Farsi Font Detection using the Adaptive RKEM-SURF Algorithm
محورهای موضوعی : Image ProcessingZahra Hossein-Nejad 1 , Hamed Agahi 2 , Azar Mahmoodzadeh 3
1 - Islamic Azad University Shiraz
2 - Islamic Azad University Shiraz
3 - Islamic Azad University Shiraz
کلید واژه: Adaptivity , Feature Extraction , Font Detection , Redundant Keypoint Elimination Method (RKEM) , Speeded-Up Robust Features (SURF),
چکیده مقاله :
Farsi font detection is considered as the first stage in the Farsi optical character recognition (FOCR) of scanned printed texts. To this aim, this paper proposes an improved version of the speeded-up robust features (SURF) algorithm, as the feature detector in the font recognition process. The SURF algorithm suffers from creation of several redundant features during the detection phase. Thus, the presented version employs the redundant keypoint elimination method (RKEM) to enhance the matching performance of the SURF by reducing unnecessary keypoints. Although the performance of the RKEM is acceptable in this task, it exploits a fixed experimental threshold value which has a detrimental impact on the results. In this paper, an Adaptive RKEM is proposed for the SURF algorithm which considers image type and distortion, when adjusting the threshold value. Then, this improved version is applied to recognize Farsi fonts in texts. To do this, the proposed Adaptive RKEM-SURF detects the keypoints and then SURF is used as the descriptor for the features. Finally, the matching process is done using the nearest neighbor distance ratio. The proposed approach is compared with recently published algorithms for FOCR to confirm its superiority. This method has the capability to be generalized to other languages such as Arabic and English.
Farsi font detection is considered as the first stage in the Farsi optical character recognition (FOCR) of scanned printed texts. To this aim, this paper proposes an improved version of the speeded-up robust features (SURF) algorithm, as the feature detector in the font recognition process. The SURF algorithm suffers from creation of several redundant features during the detection phase. Thus, the presented version employs the redundant keypoint elimination method (RKEM) to enhance the matching performance of the SURF by reducing unnecessary keypoints. Although the performance of the RKEM is acceptable in this task, it exploits a fixed experimental threshold value which has a detrimental impact on the results. In this paper, an Adaptive RKEM is proposed for the SURF algorithm which considers image type and distortion, when adjusting the threshold value. Then, this improved version is applied to recognize Farsi fonts in texts. To do this, the proposed Adaptive RKEM-SURF detects the keypoints and then SURF is used as the descriptor for the features. Finally, the matching process is done using the nearest neighbor distance ratio. The proposed approach is compared with recently published algorithms for FOCR to confirm its superiority. This method has the capability to be generalized to other languages such as Arabic and English.
[1] Mostafa Rahmandoust, "The Death of Pitcher: Persian Parables and its Stories," Tehran: School Publications, , 1387.
[2] University of Texas: New Persian Language.
[3] https://w3techs.com/technologies/overview/content_language/all/.
[4] A. Zramdini and R. Ingold, "Optical font recognition using typographical features," IEEE Transactions on pattern analysis and machine intelligence, vol. 20, no. 8, pp. 877-882, 1998.
[5] M. Rajdev, D. Sahay, S. Khare, and S. Nainan, "Optical Character and Font Recognizer," in International Conference on Advances in Computing and Data Sciences, 2019, pp. 477-486: Springer.
[6] B. Bataineh, S. N. H. S. Abdullah, and K. Omar, "A statistical global feature extraction method for optical font recognition," in Asian Conference on Intelligent Information and Database Systems, 2011, pp. 257-267: Springer.
[7] M. A. Mousa, M. S. Sayed, and M. I. Abdalla, "An efficient algorithm for Arabic optical font recognition using scale-invariant detector," International Journal on Document Analysis and Recognition (IJDAR), vol. 18, no. 3, pp. 263-270, 2015.
[8] C. Avilés-Cruz, R. Rangel-Kuoppa, M. Reyes-Ayala, A. Andrade-Gonzalez, and R. Escarela-Perez, "High-order statistical texture analysis––font recognition applied," Pattern Recognition Letters, vol. 26, no. 2, pp. 135-145, 2005.
