跳到主要內容

臺灣博碩士論文加值系統

(35.172.223.251) 您好!臺灣時間:2022/08/11 21:58
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:黃惠俞
研究生(外文):Hui-Yu Huang
論文名稱:影像認知與回想之研究
論文名稱(外文):On the Study of Image Understanding and Recall
指導教授:許文星陳永盛陳永盛引用關係
指導教授(外文):Wen-Hsing HsuYung-Sheng Chen
學位類別:博士
校院名稱:國立清華大學
系所名稱:電機工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2002
畢業學年度:90
語文別:中文
論文頁數:213
中文關鍵詞:自我組織特徵圖影像語意描述影像認知索引處理回想處理
外文關鍵詞:self-organizing maplinguistic meaning descriptionimage understandingindexing processrecall process
相關次數:
  • 被引用被引用:1
  • 點閱點閱:305
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:2
影像認知與回想之研究
研究生: 黃惠俞 指導教授: 許文星教授
共同指導: 陳永盛教授
國立清華大學 電機工程學系
摘 要
隨著科技的發達及電腦計算速度不斷的提昇,對影像處理已不在局限於黑/灰白影像,而是走向多元的彩色世界中,雖然現存的影像處理與計算機視覺等領域,已能夠利用電腦很精確的處理彩色訊息,但囿於目前對彩色的研究大都偏向光及物理特性 (如三原色,Red、Green、Blue),利用其物理特性協助彩色影像處理。對於人類對彩色影像的直覺反應及語意 (image linguistic meaning) 的表達之機制則屬跨研究領域的。因此之故,目前電腦在處理影像方面的問題大多偏向以工程的觀點來處理的較多。然而在人類觀看影像時,其乃透過視覺神經傳遞訊息到視覺皮質區及其它相關的皮質區的相互反應及作用的結果,並基於人類的知識及經驗,可以快速的辨識所看到的物體意義。如藍天、建築物等。或當接受到外在的語意訊息時如天空等,人類會回想在記憶之中所謂的天空影像之外觀、結構、及空間位置等,及其隸屬於此物體的語意。亦既在視覺皮質區中會浮現模糊的物體影像,並藉以進一步的分析物體特徵及物體重組。此浮現的模糊影像,我們稱之為初級視覺影像(primary visual image)或心理影像(mental image)。 根據此影像的屬性及結構等特徵,在人類知識庫中找到相對應的資料,並適當的給予影像中的物體人類的語意(linguistic meaning)表達。 換言之,當人眼接受外在景物刺激時,既可做聚類分群及給定隸屬的語意,並可從中獲得其相互的關連性。因此基於對人類直觀上的反應及影像處理之機制的探討,本論文提出一個基於人類視覺認知系統對彩色影像中之物體的語意解析及物體重現的研究,而藉此對人類的視覺認知能有初步的了解,並可應用到其他的影像處理技術之改良上。
為了建構此一個具有人類般處理影像訊息能力的彩色影像處理系統,我們利用總體到細節(top-down)及下而上(bottom-up)的處理流程,以漸進式的程序方式,從低階技術分析局部的影像特性,到高階的分析技術給予物體語意的描述,並進一步利用這些特徵重現、回想原影像。就低階的分析技術而言,主要是決定區域影像的特性,如色彩(color)、紋理(texture)、邊緣成分(edge elements)、臨界值(thresholding) 等。中階分析技術則是根據區域特性決定整體的屬性,如邊界(boundaries)、區域(regions)、物體(objects)等。最後經由高階分析系統中之人工智慧技術(如專家系統定律、經驗法則及關聯性),提供影像或景物一些語意的描述。在下而上(bottom-up)的處理過程上,則是主動的對由視覺接收的訊息加以編碼及鑑定此訊號的基本特性。因此屬於低階影像處理技術。而總體到細節(top-down)的處理,則是藉由儲存在記憶中之知識的協助,進一步辨認不完整的感覺訊息。因此屬於高階的影像處理技術。基於此,我們的系統主要架構在這處理流程的機制上,並可獲得不錯的結果。
基於以上的架構,我們希望開發一套語意模組的系統,經過系統的處理,可獲得影像中的基本元件(如天空、城堡等等),對這些元件,我們的表達方式除了給予關鍵字之外,並把它的上位或下位的文法關係描述出來,以語意模組來描述一張影像。給予物體元件語意的描述是基於對物體區域做特徵擷取,索引處理及推論法則資料庫的建構,藉此可判斷物體的語意及其相關的資訊攝取。我們採用色彩、紋理,空間關聯性等特徵,對物體做低階的分析,爾後進一步對此特徵加以索引處理,設定一組適當的索引值,並利用這些索引值,建構語意資料庫。經推論法則的運算後,既可獲得影像中基本物體元件語意的描述。另外經由語意的描述過程中,思考回想我所要重建的構圖,並從現有的資料庫之中,根據語意的描述,而可以重建我所要的一張影像。而這重建的影像並非真實的影像而是視覺影像(imagination image)。因此,在這個數位影像的時代,很多人所建立的數位影像資料庫,全世界都可共用這些資源,而不一定自己去拍攝或建立影像資料庫,經過我的系統,每個人就可以儘快的把他所構想的圖案建立起來。此系統可廣泛應用到物體重建、電腦輔助景觀或室內設計等。
藉由系統的建立及發展,亦可讓人類的辨識能力、認知的機制及思考組織的能力能有更進一步的了解,並將其應用到電腦視覺系統上,使電腦視覺系統的運作更具人性化的處理能力。
More recently, technological advances have made it
possible to process large amounts of image data; the main
