• Title/Summary/Keyword: object features

Search Result 1,186, Processing Time 0.025 seconds

A Method of Eye and Lip Region Detection using Faster R-CNN in Face Image (초고속 R-CNN을 이용한 얼굴영상에서 눈 및 입술영역 검출방법)

  • Lee, Jeong-Hwan
    • Journal of the Korea Convergence Society
    • /
    • v.9 no.8
    • /
    • pp.1-8
    • /
    • 2018
  • In the field of biometric security such as face and iris recognition, it is essential to extract facial features such as eyes and lips. In this paper, we have studied a method of detecting eye and lip region in face image using faster R-CNN. The faster R-CNN is an object detection method using deep running and is well known to have superior performance compared to the conventional feature-based method. In this paper, feature maps are extracted by applying convolution, linear rectification process, and max pooling process to facial images in order. The RPN(region proposal network) is learned using the feature map to detect the region proposal. Then, eye and lip detector are learned by using the region proposal and feature map. In order to examine the performance of the proposed method, we experimented with 800 face images of Korean men and women. We used 480 images for the learning phase and 320 images for the test one. Computer simulation showed that the average precision of eye and lip region detection for 50 epoch cases is 97.7% and 91.0%, respectively.

Design and Implementation of Scalable VOD System on Linux (Linux상에서 확장 가능한 VOD시스템의 설계 및 구현)

  • 김정원;김인환;정기동
    • Journal of Korea Multimedia Society
    • /
    • v.2 no.3
    • /
    • pp.265-276
    • /
    • 1999
  • Video on Demand (VOD) system is definitely one of main applications in upcoming multimedia era. In this research, we have designed and implemented a host-based scalable VOD system (SVOD) which is composed of low cost PC servers and runs on Linux kernel that is currently spotlighted in enterprise and research domains. Our contribution is as follows: first, the previous Ext2 file system was modified to efficiently support continuous media like MPEG stream. Second, the storage server features a host-based scalable architecture. Third, a software MPEG decoder was implemented using Microsoft's DirectShow$\circledR$COM. Finally, flow control between client and server is provided to suppress overflow and underflow of client circular buffer and supports FF VCR operation. We have known that it is possible to develop a thread-based and scalable VOD system on low cost PC servers and free Linux kernel.

  • PDF

Non-parametric Background Generation based on MRF Framework (MRF 프레임워크 기반 비모수적 배경 생성)

  • Cho, Sang-Hyun;Kang, Hang-Bong
    • The KIPS Transactions:PartB
    • /
    • v.17B no.6
    • /
    • pp.405-412
    • /
    • 2010
  • Previous background generation techniques showed bad performance in complex environments since they used only temporal contexts. To overcome this problem, in this paper, we propose a new background generation method which incorporates spatial as well as temporal contexts of the image. This enabled us to obtain 'clean' background image with no moving objects. In our proposed method, first we divided the sampled frame into m*n blocks in the video sequence and classified each block as either static or non-static. For blocks which are classified as non-static, we used MRF framework to model them in temporal and spatial contexts. MRF framework provides a convenient and consistent way of modeling context-dependent entities such as image pixels and correlated features. Experimental results show that our proposed method is more efficient than the traditional one.

Multiple Texture Image Recognition with Unsupervised Block-based Clustering (비교사 블록-기반 군집에 의한 다중 텍스쳐 영상 인식)

  • Lee, Woo-Beom;Kim, Wook-Hyun
    • The KIPS Transactions:PartB
    • /
    • v.9B no.3
    • /
    • pp.327-336
    • /
    • 2002
  • Texture analysis is an important technique in many image understanding areas, such as perception of surface, object, shape and depth. But the previous works are intend to the issue of only texture segment, that is not capable of acquiring recognition information. No unsupervised method is basased on the recognition of texture in image. we propose a novel approach for efficient texture image analysis that uses unsupervised learning schemes for the texture recognition. The self-organization neural network for multiple texture image identification is based on block-based clustering and merging. The texture features used are the angle and magnitude in orientation-field that might be different from the sample textures. In order to show the performance of the proposed system, After we have attempted to build a various texture images. The final segmentation is achieved by using efficient edge detection algorithm applying to block-based dilation. The experimental results show that the performance of the system Is very successful.

