• IEMEK Journal of Embedded Systems and Applications
• /
• v.3 no.1
• /
• pp.8-18
• /
• 2008

In this paper, we propose an efficient algorithm using wavelet transform for still image database retrieval. Especially, it uses only the lowest frequency sub-band in multi-level wavelet transform so that a retrieval system uses a smaller quantity of memory and takes a faster processing time. We extract different textured features, statistical information such as mean, variance and histogram, from low frequency sub-band. Then we measure the distances between the query image and the images in a database in terms of these features. To obtain good retrieval performance, we use the first feature (mean and variance of wavelet coefficients) to filter out most of the unlikely images. The rest of the images are considered to be candidate images. Then we apply the second feature (histogram of wavelet coefficient) to rank all the candidate images. To evaluate the algorithm, we create various distorted image databases using MIT VisTex texture images and PICS natural images. Through simulations, we demonstrate that our method can achieve performance satisfactorily in terms of the retrieval accuracy as well as the both memory requirement and computational complexity. Therefore it is expected to provide good retrieval solution for JPEG-2000 using wavelet transform.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.61-63
• /
• 2005

Retreiving indoor scene reference image from database using visual information is important issue in Robot Navigation. Scene matching problem in navigation robot is not easy because input image that is taken in navigation process is affinly distorted. We represent probabilistic framework for the feature matching between features in input image and features in database reference images to guarantee robust scene matching efficiency. By reconstructing probabilistic scene matching framework we get a higher precision than the existing feaure-feature matching scheme. To construct probabilistic framework we represent each image as Gaussian Mixture Model using Expectation Maximization algorithm using SIFT(Scale Invariant Feature Transform).

• Journal of Broadcast Engineering
• /
• v.2 no.1
• /
• pp.74-83
• /
• 1997

We have proposed a composite feature measure which combines the color and shape features of an image for image retrieval. We improved the performance of retrieval based on the efficient color quantization using the Lloyd-Max quanizer and on the Histogram matrix matching method which considers the spatial correlation of quantized color group. We also supplemented the color information using shape information with the Improved Moment Invarlants. We have tested our technique on Image database consisting of 200 actual trademark images. Our experimental results showed that our approach improved the performance compared to the previous method under the various situations such as rotation images, translation images, noise added images, gamma corrected images and so on. The efficiency of retrieval is found to be very high and experimental results are

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.48-52
• /
• 2008

In this paper, we propose a new selective subspace projection method in order to recognize the occlusive face image effectively. The conventional subspace projection method is project to basis image using a full image of face. The face recognition rate has reduced because the face characteristic is easy to be distorted by occlusion. To overcome this problem, the proposed method first decide to occlusion. If it hasn't an occlusion, we get the feature vectors with total basis projection using the conventional subspace projection method. If it has an occlusion, we get one with partial basis projection. We get better recognition rate than conventional PCA and NMF using AR face database with occlusive face images.

• Journal of Korean Society of Rural Planning
• /
• v.10 no.2 s.23
• /
• pp.35-42
• /
• 2004

This study aimed at establishing the multi-ranged approach on data acquisition technique for rural landscape planning, which tried categorization, grading and transferring of landscape elements in the more detailed level. For the systematic management of database for the topographic informations in the village level, a kind of the aerial photographing techniques with UAV(Unmanned Aerial Vehicle) was used and its resultant data for the landscape simulation of the rural village, which in turn helped the convenient approach to understanding of its comprehensive spatial structure. The image data from aerial photography was systematically processed through; First, after revision of the distorted one, the image map was adjusted with the topographical and cadastral maps. Second, the farm houses and buildings, and other facilities difficult to find out in the topographical map was digitally read from the adjusted image. The topographical landscape view of rural village was simulated on the base of DEM(Digital Elevation Model) and the 3-dimensional shapes of farm houses and buildings were automatically modelled using the input system developed by the author. In conclusion, the aerial image information adjusted with the edited maps could give more intuitive and detailed villagescape than the ordinary one and through landscape simulation of the rural village, its topography, features of houses/buildings and spatial distribution of land uses were effectively reproduced. And, by the linkage between field survey and photographed/simulated results of the typical landscape elements using hyper-link method, it would be expected to develop as an effective visualization technique of rural landscape.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.749-754
• /
• 2011

In this study, we propose the design of optimized pRBFNNs-based face recognition system using two-dimensional Image and ASM algorithm. usually the existing 2 dimensional face recognition methods have the effects of the scale change of the image, position variation or the backgrounds of an image. In this paper, the face region information obtained from the detected face region is used for the compensation of these defects. In this paper, we use a CCD camera to obtain a picture frame directly. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. AdaBoost algorithm is used for the detection of face image between face and non-face image area. We can butt up personal profile by extracting the both face contour and shape using ASM(Active Shape Model) and then reduce dimension of image data using PCA. The proposed pRBFNNs consists of three functional modules such as the condition part, the conclusion part, and the inference part. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of RBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to real-time face image database and then demonstrated from viewpoint of the output performance and recognition rate.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.9
• /
• pp.901-908
• /
• 2013

The introduction of industrial intelligent robot using vision sensor has been interested in automated factory. 2D and 3D vision sensors have used to recognize object and to estimate object pose, which is for packaging parts onto a complete whole. But it is not trivial task due to illumination and various types of objects. Object image has distorted due to illumination that has caused low reliability in recognition. In this paper, recognition method of complex shape object has been proposed. An accurate object region has detected from combined binary image, which has achieved using DoG filter and local adaptive binarization. The object has recognized using neural network, which is trained with sub-divided object class according to object type and rotation angle. Predefined shape model of object and maximal slope have used to estimate the pose of object. The performance has evaluated on ETRI database and recognition rate of 96% has obtained.