viewpoint of these developed techniques is generally based on the engineering viewpoint. That is, the scheme of these techniques is focused on the quality of results and the development of algorithms. Additionally, one important viewpoint called human vision mechanism is also usually to be used in the recent researches; hence, human vision mechanism is significant information. In order to further realize their potential in the application of image processing, a system for the viewpoint of human-vision base needs to be developed.
Based on human-vision base properties, the top-down
process and bottom-up process are usually adopted techniques and
applied to diverse researches. In our proposed system, we utilize these properties to process from low-level scene analysis for local image properties to high-level scene analysis for semantic description.
For bottom-up process, a image segmentation algorithm is
proposed based on Self-Organizing Map (SOM) methodology which
takes into account the color similarity and spatial relationships of objects within an image. Based on the features of color similarity, an image is first segmented into coarse cluster regions, named planes, using SOM_1 algorithm with a labeling process. The final segmented regions are treated by computing the spatial distance between any two planes and using SOM_2 algorithm with a labeling process. Moreover, the selection of parameters, named the number of iterations and output nodes for SOM algorithm is also discussed in this approach. The segmented objects, which are similar to human perceived, are represented for the proposed approach. Experiments show that this approach is reliable and feasible. It can provide the primary information to further investigate the image content.
For top-down process, we have also investigated the image
content descriptions which adopt the image features and spatial
information. A forward-recall image processing system has been
proposed which contains the forward process with a semantic
description for each segmented object and the recall process with redrawing each of segmented objects based on the semantic
description and spatial location. The forward process involving
the bottom-up and top-down processes is represented the semantic
interpretation obtained using the features of color, texture,
spatial relationships that represent to the indexes, and then
using these indexes to construct the linguistic inference rule
database based on human experiences and knowledge. The
corresponding features for each object in an image can be
obtained. Furthermore, each region can be represented its
corresponding interpretation by operating the inference rule
decision in linguistic data base. Each region, in general, can be almost exacted to interpret its semantic meaning description in our experiments.
Through our researches mentioned above, a human-vision
base image understanding system containing image segmentation,
linguistic meaning interpretation and recall is proposed.
