《计算机专业英语-专业知识课件》由会员分享，可在线阅读，更多相关《计算机专业英语-专业知识课件（64页珍藏版）》请在金锄头文库上搜索。
1、New Technologies,Abbreviations,3D3 Dimension ACMAssociation for Computing Machinery AIArtificial Intelligence ALTAdvanced Learning Technology APIApplication Programming Interface CADComputer Aided Design CBIRContent-Based Image Retrieval CBVIRContent-Based Visual Information Retrieval QBICQuery by I
2、mage Content CGComputer Graphics,Abbreviations,CGICommon Gateway Interface DVDDigital Video Disk GISGeographic Information System GPSGlobal Positioning System HCIHuman Computer Interaction HDTVHigh-Definition Television HTMLHypertext Markup Language IASTEDInternational Association of Science and Tec
3、hnology for Development IEEEInstitute of Electrical and Electronics Engineers,Abbreviations,ISOInternational Organization for Standardization LBSLocation-based Services MDMolecular Dynamics MISManagement Information System NLPNatural Language Processing NMRNuclear Magnetic Resonance PDFPortable Docu
4、ment Format Ph.D.Doctor of Philosophy RDFResource Description Framework SDKSoftware Development Kit,Abbreviations,TIFFTagged Image File Format URLUniform Resource Locator VLEVirtual Learning Environment VRMLVirtual Reality Modeling Language W3CWorld Wide Web Consortium XMLeXtensible Markup Language
5、ERPEnterprise resource planning software e.g.exempli gratia i.e.id est,6,Natural Language Processing (NLP),7,Think About,What research area does natural language processing belong to? What problems does it try to resolve? What do natural-language-generation systems and natural-language-understanding
6、 systems do respectively? What problems seem difficult in natural language processing? What are the major tasks in NLP?,8,What is Natural Language Processing,Natural language processing (NLP) is a subfield of artificial intelligence and computational linguistics. It studies the problems of automated
7、 generation and understanding of natural human languages.,9,What is Natural Language Processing,Natural-language-generation systems convert information from computer databases into normal-sounding human language. Natural-language-understanding systems convert samples of human language into more form
8、al representations that are easier for computer programs to manipulate.,10,Difficulties,Speech Segmentation Text Segmentation Word Sense Disambiguation Many words have more than one meaning Syntactic Ambiguity The grammar for natural languages is ambiguous Imperfect or Irregular Input Foreign or reg
9、ional accents and vocal impediments in speech; typing or grammatical errors Speech Acts and Plans,Speech Segmentation,In most spoken languages, the sounds representing successive letters blend into each other, so the conversion of the analog signal to discrete characters can be a very difficult proc
10、ess.,Text Segmentation,Some written languages like Chinese, Japanese and Thai do not have single-word boundaries either, so any significant text parsing usually requires the identification of word boundaries, which is often a non-trivial task.,13,Major Tasks in NLP,Automatic summarization Foreign La
11、nguage Reading Aid Foreign Language Writing Aid Information extraction Information retrieval Machine translation Named entity recognition,14,Major Tasks in NLP,Natural language generation Optical Character Recognition Question answering Speech recognition Spoken dialogue system Text simplification T
12、ext to speech Text-proofing,Content-based Image Retrieval（CBIR),Think About,What is content-based image retrieval? What does the term “content” mean? What are low level image retrieval, region based image retrieval, and semantic image retrieval respectively? From the historic overview, how has CBIR
13、evolved? What does it mean by multimedia information retrieval ?,What Research Areas Are Involved In?,Computer vision, pattern recognition, image processing, data mining, machine learning, human-computer interaction, artificial intelligence Application: digital museum/libraries, safety of society, i
14、mage/video copy detection, GIS, medicine, education, entertainment, WWW, to name just a few,Digital Image Retrieval,Search for digital images in large databases First generation: laborious, subjective Metadata (captions or keywords) Image Second generation (content-based): objective Image contents I
15、mage Current way (semantic): subjective + objective Image contents + semantic feature Image Our way: Image contents + semantic feature + keywords/captions Image,Semantic gap,What Is Content-based Image Retrieval,“Content-based” means that the search will analyze the actual contents of the image. The
16、 term “content” in this context might refer colors, shapes, textures, or any other information that can be derived from the image itself,Low Level Image Retrieval,Color Examining images based on the colors they contain is one of the most widely used techniques because it does not depend on image size or orientation. Color searches will usually involve comparing color histograms, though this is not the only technique in practice,Color Space,R,G,B,Lightness (亮度，即明暗） Hue（色调，即光的颜色） Saturation（饱和度
