Abstract
Grammars are widely used to describe string languages such as programming and natural languages and, more recently, biosequences. Moreover, since the 1980s grammars have been used in computer vision and related areas. Some factors accountable for this increasing use regard its relatively simple understanding and its ability to represent some semantic pattern models found in images, both spatially and temporally. The objective of this article is to present an overview regarding the use of syntactic pattern recognition methods in image representations in several applications. To achieve this purpose, we used a systematic review process to investigate the main digital libraries in the area and to document the phases of the study in order to allow the auditing and further investigation. The results indicated that in some of the studies retrieved, manually created grammars were used to comply with a particular purpose. Other studies performed a learning process of the grammatical rules. In addition, this article also points out still unexplored research opportunities in the literature.
- Angluin, D. 1992. Computational learning theory: Survey and selected bibliography. In Proceedings of the 24th Annual ACM Symposium on Theory of Computing (STOC'92). ACM, New York, 351--369. DOI: http://dx.doi.org/10.1145/129712.129746. Google ScholarDigital Library
- Böhm, C., Berchtold, S., and Keim, D. A. 2001. Searching in high-dimensional spaces: Index structures for improving the performance of multimedia databases. ACM Comput. Surv. 33, 3, 322--373. DOI: http://dx.doi.org/10.1145/502807.502809. Google ScholarDigital Library
- Chanda, G. and Dellaert, F. 2004. Grammatical Methods in Computer Vision: An Overview. Tech. rep. Georgia Tech Institute of Technology.Google Scholar
- Chen, H., Xu, Z. J., Liu, Z. Q., and Zhu, S. C. 2006. Composite templates for cloth modeling and sketching. In Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1 (CVPR'06). IEEE Computer Society, Washington, DC, 943--950. DOI: http://dx.doi.org/10.1109/CVPR.2006.81. Google ScholarDigital Library
- Christensen, H. I., Matas, J., and Kittler, J. 1996. Using grammars for scene interpretation. In Proceedings of the International Conference on Image Processing, vol. 1. 793--796 DOI: http://dx.doi.org/10.1109/ICIP.1996.561024.Google ScholarCross Ref
- Doi, K. 2007. Computer-aided diagnosis in medical imaging: Historical review, current status and future potential. Comput. Med. Imaging Graphics 31, 4--5, 191--211.Google ScholarCross Ref
- Fernau, H. 2003. Parallel grammars: A phenomenology. Grammars 6, 1, 25--87. DOI: http://dx.doi.org/10.1023/A:1024087118762.Google ScholarCross Ref
- Ferreira, M. J., Santos, C. P., and Monteiro, J. 2007a. Texture cue based tracking system using wavelet transform and a fuzzy grammar. In Proceedings of the 5th IEEE International Conference on Industrial Informatics, vol. 1, 393--398. DOI: http://dx.doi.org/10.1109/INDIN.2007.4384789.Google Scholar
- Ferreira, M. J., Santos, C. P., and Monteiro, J. 2007b. Texture segmentation based on fuzzy grammar for cork parquet quality control. In Proceedings of the IEEE International Symposium on Industrial Electronics (ISIE'07). 1832--1837. DOI: http://dx.doi.org/10.1109/ISIE.2007.4374884.Google Scholar
- Ferreira, M., Santos, C., and Monteiro, J. 2009. Cork parquet quality control vision system based on texture segmentation and fuzzy grammar. IEEE Trans. Ind. Electron. 56, 3, 756--765.Google ScholarCross Ref
- Gao, J., Ding, X., and Zheng, J. 2000. Image pattern recognition based on examples—A combined statistical and structural-syntactic approach. In Advances in Pattern Recognition, F. J. Ferri, J. M. Inesta, A. Amin, and P. Pudil, Eds., Lecture Notes in Computer Science, vol. 1876. Springer, Berlin, 57--66. DOI: http://dx.doi.org/10.1007/3-540-44522-6_6. Google ScholarDigital Library
- Gidas, B. and Zelic, A. 1997. Object recognition via hierarchical syntactic models. In Proceedingsof the 13th International Conference on Digital Signal Processing (DSP'97), vol. 1, 315--318. DOI: http://dx.doi.org/10.1109/ICDSP.1997.628082.Google ScholarCross Ref