TABLE OF CONTENTS
Abstract in Chinese      i
Acknowledgements in Chinese     iv
Abstract in English       vi
Acknowledgements in English     viii
ContentsS       ix
List of Figures        xiii
List of Tables  xix
Chapter 1 Introduction        1
1.1 Motivation and Objectives for this Research 1
1.2 Literature Survey 5
1.2.1 Neural Netowork Models 5
1.2.2 Image Segmentation Methods 9
1.2.3 Image Indexing and Content-based Image retrieval 11
1.2.4 Color Space Selection 13
1.3 Thesis Organization 14
Chapter 2 Basic System Framework    17
2.1 Preamble 17
2.2 System Design 18
2.2.1 Image Segmentation Model 19
2.2.2 Image Description Scheme    26
2.2.3 Image Recall Scheme    30
Chapter 3 Gray Image Segmentation and Association 31
3.1 The Segmentation Process    33
3.1.1 Gray Image Segmentation Model 35
3.1.2 The SOM Algorithm for Gray Image 36
3.1.3 The Dissimilarity Metrics Computation 38
3.1.4 Summary of the whole Segmentation Process 40
3.1.5 Illustration of a Gray Image Segmentation 41
3.2 Association Process         45
3.2.1 Morphology and Labeling Process 50
3.2.2 Regions Combination using Fuzzy Relation 52
3.2.3 Region Boundary Detection and Construction
of a regions'' Relations 56
3.3 Experimental Results 58
3.4 Summary 62
Chapter 4 Color Image Segmentation 65
4.1 The Proposed Method 65
4.1.1 Color Image Segmentation Model 68
4.1.2 The HVC Color Space 69
4.1.3 The SOM1 Algorithm for Color Image 70
4.1.4 The Relationships among Spatial Feature 73
4.1.5 The SOM2 Algorithm 74
4.2 Experimental Results 75
4.2.1 Setting Parameters 75
4.2.2 Training and Testing 77
4.2.3 Summary of Comparisons 81
4.2.4 Discussions 88
4.3 Summary 89
Chapter 5 Image Description and Recall System 95
5.1 Introduction 96
5.2 Proposed Approach 98
5.2.1 Region Feature Extraction 100
5.2.2 Indexing Definition and Processing 105
5.2.3 Semantic Description Representation 108
5.3 Recall Process 116
5.4 Experimental Results 117
5.4.1 Experimental Setup 117
5.4.2 Results of Semantic Description and Recall 117
5.5 Summary 131
Chapter 6 Further Experimental Results 137
6.1 Implementations 137
6.1.1 Image Segmentation Representation 137
6.1.2 Image Description Representation 139
6.2.3 Image Recall Representation 148
6.2 Summary 148
Chapter 7 Conclusions 151
7.1 Contributions 151
7.2 Future Directions 152
Appendices
A Bookback Segmentation Scheme 155
A.1 The Algorithm 155
A.2 Results and Concluding Remarks 162
B Fuzzy Operations and its Relationships 167
B.1 Fuzzy Operations and Image Histogram 167
B.2 Linguistic Meaning 170
C Spatial Position Assignment and Indexing Processing 173
Bibliography 175
List of Publications 185
Vitae 187
References
[1] C. T. Morgan and R. A. King, Introduction to Psychology, McGrow-Hill Inc.
New York, three edition, 1966.
[2] J. Hassett, Psychology in Perspective, Harper and Row, Publishers, Inc.,
New York, 1984.
[3] E. M. Riseman and A. R. Hanson, " A metholodology for the development
of general knowledge-based vision systems," in Vision, Grain, and Cooperative Computation,
M. A. Arbib and A. R. Hanson, Eds., U.S.A., 1987, pp. 285-328, the MIT press.
[4] A. G. Reynolds and P. W. Flagg, Congitive psychology, Little, Brown
and company, Boston, second edition, 1983.
[5] Y. S. Chen and Y. C. Hsu, "Computer vision on a colour blindness plate,"
Image and Vision Computing, vol. 13, no. 6, pp. 463-478, 1995.
[6] M. A. Fischler and O. Firschein, Intelligence: the Eye, the Brain , and the Computer,
Addision-Wesley Pub. Com., U.S.A., 1987.
[7] M. M. Gupta, "On the cognitive computing:perspectives," in Fuzzy Computing:
Theory, Hardware and Application, M.M. Gupta and T. Yamakawa, Eds., North Holland, 1988,
pp. 7-10, Elsevier Science Publishing, Inc.
[8] H. J. Zimmermann, "Fuzzy sets," Information and Control, vol. 8, pp. 338-352, 1965.
[9] L. A. Zadeh, "Fuzzy sets," Information and Control, vol. 8, pp. 338-353, 1965.
[10] H. Y. Huang, Y. S. Chen, and W. H. Hsu, "Bookback segmentatin in a bookrack image,"
Journal of the Chinese Institute of Engineers, vol. 24, no. 6, pp. 735-743, 2001.
