• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.11
• /
• pp.1088-1095
• /
• 2009

In this paper, we describe the reorientation method of distorted road sign by using projection transformation for improving recognition rate of road sign. RSR (Road Sign Recognition) is one of the most important topics for implementing driver assistance in intelligent transportation systems using pattern recognition and vision technology. The RS (Road Sign) includes direction of road or place name, and intersection for obtaining the road information. We acquire input images from mounted camera on vehicle. However, the road signs are often appeared with rotation, skew, and distortion by perspective camera. In order to obtain the correct road sign overcoming these problems, projection transformation is used to transform from 4 points of image coordinate to 4 points of world coordinate. The 4 vertices points are obtained using the trajectory as the distance from the mass center to the boundary of the object. Then, the candidate areas of road sign are transformed from distorted image by using homography transformation matrix. Internal information of reoriented road signs is segmented with arrow and the corresponding indicated place name. Arrow area is the largest labeled one. Also, the number of group of place names equals to that of arrow heads. Characters of the road sign are segmented by using vertical and horizontal histograms, and each character is recognized by using SAD (Sum of Absolute Difference). From the experiments, the proposed method has shown the higher recognition results than the image without reorientation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.5
• /
• pp.339-345
• /
• 2016

In general, mosaic blocks are used to hide some specified areas, such as human faces and disgusting objects, in an input image when images are uploaded on a web-site or blog. This paper proposes a new algorithm for robustly detecting grid mosaic areas in an image based on the edge projection. The proposed algorithm first extracts the Canny edges from an input image. The algorithm then detects the candidate mosaic blocks based on horizontal and vertical edge projection. Subsequently, the algorithm obtains real mosaic areas from the candidate areas by eliminating the non-mosaic candidate regions through geometric features, such as size and compactness. The experimental results showed that the suggested algorithm detects mosaic areas in images more accurately than other existing methods. The suggested mosaic detection approach is expected to be utilized usefully in a variety of multimedia-related real application areas.

• Archives of Plastic Surgery
• /
• v.46 no.2
• /
• pp.129-134
• /
• 2019

Background Nipple-areolar complex (NAC) reconstruction is the final stage of breast reconstruction. Ideal reconstruction of the NAC requires symmetry in position, size, shape, texture, pigmentation, and permanent projection, and although many technical descriptions of NAC reconstruction exist in the medical literature, there is no gold standard technique. The technique devised by the authors is very versatile, with excellent results, and it enables 1-step reconstruction with optimal results in terms of shape and nipple projection. Methods Our technique consists of a combination of modified local flaps and a full-thickness skin graft. Patients were observed for 18 months to estimate the amount of retraction. This procedure was performed in 40 patients, four of them bilaterally. The duration of the follow-up was 30 months. Complications occurred in 10% of patients, and included infections (5%), ischemia (2.5%), and hematoma (2.5%). Results No cases of total nipple necrosis were reported. The NAC shape remained optimal in all cases, with a very small reduction of the vertical and horizontal diameters of the areola, which maintained its designed round shape well, and negligible retraction in the diameter and projection of the nipple. Conclusions The oval technique represents a major step forward, involving a combination of existing techniques, such as the C-V flap and the cutaneous graft, to achieve excellent results regarding areola shape and nipple projection, significantly reducing the cases of nipple ischemia. These results were substantially obtained through subcutaneous equatorial sutures, skin grafting, and flattening of the apexes of the flap.

• Journal of Positioning, Navigation, and Timing
• /
• v.3 no.1
• /
• pp.25-30
• /
• 2014

Differential Global Positioning System-Correction Projection (DGPS-CP) algorithm, which has been suggested as a method of correcting pre-calculated position error by projecting range-domain correction to positional domain, is a method to improve the accuracy performance of a low price GPS receiver to 1 to 3 m, which is equivalent to that of DGPS, just by using a software program without changing the hardware. However, when DGPS-CP algorithm is actually realized, the error is not completely eliminated in a case where a reference station does not provide correction of some satellites among the visible satellites used in user positioning. In this study, the problem of decreased performance due to the difference in visible satellites between a user and a reference station was solved by applying the Multifunctional Transport Satellites (MTSAT) based Augmentation System (MASA) correction to DGPS-CP, instead of local DGPS correction, by using the Satellite Based Augmentation System (SBAS) operated in Japan. The experimental results showed that the accuracy was improved by 25 cm in the horizontal root mean square (RMS) and by 20 cm in the vertical RMS in comparison to that of the conventional DGPS-CP.