[9] V.-C. Juan and A.-C. Carlos, "Font recognition by invariant moments of global textures," in Proceedings of international workshop VLBV05 (very low bit-rate video-coding 2005), 2005, pp. 15-16.
[10] M. Lutf, X. You, Y.-m. Cheung, and C. P. Chen, "Arabic font recognition based on diacritics features," Pattern Recognition, vol. 47, no. 2, pp. 672-684, 2014.
[11] G. D. Joshi, S. Garg, and J. Sivaswamy, "A generalised framework for script identification," International Journal of Document Analysis and Recognition (IJDAR), vol. 10, no. 2, pp. 55-68, 2007.
[12] H. Khosravi and E. Kabir, "Farsi font recognition based on Sobel–Roberts features," Pattern Recognition Letters, vol. 31, no. 1, pp. 75-82, 2010.
[13] Y. Zhu, T. Tan, and Y. Wang, "Font recognition based on global texture analysis," IEEE Transactions on pattern analysis and machine intelligence, vol. 23, no. 10, pp. 1192-1200, 2001.
[14] F. Slimane, S. Kanoun, A. M. Alimi, R. Ingold, and J. Hennebert, "Gaussian mixture models for arabic font recognition," in 2010 20th International Conference on Pattern Recognition, 2010, pp. 2174-2177: IEEE.
[15] E. Rashedi, E. Nezam abadipour, and a. S. Saryazdi, "Farsi font recognition using correlation coefficients (in Farsi)," 4th Conf. on Machine Vision and Image Processing, Ferdosi Mashhad, 2007.
[16] N. E. B. Amara and S. Gazzah, "Une approche d'identification des fontes arabes," in Conférence Internationale Francophone sur l'Ecrit et le Document (CIFED 04), 2004.
[17] Y. Pourasad, H. Hassibi, and A. Ghorbani, "Farsi font recognition using holes of letters and horizontal projection profile," in International Conference on Innovative Computing Technology, 2011, pp. 235-243: Springer.
[18] Y. Pourasad, H. Hassibi, and A. Ghorbani, "Farsi font recognition in document images using PPH features," International Journal of Natural and Engineering Sciences (IJNES) E-ISSN: 2146-0086, vol. 2, no. 3, pp. 17-20, 2011.
[19] M. Zahedi and S. Eslami, "Farsi/Arabic optical font recognition using SIFT features," Procedia Computer Science, vol. 3, pp. 1055-1059, 2011.
[20] A. Nicolaou, F. Slimane, V. Maergner, and M. Liwicki, "Local binary patterns for arabic optical font recognition," in 2014 11th IAPR International Workshop on Document Analysis Systems, 2014, pp. 76-80: IEEE.
[21] J. H. AlKhateeb, J. Ren, S. S. Ipson, and J. Jiang, "Knowledge-based baseline detection and optimal thresholding for words segmentation in efficient pre-processing of handwritten Arabic text," in Fifth International Conference on Information Technology: New Generations (itng 2008), 2008, pp. 1158-1159: IEEE.
[22] C. ERGÜN and S. Norozpour, "Farsi document image recognition system using word layout signature," Turkish Journal of Electrical Engineering & Computer Sciences, vol. 27, no. 2, pp. 1477-1488, 2019.
[23] D. G. Lowe, "Distinctive image features from scale-invariant keypoints," International journal of computer vision, vol. 60, no. 2, pp. 91-110, 2004.
[24] Z. Hossein-Nejad and M. Nasri, "RKEM: Redundant Keypoint Elimination Method in Image Registration," IET Image Processing, vol. 11, no. 5, pp. 273-284, 2017.
[25] Z. H.-N. a. M. Nasri, "Copy-Move Image Forgery Detection Using Redundant Keypoint Elimination Method," in Cryptographic and Information Security Approaches for Images and Videos, S. Ramakrishnan, Ed. Boca Raton: CRC Press, pp. 773-797, 2019.
[26] H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool, "Speeded-up robust features (SURF)," Computer vision and image understanding, vol. 110, no. 3, pp. 346-359, 2008.
[27] K. Mikolajczyk and C. Schmid, "A performance evaluation of local descriptors," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 27, no. 10, pp. 1615-1630, 2005.
[28] K. Mikolajczyk and C. Schmid, "A performance evaluation of local descriptors," IEEE transactions on pattern analysis and machine intelligence