[11] S. Saykin, Neural Networks: a comprehensive foundation, Mac,illan Colledge Publishing
Company, Inc., U.S.A., 1994.
[12] D. D. Lee, "A discrete sequential bidirectional assoicative memory for multistep
pattern recognition," Pattern Recognition Letters, vol. 19, pp. 1087-1102, 1998.
[13] H. Iyatimi and M. Hagiwara, "Knowledge extraction from scenery images and the
recogintion using fuzzy inference neural networks," in Proc. IEEE Int. Conf. on System,
Man and Cybernetics, 1998, vol. 5, pp. 4486-4491.
[14] E. Sanchez, "Fuzzy logic and neural networks in artificial intelligence and
pattern recognition," in Proc. SPIE Stochastic and Neural Methods in Signal Processing,
Image Processing, and Computer Vision, San Diega, California, 1991, vol. 1569, pp. 254-259.
[15] J. Huang, S. Ravikumar, M. Mitra, W. J. Zhu, and R. Zabih,"Spatial color indexing
and application," International Hournal of Computer Vision, vol. 35, no. 3, pp. 245-268, 1999.
[16] T. Nishina and M. Hagiwara, "Fuzzy inference neural network," Neruocomputing,
vol. 14, pp. 223-239, 1997.
[17] H. Y. Huang, Y. C. Chen, and W. H. Hsu, "Primary-view perception on a gray image:region
segmentation and association," Journal of the Chinese Institute of Engineers, vol. 24, no. 2,
pp.221-235, 2001.
[18] H. Y. Huang, Y. C. Chen, and W. H. Hsu, "A self-organizing map approach to segmentation
of color image," in Computational Intelligence and Application, N. E. Mastorakis, Ed.,
New York, 1999, pp. 336-341, World Scientific and Engineering Society.
[19] Y. S. Lo and S. C. Pei, "Color image segmentaitn using locak histogram and self-organization
of Kohonen feature map," in Proc. ICIP''99 Int. Conf. on Image Processing, 1999. vol. 3, pp232-235.
[20] S. Rout, P. S. Seethalakshmy, and J. Majumdar, "Multi-model image segmentatin using a
modified Hopfield neural neetwork," Pattern Recognition, vol. 31, no. 6, pp. 743-750, 1998.
[21] J. Moreira, "Neural-based color image segmentatin and classificiation using self-organizing maps."
in Anais do IX SIBGRAPI, 1996, pp47-54.
[22] M. M. Gupta and G. K, Knopf, Neuro-vision Systems: principles and application,
IEEE Neural Newtork Council, IEEE Press, 1994.
[23] P. K. Simpson, Artificial Neural Systems: fundations, paradigms, applications, and implementations,
Pergamon Press, U.S.A., first edition, 1990.
[24] T. Kohonen, Selg-Organization and Associative Memory, Springer-Berlag, New York, second edition, 1989.
[25] Y. W. Lim and S. U. Lee, "On the color image segmentaitn algorithm based on the
thresholdong and the fyzzt c-means techniques," Pattern Recognition, vol. 23, no. 9,
pp. 935-952, 1990.
[26] J. C. Noordam, W. H. A. M. van den broek, and L. M. C. Buydens, "Geometrically guided fuzzy
c-means clustering for multivariate image segmentation," in Proc. IEEE 15th ICPR In. Conf. on
Pattern Recognition, 2000, vol. 1, pp. 462-465.
[27] D. X. Zhong and H. Yan, "Color image segmentatin using color space analysis and fuzzy clustering,"
in Proc. IEEE Signal Processing Society Workshop, Neural Networks for Signal Processing X, 2000,
vol. 2, pp. 624-633.
[28] R. Schettini, "A segmentation algorithm for color image," Pattern Recognition Letters,
vol. 14, pp. 499-506, 1993.
[29] A. Tremeau and N. Borel, "A region growing and merging algorithm to color segmentaiton,"
Pattern Recognition, vol. 30, no. 6, pp. 1191-1203, 1997.
[30] A. Moghaddamzadeh and N. Bourbakis, "A fuzzy region growing approach for segmentatin of color images,"
Pattern Recognition, vol. 30, no. 6, pp.867-881, 1997.