- Glomb, P. 2007. Image language terminal symbols from feature analysis. In Proceedings of the IEEE International Workshop on Imaging Systems and Techniques (IST'07). 1--6. DOI: http://dx.doi.org/10.1109/IST.2007.379599.Google ScholarCross Ref
- Hamdi, S., Abdallah, A. B., and Bedoui, M. H. 2012. Grammar-based image segmentation and automatic area estimation. In Proceedings of the 16th IEEE Mediterranean Electrotechnical Conference (MELECON'12). 356--359. DOI: http://dx.doi.org/10.1109/MELCON.2012.6196448.Google Scholar
- Han, F. and Zhu, S.-C. 2005. Bottom-up/top-down image parsing by attribute graph grammar. In Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on, vol. 2. Beijing, China, 1778--1785, vol. 2. 1550--5499. DOI: http://dx.doi.org/10.1109/ICCV.2005.50. Google ScholarDigital Library
- Han, F. and Zhu, S.-C. 2009. Bottom-up/top-down image parsing with attribute grammar. IEEE Trans. Pattern Anal. Mach. Intell. 31, 1, 59--73. DOI: http://dx.doi.org/10.1109/TPAMI.2008.65. Google ScholarDigital Library
- Hemberg, M. and OReilly, U.-M. 2004. Extending grammatical evolution to evolve digital surfaces with Genr8. In Genetic Programming, M. Keijzer, U.-M. OReilly, S. Lucas, E. Costa, and T. Soule, Eds., Lecture Notes in Computer Science, vol. 3003. Springer, Berlin, 299--308. DOI: http://dx.doi.org/10.1007/978-3-540-24650-3_28.Google Scholar
- Hingway, S. P. and Bhurchandi, K. M. 2011. A simple graph theoretic approach for object recognition. In Proceedings of the 4th International Conference on Emerging Trends in Engineering and Technology (ICETET'11). 200--205. DOI: http://dx.doi.org/10.1109/ICETET.2011.62. Google ScholarDigital Library
- Jin, Y. and Geman, S. 2006. Context and hierarchy in a probabilistic image model. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, 2145--2152. DOI: http://dx.doi.org/10.1109/CVPR.2006.86. Google ScholarDigital Library
- Kanungo, T. and Mao, S. 2003. Stochastic language models for style-directed layout analysis of document images. IEEE Trans. Image Process. 12, 5, 583--596. DOI: http://dx.doi.org/10.1109/TIP.2003.811487. Google ScholarDigital Library
- Kong, J., Barkol, O., Bergman, R., Pnueli, A., Schein, S., Zhang, K., and Zhao, C. 2012. Web interface interpretation using graph grammars. IEEE Trans. Syst. Man Cybern., Part C Appl. Rev. 42, 4, 590--602. DOI: http://dx.doi.org/10.1109/TSMCC.2011.2171335.Google ScholarDigital Library
- Lin, W.-C. and Fu, K.-S. 1986. A syntactic approach to three-dimensional object recognition. IEEE Trans. Syst. Man Cybern. 16, 405--422. Google ScholarDigital Library
- Luo, P., He, J., Lin, L., and Chao, H. 2009. Hierarchical 3D perception from a single image. In Proceedings of the 16th IEEE International Conference on Image processing (ICIP'09). IEEE, Los Alamitos, CA, 4209--4212. Google ScholarDigital Library
- Mäkinen, E. 1992. On the structural grammatical inference problem for some classes of context-free grammars. Inf. Process. Lett. 42, 1, 1--5. Google ScholarDigital Library
- Mao, S., Rosenfeld, A., and Kanungo, T. 2003. Stochastic attributed K-d tree modeling of technical paper title pages. In Proceedings of the 2003 International Conference on Image Processing (ICIP'03). 533--536. DOI: http://dx.doi.org/10.1109/ICIP.2003.1247016.Google Scholar
- Mas, J., Jorge, J. A., Sanchez, G., and Llados, J. 2008. Representing and parsing sketched symbols using adjacency grammars and a grid-directed parser. In Graphics Recognition. Recent Advances and New Opportunities, W. Liu, J. Llados, and J.-M. Ogier, Eds., Lecture Notes in Computer Science, vol. 5046. Springer, Berlin, 169--180. DOI: http://dx.doi.org/10.1007/978-3-540-88188-9_17. Google ScholarDigital Library
- Mas, J., Sanchez, G., and Llados, J. 2005. An adjacency grammar to recognize symbols and gestures in a digital pen framework. In Pattern Recognition and Image Analysis, J. S. Marques, N. P. de la Blanca, and P. Pina, Eds., Lecture Notes in Computer Science, vol. 3523. Springer, Berlin, 115--122. DOI: http://dx.doi.org/10.1007/11492542_15. Google ScholarDigital Library