The clinical study on 1 case of stroke patient with symptoms of Sang-So(上消) (중풍환자(中風患者)의 상소증(上消證) 치험(治驗) 1례(例))

  • Lee, Eun-Suk;An, Hyo-Myug;Hwang, Kyu-Dong;Ko, Hyun
    • The Journal of Internal Korean Medicine
    • /
    • v.21 no.5
    • /
    • pp.873-876
    • /
    • 2000
  • So-gal(消渴) is a oriental medical pathologic state that is characterized by 3 major symptoms - thirst, polyphasia, polyuria - of which especially thirst features Sang-so(上消). Diabetes mellitus and So-gal(消渴) have many points in common. But there are considerable differencies between them, because they have obviously different diagnostic bases from each other. That is, oriental medicine places more weight on symptoms than clinopathologic laboratory reports. This case of stroke patient complained of severe thirst and additional dryness in the mouth, choking sensation in the chest, hidrosis, insomnia, dark colored urine, constipation. The patient had no clinical history of diabetes mellitus. Based on oriental medical standards, we diagnosed the case as Sang-so(上消). Several herbal medicines were dispensed for 48 days. And considerably effective result were obtained. Object : 1 case of stroke patient who complained severe thirst. Medication : . Seonghyangjeonggisan for 5 days (2000. 6. 9 - 6. 13.) . Paljeongsan for 21 days (2000. 6. 14. -7. 5) . Ikwonsan for 8 days (2000. 7. 6 - 7. 13) . Okcheonsan for 14 days (2000. 7. 14 - 7. 27) Result : 1. After administration of Paljeongsan, dark colored urine turned normal. 2. After administration of Ikwonsan, dryness in the mouth improved. 3. After administration of Okcheonsan, thirst significantly improved. Constipation, choking sensation, hidrosis, insomnia also improved.

  • PDF

Comparative Analysis of Dragon Patterns Found in Contemporary Fashion between Korea and Japan (한국과 일본의 현대복식에 나타난 용양의 비교분석)

  • 남미현
    • Journal of the Korea Fashion and Costume Design Association
    • /
    • v.3 no.1
    • /
    • pp.57-76
    • /
    • 2001
  • This study was intended to make a comparative analysis of the plastic features of Korean and Japanese dragon patterns found in the process of recreating traditions in comtemporary fashion based on the investigation into the style of expression in relation to the origin, formative evolution, symbolism and traditional costume of the dragon. The form of the dragon has evolved with some similarity and peculiarity between both countries and been changed into many kinds and diverse forms such as the humorous dragon pattern of the Yi Dynasty and the simplified and designed dragon pattern symbolizing the Japanese family crest and the like, Its symbolism has lasted in terms of the sacrificial object, royal power, good omen, Buddhist guardian and the like. There is a difference in the aesthetic sense due to the different traditions and cultural background between Korea and Japan, and the dragon pattern found in the process of recreating the tradition in comtemporary fashion manifested itself as the peculiar aspect. An attempt was made to make a comparative analysis of the dragon pattern found in comtemporary fashion between Korea and Japan. The following results were obtained: First, the commonality between both countries was to make a contemporary expression of the dragon pattern, which was expressed in a realistic form because of a traditionally inherent strong image of the dragon. On the other hand, the designed dragon pattern rarely found expression. It can be said that carefully treating the dragon pattern is attributed to the Oriental thinking like this. Second, Korean people have arranged one or more simplified dragon patterns taking on a form of the coiling dragon in the composition of the scattered point and made a comtemporary expression of them by the contrast of black and white shading in Korea. And the humorous form of the dragon pattern manifested itself in the Yi Dynasty. On the other hand, the case of printing the dragon pattern in the black dragon sword of all over the Kabuki costume in a pictorial composition has frequently appeared in Japan. And Japanese people have expressed its lightness and briskness rather than the dignity and strength that the dragon pattern gives with the use of strong color tones and new materials.