[31] E. Saber, A. M. Tekalp, and G. Bozdagi, "Fusion of color and edge information for improved
segmentation," Image and Vision Computing, vol. 15, pp. 769-780, 1997.
[32] D. Zugaj and V. Lattuati, "A new approach of color images segmentation based on fusing region
and edge segmentatins outputs," Pattern Recognition, vol. 31, no. 2, pp. 105-113,1998.
[33] D. Zugaj and V. Lattuati, "Perceptual grouping of natural images for CBIR," in Proc. 15th Int. Symposium
on Signal Processing and Its Applications, 1999, vol. 2, pp. 923-926.
[34] M. I. Chowdhury and J. A. Robinson, "Improving image segmentation using edge information," in Canadian
Conf. on Electrical and Computer Engineering, 2000, vol. 1, pp. 312-316.
[35] C. L. Huang, T. Y. Cheng, and C. C. Chen, "Color images'' segmentation using scale space filter and
markov random field," Pattern Recognition, vol. 25, no. 10, pp. 1217-1229, 1992.
[36] J. Liu and Y. H. Yang, "Multiresolution color image segmentatin," IEEE Trans. Pattern Anal. Mach. Intell.,
vol. 16, no. 7, pp. 689-700, 1994.
[37] P. Andrey and P. Tarroux, "Unsupervised segmentation fo markov random field modeled textured images using
selectionist relaxation," IEEE Trans. Pattern Anal. Mach. Intell., vol. 20, no. 3, pp.2520262, 1998.
[38] E. Y. Kim, S. H. Park, and H. J. Kim, "A genetic algorithm-based segmentatin of markov random field modeled images,"
IEEE Signal Processing Letters, vol. 7, no. 11, pp. 301-303, 2000.
[39] A. Verikas, K. Malmqvist, and L. Vergman, "Color image segmentation by modular nerual network,"
Pattern Recognition Letters, vol. 18, pp. 173-185, 1997.
[40] P. Campadelli, D, Medici, and R. Schettini, "Color image segmentation using Hopfield networks,"
Image and Vision Computing, vol. 15, pp. 161-166, 1997.
[41] C. Faloutsos, R. Barberm M. Flickner, J. Hafner, W. Nivlack, and D. Petkovic, "Efficient and effective querying
by image content," Journal of Intelligent Information Systems, vol. 3, pp. 231-262, 1994.
[42] H. Atmaca, M. Bulut, and D. Demir, "Histogram based fuzzy Kohonen clustering network for image segmentaiton,"
in Proc. IEEE Int. Conf. on Image Processing, 1996, vol. 2, pp. 951-954.
[43] L. Shafarenko, M. Petrou, and J. Kittler, "Histogram-based segmentation in a perceptually uniform color space,"
IEEE Trans. on Image Processing, vol. 7, no. 9, pp. 1354-1358, 1998.
[44] M. Tico, T. Haverinen, and P. Kuosmanen, "An unsupervised method of rough color image segmentation," in Conf.
Record 33th Asilomar Conf. on Signals, Systems, and Computers, 1999, vol. 1, pp. 58-62.
[45] C. Amoroso, E. Ardizzone, V. Morreale, and P. Storniolo, "A new technique for color image segmentation,"
in Proc. Int. Conf. on Image Analysis and Processing, 1999, pp. 352-257.
[46] H. D. Cheng and Y. Sun, "A hierarchical approach to color image segmentation using homogeneity," IEEE Trans.
on Image Processig, vol. 9, no. 12, pp. 2071-2082, 2000.
[47] G. Healey, "Segmentation images using normaized color," IEEE Trans. on Systems, Man, and Cybernetics,
vol. 22, no. 1, pp. 64-73, 1992.
[48] N. R. Pal and S. K. Pal, "A review on Image segmentation techniques," Pattern Recognition,
vol. 26, no. 9, pp. 1277-1294, 1993.
[49] Y. S. Chen and Y. C. Hsu, "Image segmentation of a color-blindness plate," Applied Optics, vol. 33, no. 29,
pp. 6818-6822, 1994.
[50] D. Walters, "Selection of image primitives for general-purpose visual processing,"
Computer Vision, Graphics and Image Processing, vol. 37, pp 261-298, 1987.
[51] M. J. Swain, "Color indexing," International Hournal of Computer Vision, vol. 7,
no. 1, pp. 11-32, 1991.
