Patent Document Similarity Based on Image Analysis Using the SIFT-Algorithm and OCR-Text
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Images are an important element in patents and many experts use images to analyze a patent or to check differences between patents. However, there is little research on image analysis for patents partly because image processing is an advanced technology and typically patent images consist of visual parts as well as of text and numbers. This study suggests two methods for using image processing; the Scale Invariant Feature Transform(SIFT) algorithm and Optical Character Recognition(OCR). The first method which works with SIFT uses image feature points. Through feature matching, it can be applied to calculate the similarity between documents containing these images. And in the second method, OCR is used to extract text from the images. By using numbers which are extracted from an image, it is possible to extract the corresponding related text within the text passages. Subsequently, document similarity can be calculated based on the extracted text. Through comparing the suggested methods and an existing method based only on text for calculating the similarity, the feasibility is achieved. Additionally, the correlation between both the similarity measures is low which shows that they capture different aspects of the patent content.
Abstract
Images are an important element in patents and many experts use images to analyze a patent or to check differences between patents. However, there is little research on image analysis for patents partly because image processing is an advanced technology and typically patent images consist of visual parts as well as of text and numbers. This study suggests two methods for using image processing; the Scale Invariant Feature Transform(SIFT) algorithm and Optical Character Recognition(OCR). The first method which works with SIFT uses image feature points. Through feature matching, it can be applied to calculate the similarity between documents containing these images. And in the second method, OCR is used to extract text from the images. By using numbers which are extracted from an image, it is possible to extract the corresponding related text within the text passages. Subsequently, document similarity can be calculated based on the extracted text. Through comparing the suggested methods and an existing method based only on text for calculating the similarity, the feasibility is achieved. Additionally, the correlation between both the similarity measures is low which shows that they capture different aspects of the patent content.
참고문헌 (39)
- "What is intellectual property?" (2011)[URL]
- H. Joho, "A survey of patent users: an analysis of tasks, behavior, search functionality and system requirements", Proceedings of the third symposium on information interaction in context, pp.13~24 (2010)
- F. Piroi, "Clef-ip 2011:Retrieval in the intellectual property domain", The conference and labs of the evaluation forum - intellectual property(clef-ip) (2011)
- G. Csurka, "Xrce’s participation at patent image classification and imagebased patent retrieval tasks of the clef-ip 2011", The conference and labs of the evaluation forum – intellectual property(clefip) (2011)
- A. Hanbury, "Patent image retrieval: a survey", Proceedings of the 4th workshop on patent information retrieval, pp.3~8 (2011)
- P. Mandl, "Understanding trends in the patent domain", Proceedings of the first international workshop on patent mining and its applications(ipamin 2014)colocated with konvens 2014 (2014)
- A. Tiwari, "Patseek : Content based image retrieval system for patent database", The fourth international conference on electronic business (iceb), pp.1167~1171 (2004)
- C. A. Gonçalves, "The impact of pre-processing on the classification of medline documents", Pattern recognition in information systems(pris), pp.53~61 (2010)
- C. D. Manning, "Introduction to informationretrieval" (2008), Cambridge University(Kyo-bo)
- P. C. Gaigole, "Preprocessing techniques in text categorization", International Journal of Computer Applications(IJCA), (3), pp.1~3 (2013)
- S. Robertson, "Understanding inverse document frequency : on theoretical arguments for idf", Journal of documentation, 60(5), pp.503~520 (2004)
- "Digital and medical image processing" (2005)[URL]
- D. G. Lowe, "Distinctive image features from scaleinvariant keypoints", International journal of computer vision, 60(2), pp.91~110 (2004)
- M. Brown, "Invariant features from interest point groups", Bmvc (2002)
- C. Harris, "A combined corner and edge detector", Alvey vision conference, 15, pp.50~ (1988)
- A. Singh, "A survey of ocr applications", International Journal of Machine Learning and Computing, 2(3), pp.314~ (2012)
- R. Smith, "An overview of the tesseract ocr engine", Institute of Electrical and Electronics Engineers(IEEE), 2, pp.629~633 (2007)
- S. Vrochidis, "Papadopoulos, Symeon; Moumtzidou, Anastasia; Sidiropoulos, Panagiotis; Pianta, Emanuelle;Kompatsiaris, Ioannis(2010) : Towards Content-based Patent Image Retrieval. A Framework Perspective", World Patent Information, 32(2), pp.94~106 (2010)
- H. Ni, "Binary Patent Image Retrieval Using the Hierarchical Oriented Gradient Histogram", Proceedings of the International Conference on Service Science, ICSS, pp.23~27 (2015), IEEE
- D. Liparas, "Concept-oriented Labelling of Patent Images Based on Random Forests and Proximity-driven Generation of Synthetic Data", Proceedings of the 25th International Conference on Computational Linguistics. COLIN, pp.25~32 (2014)
- Stefanos Vrochidis, "Concept-based patent image retrieval", World Patent Information, 34(4), pp.292~303 (2012), Elsevier BV[DOI]
- Naeem Bhatti, "Image search in patents: a review", International Journal on Document Analysis and Recognition (IJDAR), 16(4), pp.309~329 (2013), Springer Nature[DOI]
- "Document object model (dom) level 3 core specification" (2004)[URL]
- GridlogicsTechnologies, "Contact lenses technology insight report", Patent iNSHIGHT Pro., ~ (2014)
- E. J. Sarver, "Aspheric, astigmatic, multifocal contact lens with asymmetric point spread function", Google Patents (US Patent App. 13, 2012
- "Standard st. 36" (2007)[URL]
- P. Chakraborty, "An open source tesseract based tool for extracting text from images with application in braille translation for the visually impaired", International Journal of Computer Applications, 68(16) (2013)
- K. EL GAJOUI, "Training tesseract tool for amazigh ocr", Recent researches in applied computer science: Proceedings of the 15th international conference on applied computer science 2015, pp.20~22 (2015)
- D. F. Broderick, "Method and system for or dering customized cosmetic contact lenses", Google Patents (US Patent 6,746,120), ~ (2004)
- A. Sozykin, "Mipr-a framework for distributed image processing using hadoop", Application of information and communication technologies (aict), 2015 9th international conference on, 2015, pp.35~39 (2015)
- "The openimaj tutorial" (2012)[URL]
- G. Kondrak, "N-gram similarity and distance", International symposium on string processing and information retrieval, pp.115~126 (2005)
- E. Keogh, "Encyclopedia of machine learning", pp.257~258 (2011), Springer
- E. D’hondt, "Text representations for patent classification", Computational Linguistics, 39(3), pp.755~775 (2013)
- C. Im, "Text classification for patents : Experiments with unigrams, bigrams and different weighting methods", master, pp.2016
- K. Toutanova, "Feature-rich part-ofspeech tagging with a cyclic dependency network", Proceedings of the 2003conference of the north american chapter of the association for computational linguistics on human language technology, 1, pp.173~180 (2003)
- Anjali Ganesh Jivani, "A comparative study of stemming algorithms", International Journal of Computer Technology and Applications(IJCTA), 2(6), pp.1930~1938 (2011)
- "Stochastic processes (advanced probability ii)" (2006)[URL]
- M. Mukaka, "A guide to appropriate use of correlation coefficient in medical research", Malawi Medical Journal, 24(3), pp.69~71 (2012)