http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
박정호,김혜숙,서재성,곽훈성,황형수 원광대학교 생산 및 자동화기술연구소 1994 생산.자동화기술연구소논문집 : 원광대 Vol.- No.1
In this paper, we propose a fuzzy inferencing algorithm to improve block classificaion considering the block characteristics in the classified VQ using DCT. For this we create fuzzy rules having the form "IF p is A and q is B THEN r is C". The "p is A and q is B" is called the antecedent and the "r is C" the consequent. "p is A" has five fuzzy sets using energy compaction of vertical and horizontal direction in DCT domain and the "q and B" four fuzzy sets using diagonal. The "r is C" gets seven another fuzzy classes following the block feature. By training the generated fuzzy rules using several images, twenty fuzzy rules having objective validity can be identified. Ultimately these rules apply fuzzy inference for a new input image to be classified into seven slcaaes. After classification, the vector quantization, the same with Aizawa's method, adopt to each class. Our proposed method(F-DCT-CVQ) shows that PSNR is increased by about 1-2 dB for 0.3 - 0.5(bpp) range, when the performance is compared with Aizawa's scheme.
이재철,김혜숙,서재성,곽훈성,김환용 원광대학교 생산 및 자동화기술연구소 1994 생산.자동화기술연구소논문집 : 원광대 Vol.- No.1
In general, model-based object recognition methods used adhoc techniques to decide whether or not an object model a given scene. However, to get the reasonable features between the model and data, the number of views needed may be large and the selection of view points may be critical In order to solve these problems, we propose a grid coding technique to extract the surfaces with a different orientation. Here, the objects are recognized using matched features such as the interior angle the elements for deciding the shape of surfaces. The observed objects are assumed to rest on a plane(base plane) in a scene which is "encoded" with light cast through a grid plane. Two orthogonal grid pattern are used, where each pattern is obtained with a set of equally spaced stripe marked on a glass. The scene is observed through a camera and the object surface orientation is determined using the projected pattern on the surface. Finally, the paper contains the simulation results of this prototype system for verfing simple blocks world.