the existing method which use only GLCM as the feature of fingerprint by using the multi-layer perceptron and support vector machine.

• Archives of design research
• /
• v.15 no.4
• /
• pp.87-96
• /
• 2002

This study investigated the influence of ideals(goal-directed design attributes) and physical common features on typicality of product design and the relationship between typicality and preference that suggested different result in prior research. So for these objectives we explored the relationship between typicality and preference with two dimensions composed of goal-directed attribute typicality and physical common features typicality. The result showed that consumers' judgment of typicality on product design was increased as the product design has ideals. This was a same result as the prior research. In addition, Increasing the physical common feature with other members in product category, consumers judged that the product design is typical. Otherwise, in results of the relationship between typicality and preference were showed that the design of ideals(goal-directed design attributes) influenced on preference positively, but the design of physical common features had an inverted U-shaped.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.3
• /
• pp.27-35
• /
• 2002

A knowledge-based image retrieval technique is image searching methods using some features from the queried image. The materials in this study are automobile head lamps. The input data is composed of characters and images which have various pattern. The numbers, special symbols, and general letters are under the category of the character. The image informations are made up of the distribution of pixel data, statistical analysis, and state of pattern which are useful for the knowledge data. In this paper, we implemented a retrieval system for the scientific crime detection at traffic accident using the proposed multi knowledge-based image retrieval technique. The values for the multi knowledge-based image features were extracted from color and gray scale each. With this 22 features, we improved the retrieval efficiency about the color information and pattern information. Visual basic, crystal report and MS access DB were used for this application. We anticipate the efficient scientific detection for the traffic accident and the tracking of suspicious vehicle.