[52] V. F. Brain and D. F. Graham, "Color constant color indexing," IEEE Trans. Pattern Analysis and
Machine Intelligence, vol. 17, no. 5, pp. 522-529, 1995.
[53] J. R. Smith and S. F. Chang, "Tools and techniques for color image retrieval," in Proc.
SPIE Storage, Retrieval for Image and Video Databases IV, 1996, vol. 2670, pp. 1-13.
[54] W. Niblack, R. Barber, W. Equitz, M. Flickner, E. Glasman, D. Petkovic, and P. Yanker,
"The QBIC project:query images by content using color, texture, and shape," in Proc. SPIE Storage and
retrieval Image and Video Databased, Bellingham, WA. 1993, vol. 1908, pp. 173-187.
[55] V. N. Gudivada and V. Raghavan V, "Content-based image retrieval systems,"
IEEE Computer, vol. 28, no. 9. pp. 18-22, 1995.
[56] M. Ren, J. P. Eakins, and R. Briggs, "Human perception of trademark images:
Implications for retrieval system design," Journal of Electronic Imaging, vol. 9, no. 4,
pp. 18-22, 1995.
[57] J. P. Eakins, J. M. Boardman, and M. E. Graham, "Similarity retrieval of trademark images,"
IEEE Multimedia, vol. 5, no. 2, pp. 53-63, 1998.
[58] Y. S. Kim and W. Y. Kim, "Content-based trademark retreival system using a visually
salient feature," Image and Vision computing, vol. 16, pp.931-939, 1998.
[59]T. Gevers and A. W. M. Smeulders, "Content-based image retrieval by viewpoint-invariant
color indexing," Pattern Recognition, vol. 32, pp. 1857-1872, 1999.
[60] T. Gevers and A. W. M. Smeulders, "PicToSeek:conbining color and shape imvariant features
for image retrieval," IEEE Trans. Image Processing. vol. 9, no. 1, pp. 102-119, 1999.
[61] S. T. Goh and K. L. Tan, "MISAIC: a fast multi-feature image retrieval system,"
Data and Knowledge Engineering, vol. 33, pp. 219-239, 2000.
[62] Y. Zhong and A. K. Jain, "Object localization using color, texture and shape,"
Pattern Recognition, vol. 33, pp. 671-684, 2000.
[63] J. Laaksonen, M. Koskela, S. Laakso, and E. Oja, "PICSOM-content-based image retrieval
with self-organizing maps," Pattern Recognition Letters, vol. 21, pp. 1199-1207, 2000.
[64] M. S. Kankanhalli, B. M. Mehtre, and H. Y. Huang, "Color and spatial feature for
content-based image retrieval," Pattern Recognition Letters, vol. 20, pp. 109-118, 1999.
[65] J. Favela and V. Meza, "Image-retrieval agent:integrating image content and text,"
IEEE Intelligent Systems, vol. 14, no. 5, pp. 36-39, 1999.
[66] A. Valiaya, A. Jain, and H. J. Zhang, "On image classification city images vs. landscapes,"
Pattern Recognition, vol. 31, no. 12, pp. 1921-1935, 1998.
[67] A. Pentland, R. W. Picard, and S. Sclaroff, "Photobook:content-based manipulation of
image databased," International Journal of Computer Vision, vol. 18, no. 3, pp. 233-254, 1996.
[68] J. R. Smith and S. F. Chang, "VisualSEEK: a fully automated contend-based image query system,"
in Proc. ACM Int. Conf. Multimedia, 1996, pp. 87-98.
[69] M. Flickner, H. Sawhney, W. Niblack, J. Ashley, Q. Huang, B. Dom, M. Gorkani, J. Hafner, D. Lee,
D. Petkovic, D. Steele, and P. Yanker, "Query by image and video content: the QBIC system," IEEE
Computer, vol. 28, no. 9, pp. 23-32, 1995.
[70] B. M. Mehtre, M. S. Kankanhalli, and A. D. Narasimhalu, "Color matching for image retrieval,"
Pattern Recognition Letters, vol. 16. pp. 325-331, 1995.
[71] G. Wyszecki and W. S. Stiles, Color Science: concepts and method, quantitative data and formulae,
Jhon Wiley and Sons, Canada, 2nd edition, 1982.