• Proceedings of the KIEE Conference
• /
• 1987.07b
• /
• pp.1100-1103
• /
• 1987

In this paper, we report a method for the primitive segments extraction from printed Korean characters without thinning as a preliminary stage to design an efficient recognition system. The primitive segments are defined by fundamental subpatterns which are vertical(I), right sloping(/), left. sloping(\). horizontal(-), and circular segment(o). The circular segment among the five kinds of segment is different from the others in geometrical properties. Therefore, at first, the circular segment is extracted by using the closed circle of the inner boundary and the geometrical characteristics of its outer. Next, linear segments are separated from the character pattern by means of a directional coding method. Finally, primitive segments are extracted from each set of linear segments by using a projection profile which involves the fact whether the segment has branches or not. The experimental results show that this method reduces computation time and storage space in comparision with the existing methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.784-787
• /
• 2006

In this paper, we propose a method for nonlinear grapheme segmentation in Korean printed character type classification. The characters are subdivided into six types based on character type information. The feature vector is consist of mesh features, vertical projection features and horizontal projection features which are extracted from gray-level images. We classify characters into 6 types using Back propagation. Character segmentation regions are determined based on character type information. Then, an optimal nonlinear grapheme segmentation path is found using multi-stage graph search algorithm. As the result, a proposed methodology is proper to classify character type and to find nonlinear char segmentation paths.

• The KIPS Transactions:PartD
• /
• v.17D no.6
• /
• pp.463-470
• /
• 2010

We presented a very fast and robust method of text line segmentation based on the DCT blocks of color image without decompression and binary transformation processes. Using DC and another three primary AC coefficients from block DCT we created a gray-scale image having reduced size by 8x8. In order to detect and locate white strips between text lines we analyzed horizontal and vertical projection profiles of the image and we applied a direct markov model to recover the missing white strips by estimating hidden periodicity. We presented performance results. The results showed that our method was 40 - 100 times faster than traditional method.

• Korean Journal of Applied Biomechanics
• /
• v.23 no.4
• /
• pp.295-306
• /
• 2013

The purpose of this study was to provide high school male shot putters training methods of gliding and delivery motion through comparative analysis of kinematic characteristics. To accomplish this purpose, three dimensional motion analysis was performed for the subjects(PKC, KKH, YDL) who participated in high school male shot putter competition on 92nd (2011), 93rd (2013) National Sports Festival. The subjects were filmed by four Sony HXR-MC2000 video cameras with 60 fields/s. The three-dimensional kinematic data of the glide, conversion and delivery phase were obtained by Kwon3d 3.1 version. The data of the shoulder rotational angles and projection angles were calculated with Matlab R2009a. The following conclusions had been made. With the analysis of the gliding and stance length ratio, the gliding length was shorter at the TG than the SG with short-long technique but the gliding and stance length ratio was 46.8:53.2% respectively. The deviation of the shots trajectory from APSS(Athlete-plus-shot-system) revealed that the PKC showed similar to "n-a-b-c-I" of skilled S-shape type, KKH and YDL showed "n-a-d-f-I'" of unskilled type. Furthermore, they showed smaller radial distance from the central axis of the APSS and the shots were away from the linear trajectory. From this characteristics, The PKC who performed more TG than SG had shorter glide with S-shape of APSS(skilled type) showed the better record than others with technical skill. But KKH and YDL had bigger glide ratio with "n-a-d-f-I'" of unskilled type and improved their records with technical factor. The projection factor had an effect on the record directly. Because PKC maintained more lower glide and transition posture with momentum transfer through COG's rapid horizontal velocity respectively the subject possessed the characteristics of high horizontal and vertical velocity with large turning radius from shot putter to APSS.

• Proceedings of the Korea Contents Association Conference
• /
• 2015.05a
• /
• pp.53-54
• /
• 2015

Optical music recognition (OMR) systems have been developed in recent years. However, chord symbols that play a role in a music sheet have been still disregarded. Therefore, we aimed to develop a proper approach to recognize these chord symbols. First, we divide the image of chord symbol into small segments in horizontal by a method based on vertical projection. Then, the optimal combination of these segments is found by using a lexicon-driven word scoring technique and a nearest neighbor classifier. The word that corresponds to the optimal combination is the result of recognition. The experiment gives an impressive result with accuracy 97.32%.

• Journal of the Korean housing association
• /
• v.12 no.2
• /
• pp.77-85
• /
• 2001

Along with the development of creative design ideas, how to effectively present design concepts is also an important consideration on housing plan process. This could consequently make it possible to automate presentations. In spite of such needs of presentations any significant efforts for the systematic design presentation have not been made yet. The research goals established in order to solve these problems are to develop structures of presentation and analyze the cases of it. This paper explains structures of housing plan presentations in two ways: the compositional elements of panel presentations and the relationships among the elements. The elements include a project title, a synopsis, design concepts, building layouts, floor plan1 and 2, longitudinal and latitudinal elevations, sections, projection and perspective views, and model photographs. Among various relationships among panel compositional elements this study uses relationships based on the Gestalt theory, the balance theory by Rudolf Arnheim and the optical array theory by Gibson. The relationships investigated on the basis of the visual perception theories include the relationships between compositional elements and background space, visual weight balance, horizontal and vertical balances, grouping, and visual layout patterns.