- Nunes, F. L. S., Schiabel, H., and Goes, C. E. 2007. Contrast enhancement in dense breast images to aid clustered microcalcifications detection. J. Digital Imaging 20, 1, 53--66.Google ScholarCross Ref
- Ogiela, L., Ogiela, M. R., and Tadeusiewicz, R. 2009. Mathematical linguistics in cognitive medical image interpretation systems. J. Math. Imaging Vision 34, 3, 328--340. DOI: http://dx.doi.org/10.1007/s10851-009-0151-4. Google ScholarDigital Library
- Ogiela, L., Tadeusiewicz, R., and Ogiela, M. R. 2008. Cognitive modeling in medical pattern semantic understanding. In Proceedings of the International Conference on Multimedia and Ubiquitous Engineering (MUE'08). 15--18. DOI: http://dx.doi.org/10.1109/MUE.2008.47. Google ScholarDigital Library
- Parag, T., Bahlmann, C., Shet, V., and Singh, M. 2012. A grammar for hierarchical object descriptions in logic programs. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW'12). 33--38. DOI: http://dx.doi.org/10.1109/CVPRW.2012.6239171.Google Scholar
- Peng, S., Liu, L., Yang, X., and Sang, N. 2008. A database schema for large scale annotated image dataset. In Proceedings of the Congress on Image and Signal Processing (CISP'08). 57--62. DOI: http://dx.doi.org/10.1109/CISP.2008.49. Google ScholarDigital Library
- Petrakis, E. G. M., Faloutsos, C., and Lin, K.-I. 2002. ImageMap: An image indexing method based on spatial similarity. IEEE Trans. Knowl. Data Eng. 14, 5, 979--987. DOI: http://dx.doi.org/10.1109/TKDE.2002.1033768. Google ScholarDigital Library
- Prusinkiewicz, P., Lindenmayer, A., and Hanan, J. 1988. Development models of herbaceous plants for computer imagery purposes. SIGGRAPH Comput. Graph. 22, 4, 141--150. DOI: http://dx.doi.org/10.1145/378456.378503. Google ScholarDigital Library
- Qu, H., Zhu, Q., Zeng, L., Guo, M., and Lu, Z. 2008. Automata-based L-Grammar extraction from multiple images for virtual plants. In Proceedings of the 3rd International Conference on Bio-Inspired Computing: Theories and Applications (BICTA'08). 89--96. DOI: http://dx.doi.org/10.1109/BICTA.2008.4656709.Google Scholar
- Reddy, H. T., Karibasappa, K., and Damodaram, A. 2009. Probabilistic parser for face detection. In Proceeding of International Conference on Methods and Models in Computer Science (ICM2CS'09). 1--7. DOI: http://dx.doi.org/10.1109/ICM2CS.2009.5397986.Google ScholarCross Ref
- Ron, D., Singer, Y., and Tishby, N. 1995. On the learnability and usage of acyclic probabilistic finite automata. In Proceedings of the 8th Annual Conference on Computational Learning Theory (COLT'95). ACM, New York, 31--40. DOI: http://dx.doi.org/10.1145/225298.225302. Google ScholarDigital Library
- Rothrock, B. and Zhu, S.-C. 2011. Human parsing using stochastic and-or grammars and rich appearances. In Proceedings of the 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops'11). 640--647. DOI: http://dx.doi.org/10.1109/ICCVW.2011.6130303.Google ScholarCross Ref
- Sainz, M. and Sanfeliu, A. 1996. Learning bidimensional context-dependent models using a context-sensitive language. In Proceedings of the 13th International Conference on Pattern Recognition, vol. 4, 565--569. DOI: http://dx.doi.org/10.1109/ICPR.1996.547628. Google ScholarDigital Library
- Sakakibara, Y. 1992. Efficient learning of context-free grammars from positive structural examples. Inf. Comput. 97, 1, 23--60. DOI: http://dx.doi.org/10.1016/0890-5401(92)90003-X. Google ScholarDigital Library
- Sakakibara, Y. 1995. Grammatical inference: An old and new paradigm. In Algorithmic Learning Theory, K. P. Jantke, T. Shinohara, and T. Zeugmann, Eds., Lecture Notes in Computer Science, vol. 997. Springer, Berlin, 1--24. DOI: http://dx.doi.org/10.1007/3-540-60454-5_25. Google ScholarDigital Library
- Sakakibara, Y. 2005. Learning context-free grammars using tabular representations. Pattern Recogn. 38, 9, 1372--1383. DOI: http://dx.doi.org/10.1016/j.patcog.2004.03.021. Google ScholarDigital Library
- Sakakibara, Y. and Muramatsu, H. 2000. Learning context-free grammars from partially structured examples. In Grammatical Inference: Algorithms and Applications, A. L. Oliveira, Ed., Lecture Notes in Computer Science, vol. 1891. Springer, Berlin, 229--240. DOI: http://dx.doi.org/10.1007/978-3-540-45257-7_19. Google ScholarDigital Library