[72] R. W. G. Hunt, Measuring Color, John Wiley and Sons. England, first edition, 1989.
[73] J. C. Russ, The Image Processing Handbook, CRC Press, Boca Raton, 1995.
[74] H. Y. Huang, Y. S. Chen, and W. H. Hsu, "Segmentatin and association for a gray image,"
in ACCV2000, Proceeding of the 4th Asian Conf. on Computer Vision, Taiwan, 2000, vol. 1, pp. 210-215.
[75] H. Y. Huang, Y. S. Chen, and W. H. Hsu, "Color image segmentation using self-organizing map
algorithm," Journal of Electronic Imaging, (to appear), 2002.
[76] H. Y. Huang, Y. S. Chen, and W. H. Hsu,"Human-based image interpretation using color and texture and
spatial relationships features," in 2001 14th IPPR Conference on Computer Vision, Graphics and Image
Processing, Taiwan, 2001.
[77] H. Y. Huang, Y. S. Chen, and W. H. Hsu, "Image indexing and retrieval," Journal of Electronic Imaging,
(Prepare to submit), 2002,1
[78] T. Kohonen, J. Kangas, and J. Laaksonen, SOM_PAK: The self-organizing map program package,
vol. 1.2, SOM Programming Team of the Helsinki University of Techology, Laboratory of Computer
and Information Science, Rakentajanaukio 2 C, SF-02150, Espoo, Finland, 1992.
[79] A. V. Oppenheim and R. W. Schafer, Discrete-time Signal Processing, Prentice-Hall Inc., U.S.A. 1989.
[80] B. T. Chen, On the study of fuzzy number computing and its applications to image processing,
Ph.D. Thesis, National Tsing Hua University, Department of Electrical Engineering, Taiwan, R.O.C., 1996.
[81] B. T. Chen, Y. S. Chen, and W. H. Hsu, "Automatic histogram specification based fuzzy set
operations for image enhancement," IEEE Signal Processing Letters, vol. 2, pp. 37-40, 1995b.
[82] H. Tamura, s. Mori, and T. Yamawaki, "Textural features corresponding to visual perception,"
IEEE Trans. Systems, Man, and Cybernetics, vol. SMC-8, no. 6, pp. 460-473, 1978.
[83] R. R. Yager and L. A. Zadeh, An Introduction to Fuzzy Logical Applications in Intelligent Systems,
Kluwer Academic Publishers, Boston, 1992.
[84] Y. S. Chen, "Segmentation and association among lines and junctions for a line image," Pattern Recognition,
vol. 27, no. 9, pp. 1135-1157, 1994.
[85] W. K. Pratt, Digital image processing, John Wiley and Sons, Inc., New York, 1991.
[86] B. T. Chen, Y. S. Chen, and W. H. Hsu, "A parameterized fuzzy processor and its application,"
Fuzzy Sets and Systems, vol. 59, no. 2, pp. 149-172, 1993.
[87] B. T. Chen, Y. S. Chen, and W. H. Hsu, "Performance evaluation of a parameterized fuzzy processor(PFP),"
Fuzzy Sets and Systems, vol. 81, no. 3, pp. 293-309, 1996.
[88] B. T. Chen, Y. S. Chen, and W. H. Hsu, "Image processing and understanding based on fuzzy inference approach,"
in Proce. IEEE 3rd Int. Conf. on Fuzzy Systems, Orlando, 1994, pp. 254-259.
[89] Y. S. Chen, H. Y. Hwang, and B. T. Chen, "An image understanding system designed for feeling the weather
state from an image," Journal of the Chinese Fuzzy Systems Association, vol. 5, no. 2, pp. 89-102, 1999.
[90] N. Kanatg, K. S. Kumar, U. V. Desai, and R. Fugud, "Joint segmentation and image interpretation
using Hidden Markov Mofels," in IEEE proc. on 14th IAPR Inter. Conf. on Pattern Recognition, Brisbane,
Australia, 1998, pp. 1822-1824.
[91] A Celentano, "Feature integration and relevance feedback analysis in image similarity evaluation,"
Journal on Electronic Imaging, vol. 7, no. 2, pp. 308-317, 1998.