• Journal of the Korean Society of Costume
• /
• v.64 no.8
• /
• pp.20-36
• /
• 2014

This research aims to identify and analyze the expression elements and features of Goth style observed in clothing of unique characters in movies directed by Tim Burton, and to build the database on diverse features movie costumes, so that such data can be used to develop new fashion design. The research-classified features of Goth style into romanticism overturns Satanism, grief, and sensuality. The results are as follow; First, Goth expressed romanticism by reminding the gloom and fear of medieval times through the image of clowns, medieval knights, werewolves and vampires. Second, The costumes in Tim Burton's movies overthrew the rules in reality using flexible changes, ambiguity of gender, distorted human beings, half-man-half-beasts, and ghost images. Furthermore, the positive expression on characters in gloomy and fearful costumes showed the overturn of common idea and value system in a society. Third, Tim Burton created fear using the image of a live dead body, shape of a devil, shape of death. Also, accessories suddenly changed into arms in his movies. He expressed Satanism by positively describing satanic shapes and shapes meaning death. Next, characters in Tim Burton's movies are mainly losers, aliens or outsiders. Sorrow, alienation and darkness inside them expressed the sadness through embodiment of mean animals in darkness, masks, veils and extreme black costumes. Finally, Sensuality was rarely shown in Tim Burton's movies, but expressed in various ways including pursuit of new beauty in excessive exposure, skintight silhouette, suggestion on sexualized violence and frightfulness.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.2
• /
• pp.465-482
• /
• 1997

In this paper, we have studied on cinstructing code-recognition shstem by neural network according to a image process taking the DOT classification code stamped on tire surface.It happened to a few problems that characters distorted in edge by diffused reflection and two adjacent characters take the same label,even very sen- sitive to illumination ofr recognition the stamped them on tire.Thus,this paper would propose the algorithm for tire code under being cinscious of these properties and prove the algorithm drrciency with a simulation.Also,we have suggerted the MCBP network composing of multi-linked recognizers of dffcient identify the DOT code being tire classification code.The MCBP network extracts the projection balue for classifying each character's rdgion after taking out the prjection of each chracter's region on X,Y axis,processes each chracters by taking 7$\times$8 normalization.We have improved error rate 3% through the MCBP network and post-process comparing the DOT code Database. This approach has a accomplished that learming time get's improvenent at 60% and recognition rate has become to 95% from 90% than BckPropagation with including post- processing it has attained greate rates of entire of tire recoggnition at 98%.

• Cartoon and Animation Studies
• /
• s.37
• /
• pp.159-195
• /
• 2014

An animation film, , is a work that declared a perfect revival of Disney. It is considered that the success was the result of its impressive theme song and characters working influentially. The main characters let audience experience empathy as well as catharsis by building the image of women making their own future without relying on men, and among the characters, Elsa is still popular even if one year has passed since its premiere in Korea. In the narrative genre, the character's degree of completion is regarded to be so important that it can even determine the work's success or failure. Accordingly, to analyze the personality structure among the major components of character rising, this study focuses on the psychodynamics of fear and desire which determines the directions of thought or behavior. Fear is the emotion attributed not to a real threat but to an ominous assumption about the future. Because fear that is originated from the memory of any deficit or suppression distorts our sound needs, escaping from fear means facing the reality. To verify the unique psychodynamics of the characters, the researcher analyzed the hierarchy of their attitudes, psychological dispositions, and psychic functions by using 'MBTI Personality Typology'. According to the results, (1) Elsa and Anna are in a conflicting relationship in terms of psychic functions. Although they are the combination that shows the highest possibility of conflict, the two sisters overcome it basically grounded on fellowship and family love. (2) Although Hans and Kristoff, too, are against each other in terms of psychic functions, the two male characters do not interact with each other in the work. (3) Hans is a person equipped with psychic functions that can complement both Elsa and Anna the most effectively, but he abuses it and turns into the most fatal opponent to them. (4) Olaf is a type of person combining Anna's attitudes with Elsa's psychological dispositions. And according to the results of analyzing the frequency of expressing fear and desire, (1) Elsa employs overwhelming fear and Anna and others characters use desire as the major drive of their behavior. (2) Fear is the underlying deficit internalized in every character and is attributed to 'the deficit of family love', and as a result, they all share the pain of 'loneliness and isolation'. It is thought that analyzing psychodynamics will help us understand the character's growth tale, that is, the narration that they distort their desire for the first motive to avoid fear and end up being ruled by it, and also, they realize the underlying reason for the distorted desire in the process of getting rid of their own fear and reach self-healing. Lastly, regarding character rising in the animation, it is expected that the directions and analysis results of this research will be referred to as a database in creating characters and setting up relations among them.