- Schlecht, J., Barnard, K., Spriggs, E., and Pryor, B. 2007. Inferring grammar-based structure models from 3D microscopy data. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR'07). 1--8. DOI: http://dx.doi.org/10.1109/CVPR.2007.383031.Google Scholar
- Shet, V., Singh, M., Bahlmann, C., and Ramesh, V. 2009. Predicate logic based image grammars for complex pattern recognition. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops'09). 7. DOI: http://dx.doi.org/10.1109/CVPRW.2009.5204328.Google Scholar
- Shilman, M., Liang, P., and Viola, P. 2005. Learning nongenerative grammatical models for document analysis. In Proceedings of the IEEE International Conference on Computer Vision (ICCV'05), vol. 2, 962--969. DOI: http://dx.doi.org/10.1109/ICCV.2005.140. Google ScholarDigital Library
- Si, Z. and Zhu, S.-C. 2011. Unsupervised learning of stochastic AND-OR templates for object modeling. In Proceedings of the 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops'11). 648--655. DOI: http://dx.doi.org/10.1109/ICCVW.2011.6130304.Google ScholarCross Ref
- Siddiqi, K. and Kimia, B. B. 1996. A shock grammar for recognition. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'96). 507--513. DOI: http://dx.doi.org/10.1109/CVPR.1996.517119. Google ScholarDigital Library
- Siddiqi, K., Shokoufandeh, A., Dickenson, S. J., and Zucker, S. W. 1998. Shock graphs and shape matching. In Proceedings of the 6th International Conference on Computer Vision. 222--229. DOI: http://dx.doi.org/10.1109/ICCV.1998.710722. Google ScholarDigital Library
- Sipser, M. 2006. Introduction to the Theory of Computation (2nd ed.). Thomson Course Technology.Google Scholar
- Siskind, J., Sherman Jr, J., Polak, T., Harper, M., and Bouman, C. 2007. Spatial random tree grammars for modeling hierarchical structure in images with regions of arbitrary shape. IEEE Trans. Pattern Anal. Mach. Intell. 29, 9, 1504--1518. Google ScholarDigital Library
- Soltanpour, S. and Ebrahimnezhad, H. 2010. Learning novel object parts model for object categorization. In Proceedings of the 5th International Symposium on Telecommunications (IST'10). 796--800. DOI: http://dx.doi.org/10.1109/ISTEL.2010.5734131.Google Scholar
- Stuckelberg, M. V. and Doermann, D. 1999. On musical score recognition using probabilistic reasoning. In Proceedings of the 5th International Conference on Document Analysis and Recognition (ICDAR'99). 115--118. DOI: http://dx.doi.org/10.1109/ICDAR.1999.791738. Google ScholarDigital Library
- Subramanian, K. G., Mary, A. R. S., and Dersanambika, K. S. 2005. Splicing array grammar systems. In Proceedings of the International Conference on Theoretical Aspects of Computing (ICTAC'05), D. Hung and M. Wirsing, Eds., Lecture Notes in Computer Science, vol. 3722. Springer, Berlin, 125--135. DOI: http://dx.doi.org/10.1007/11560647_8. Google ScholarDigital Library
- Sun, R., Jia, J., Li, H., and Jaeger, M. 2009. Image-based lightweight tree modeling. In Proceedings of the 8th International Conference on Virtual Reality Continuum and its Applications in Industry (VRCAI'09). ACM, New York, 17--22. DOI: http://dx.doi.org/10.1145/1670252.1670258. Google ScholarDigital Library
- Takada, Y. 1988. Grammatical inference for even linear languages based on control sets. Inform. Process. Lett. 28, 4, 193--199. DOI: http://dx.doi.org/10.1016/0020-0190(88)90208-6. Google ScholarDigital Library
- Toshev, A., Mordohai, P., and Taskar, B. 2010. Detecting and parsing architecture at city scale from range data. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'10). 398--405. DOI: http://dx.doi.org/10.1109/CVPR.2010.5540187.Google Scholar
- Trzupek, M., Ogiela, M. R., and Tadeusiewicz, R. 2009. Image content analysis for cardiac 3D visualizations. In Knowledge-Based and Intelligent Information and Engineering Systems, J. D. Velásquez, S. A. Ríos, R. J. Howlett, and L. C. Jain, Eds., Lecture Notes in Computer Science, vol. 5711. Springer, Berlin 192--199. DOI: http://dx.doi.org/10.1007/978-3-642-04595-0_24. Google ScholarDigital Library