[92] A. K. Jain, Fundamentals of Digital Image Processing, Prentice-Hall Internationsl Editions, U.S.A. 1989.
[93] N. W. Campbell, W. P. J. Mackeown, B. T. Thomas, and T. Troscianko, "Interpreting image databases by
region classification," Pattern Recognition, vol. 30, no. 4, pp. 555-563, 1997.
[94] N. Tajahasgu abd M Iwasaki and T. Kunieda, "Image retrieval using spatial intensity features," Signal
Processing:Image Communication, vol. 16, no. 1-2, pp. 45-57, 2000.
[95] J. Battle, A. Casala, J. Freixenet, and J, Marti, "A review on strategies for recognizing natural objects
in colour images of ourdoor scenes," Image and Vision Computing, vol. 18. pp. 515-530, 2000.
[96] T. P. Minka and R. W. Picard, "Interactive learning with a Society of Models," Pattern Recognition,
vol. 30, no. 4, pp. 565-585, 1997.
[97] B. C. Ko, H. S. Lee, and H. Byun, "Region-based image retrieval system using efficient feature description,"
in Proc. 15th Int. Conf. on Pattern Recognition, 2000, vol. 4, pp. 283-286.
[98] Y. S. Chen, H. Y. Huang, and B. T. Chen, "An image understanding system designed for feeling the weather
state from an image," Journal of the Chinese Fuzzy Systems Association, vol. 5, no. 2, pp. 89-102, 1999.
[99] Y. S. Chen, H. Y. Hwang, and B. T. Chen, "Color image analysis using fuzzy set theory," in Proc. IEEE Int.
Conf. on Image Processing, Washington, D.C., 1995, vol. 3, pp.1137-1142.
[100] Y. Nakagawa ans K. Hirota, "Fundamentals of fuzzy knowledge base for image understanding,"
in Proc. IEEE Int. Conf. on Fuzzy Systems, Yakohama, Japan, 1995, vol. 3, pp. 1137-1142.
[101] W. Pratt, Digital Image Processing, John Wiley and Sons. New York, second edition, 1991.
[102] P. A. Mlsna and J. J. Rodriguez, "Efficient indexing of multi-color sets for content-based image retrieval,"
in Proc. 4th IEEE Southwest Symposium Image Analysis and Interpretation, 2000, pp. 116-120.
[103] J. Han and K. K. Ma, "Fuzzy color histogram:an efficient color geature for image indexing and retrieval,"
in Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, 2000, vol. 4, pp. 2011-2014.
[104] T. Gevers and A. W. M. Smeulders, "Content-based image retrieval by viewpoint-invariant color indexing,"
Pattern Recognition, vol. 32, pp. 1857-1872, 1999.
[105] Y. Gong, G. Proietti, and C. Faloutsos, "Image indexing and retrieval based on human perceptual color clustering,"
in IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 1998, pp. 578-583.
[106] J. R. Smith and S. F. Chang, "Intergrated spatial and feature image query," Multimedia Systems, vol. 7, pp. 126-140, 1999.
[107] A. Kaufmann and M. M. Gupta, Introduction to Fuzzy Arithmetic:Theory and Application,
Vab Bostrand Co., New York, 1985.
[108] D. Dubois and H. Prade, "Outline of fuzzy set theory: an introduction," in Advances in Fuzzy Set Theory and
Application, M. M. Gupta and R. R. Yager, Eds., North Holland, 1982, pp. 27-48, Elsevier Science Publishing, Inc.
[109] V. Catania, A. Puliafito, M. Russo, and L. Vita, "A VLSI fuzzy inference processor based on discrete analog approach,"
IEEE Trans. on Fuzzy Systems, vol. 81, no. 3, pp. 293-309, 1996.
[110] A. Rosenfeld and A. C. Kak, Digital Picture Processing, Academic Press, Inc., New York, second edition, 1982.
[111] S. Fukami, M. Mizumoto, and K. Tanaka, "Some considerations on fuzzy conditional inference," Fuzzy Sets and Systems,
vol. 4, pp. 243-273, 1980.
[112] M. Mizumoto and H. J. Zimmermann, "Comparison of fuzzy reasoning methods," Fuzzy Sets and Systems,
vol. 8. pp. 253-283,1982.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top