  • PDF

A Study on the Formation Factors of Grotesque Image expressed in Fashion (복식에 표현된 그로테스크 이미지의 형성 요인에 관한 연구)

  • 남미현
    • Journal of the Korea Fashion and Costume Design Association
    • /
    • v.4 no.3
    • /
    • pp.43-54
    • /
    • 2002
  • Some factors had influence upon the grotesque image formation expressed in fashion: for instance, thanatos, religions, fin de siecle (end of the century), the aesthetics of ugliness, subculture group's resistance and technology development, etc. Those factors have formed a grotesque while exchanging influence each other, and have following features: First, the thanatos, which is destructive and aggressive instinct of the inner world of human being, creates frightening object and motif to form the images of grotesque. Second, from religious point of view, the church made the Devil a tool for maintenance of power: They manipulated physical body and give a damage to it to sublimate it in holy existence, so that they could feel catharsis. Third, there was fin de siecle (end of the century) to let people have negative life attitude, such as uneasiness on following century, eschatology, skepticism and nihilism, etc. Fourth, the ugliness having unpleasantness and disharmony occupies governing position when our society becomes corrupted and uneasy, and the aesthetics of ugliness discloses the inconsistency of ideal and beautiful life in the grotesque images. Fifth, subculture groups, i.e., the lower classes, homosexual and the youth's group, etc, form the grotesque images by political and ideological resistance, complaints and specific identity, etc concerning governing culture keeping traditional ethics consciousness. Sixth, recent technology development has destroyed a boundary between human being and machinery, and bio-technology development has created transplant operation, plastic operation and other human body transformation operations, and genome research, etc has raised human being's identity.

  • PDF

Histogram Based Hand Recognition System for Augmented Reality (증강현실을 위한 히스토그램 기반의 손 인식 시스템)

  • Ko, Min-Su;Yoo, Ji-Sang
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.15 no.7
    • /
    • pp.1564-1572
    • /
    • 2011
  • In this paper, we propose a new histogram based hand recognition algorithm for augmented reality. Hand recognition system makes it possible a useful interaction between an user and computer. However, there is difficulty in vision-based hand gesture recognition with viewing angle dependency due to the complexity of human hand shape. A new hand recognition system proposed in this paper is based on the features from hand geometry. The proposed recognition system consists of two steps. In the first step, hand region is extracted from the image captured by a camera and then hand gestures are recognized in the second step. At first, we extract hand region by deleting background and using skin color information. Then we recognize hand shape by determining hand feature point using histogram of the obtained hand region. Finally, we design a augmented reality system by controlling a 3D object with the recognized hand gesture. Experimental results show that the proposed algorithm gives more than 91% accuracy for the hand recognition with less computational power.

Construction of Theme Melody Index by Transforming Melody to Time-series Data for Content-based Music Information Retrieval (내용기반 음악정보 검색을 위한 선율의 시계열 데이터 변환을 이용한 주제선율색인 구성)

  • Ha, Jin-Seok;Ku, Kyong-I;Park, Jae-Hyun;Kim, Yoo-Sung
    • The KIPS Transactions:PartD
    • /
    • v.10D no.3
    • /
    • pp.547-558
    • /
    • 2003
  • From the viewpoint of that music melody has the similar features to time-series data, music melody is transformed to a time-series data with normalization and corrections and the similarity between melodies is defined as the Euclidean distance between the transformed time-series data. Then, based the similarity between melodies of a music object, melodies are clustered and the representative of each cluster is extracted as one of theme melodies for the music. To construct the theme melody index, a theme melody is represented as a point of the multidimensional metric space of M-tree. For retrieval of user's query melody, the query melody is also transformed into a time-series data by the same way of indexing phase. To retrieve the similar melodies to the query melody given by user from the theme melody index the range query search algorithm is used. By the implementation of the prototype system using the proposed theme melody index we show the effectiveness of the proposed methods.

Formal Semantics for Processing Exceptions (예외 처리를 위한 형식 의미론)

  • Han, Jung-Lan
    • The KIPS Transactions:PartA
    • /
    • v.17A no.4
    • /
    • pp.173-180
    • /
    • 2010
  • To specify a formal semantics is to do a significant part for design, standardization and translation of programming languages. The existing studies of a formal semantics for Java have a weak point to describe a clear and practical semantics for an efficient translation. It is necessary to do research for a formal semantics to specify a static and dynamic semantics clearly in order to do an efficient translation. This paper presents the improved Action Equation that specifies a formal semantics for Java to extend the research using Action Equation. The Action Equation is a practical and accurate specification that describes object-oriented programming features and handles exceptions. The specified Action Equation is compared to other descriptions, in terms of readability, modularity, extensibility, and flexibility and then we verified that Action Equation is superior to other formal semantics.