- Trzupek, M., Ogiela, M. R., and Tadeusiewicz, R. 2011. Intelligent image content description and analysis for 3D visualizations of coronary vessels. In Intelligent Information and Database Systems, N. T. Nguyen, C.-G. Kim, and A. Janiak, Eds., Lecture Notes in Computer Science, vol. 6592. Springer, Berlin, 193--202. DOI: http://dx.doi.org/10.1007/978-3-642-20042-7_20. Google ScholarDigital Library
- Tylecek, R. and Sara, R. 2011. Modeling symmetries for stochastic structural recognition. In Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCV Workshops'11). 632--639. DOI: http://dx.doi.org/10.1109/ICCVW.2011.6130302.Google Scholar
- Wang, Q. and Jiang, Z. 2009. A grammatical framework for building rooftop extraction. In Proceedings of the IEEE International Symposium on Geoscience and Remote Sensing (IGARSS'09). III--334--III--337. DOI: http://dx.doi.org/10.1109/IGARSS.2009.5417768.Google Scholar
- Wang, W., Pollak, I., Bouman, C. A., and Harper, M. P. 2005b. Classification of images using spatial random trees. In Proceedings of the 2005 IEEE/SP 13th Workshop on Statistical Signal Processing. 449--452. DOI: http://dx.doi.org/10.1109/SSP.2005.1628637.Google ScholarCross Ref
- Wang, W., Pollak, I., Wong, T.-S., Bouman, C. A., Harper, M. P., and Siskind, J. M. 2006. Hierarchical stochastic image grammars for classification and segmentation. IEEE Trans. Image Process. 15, 10, 3033--3052. DOI: http://dx.doi.org/10.1109/TIP.2006.877496. Google ScholarDigital Library
- Wang, Y., Bahrami, S., and Zhu, S.-C. 2005a. Perceptual scale space and its applications. In Proceedings of the 10th IEEE International Conference on Computer Vision (ICCV'05). Vol. 1, 58--65. DOI: http://dx.doi.org/10.1109/ICCV.2005.187. Google ScholarDigital Library
- Wu, Y. and Bian, H. 2009. Image segmentation integrating generative and discriminative methods. In Proceedings of the International Conference on Web Information Systems and Mining (WISM'09). 769--774. DOI: http://dx.doi.org/10.1109/WISM.2009.159. Google ScholarDigital Library
- Yao, B., Yang, X., and Wu, T. 2009. Image parsing with stochastic grammar: The Lotus Hill dataset and inference scheme. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops'09). DOI: http://dx.doi.org/10.1109/CVPRW.2009.5204331.Google Scholar
- Zaboli, H. and Rahmati, M. 2007. An improved shock graph approach for shape recognition and retrieval. In Proceedings of the 1st Asia International Conference on Modelling Simulation (AMS'07). 438--443. DOI: http://dx.doi.org/10.1109/AMS.2007.13. Google ScholarDigital Library
- Zhu, L., Chen, Y., and Yuille, A. 2009. Unsupervised learning of probabilistic grammar-Markov models for object categories. IEEE Trans. Pattern Anal. Mach. Intell. 31, 1, 114--128. DOI: http://dx.doi.org/10.1109/TPAMI.2008.67. Google ScholarDigital Library
- Zhu, S.-C. and Mumford, D. 2006. A stochastic grammar of images. Found. Trends. Comput. Graph. Vis. 2, 4, 259--362. DOI: http://dx.doi.org/10.1561/0600000018. Google ScholarDigital Library
Index Terms
- Using grammars for pattern recognition in images: A systematic review
Recommendations
Syntactic Pattern Recognition in Computer Vision: A Systematic Review
Using techniques derived from the syntactic methods for visual pattern recognition is not new and was much explored in the area called syntactical or structural pattern recognition. Syntactic methods have been useful because they are intuitively simple ...
A CKY parser for picture grammars
We study the complexity of the membership or parsing problem for pictures generated by a family of picture grammars: Siromoney's Context-Free Kolam Array grammars (coincident with Matz's context-free picture grammars). We describe a new parsing ...
Analogical Conception of Chomsky Normal Form and Greibach Normal Form for Linear, Monadic Context-Free Tree Grammars
This paper presents the analogical conception of Chomsky normal form and Greibach normal form for linear, monadic context-free tree grammars (LM-CFTGs). LM-CFTGs generate the same class of languages as four well-known mildly context-sensitive grammars. ...
Comments