ENHANCING THE EFFECTIVENESS OF BLOB DETECTION USING THE GLOG FILTER
Main Article Content
Abstract
This paper proposes two strategies to optimize the computational efficiency of the Generalized Laplacian of Gaussian (gLoG) filter for blob detection. The first strategy employs Principal Component Analysis (PCA) to identify dominant orientations and reduce the number of scales that need to be evaluated, thereby eliminating redundant computations. The second strategy exploits the distribution of local gradient magnitudes to select and apply filters along the most relevant orientations. Experiments on the Oxford and ORL datasets show that the proposed methods maintain high repeatability and strong localization accuracy while significantly reducing processing time. Specifically, the PCA‑based method achieves a 44% reduction in runtime with only a 1.7% drop in matching accuracy, whereas the gradient‑based variant attains a 37% speed-up. The compact design and geometric consistency of the proposed filters highlight their potential for feature extraction tasks under limited computational resources.
Keywords
Phát hiện blob, Laplacian of Gaussian tổng quát (gLoG), trích xuất đặc trưng.
Article Details
References
[2] H. Kong, H. C. Akakin, and S. E. Sarma, "A generalized laplacian of gaussian filter for blob detection and its applications," IEEE Transactions on Cybernetics, 43(6):179-1733, 2013, DOI:10.1109/TSMCB.2012.2228639
[3] R. Reisenhofer and E. J. King, "Edge, ridge, and blob detection with symmetric molecules," SIAM Journal on Imaging Sciences, 12(4):1585-1626, 2019, DOI:10.1137/19M1240861
[4] J. Chen, L. Y. Duan, F. Gao, J. Cai, A. C. Kot, and T. Huang, "A low complexity interest point detector," IEEE Signal Processing Letters, 22(2):172-176, 2014, DOI:10.1109/LSP.2014.2354237
[5] P. Shivakumara, T. Q. Phan, and C. L. Tan, "A laplacian approach to multi-oriented text detection in video," IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(2):412-419, 2010, DOI:10.1109/TPAMI.2010.166
[6] Z. Miao, X. Jiang, and K. H. Yap, "Contrast invariant interest point detection by zero-norm log filter," IEEE Transactions on Image Processing, 25(1):331-342, 2015, DOI:10.1109/TIP.2015.2470598
[7] H. Xu, C. Lu, R. Berendt, and N. Jha, "Automatic nuclei detection based on generalized laplacian of gaussian filters," IEEE Journal of Biomedical and Health Informatics, 21(3):826-837, 2016, DOI:10.1109/JBHI.2016.2544245
[8] V. Majanga and S. Viriri, "Automatic blob detection for dental caries," Applied Sciences, 11(19):9232, 2021, DOI:10.3390/app11199232
[9] G. Wang, C. Lopez-Molina, and B. De Baets, "Blob reconstruction using unilateral second order gaussian kernels with application to high-iso long-exposure image denoising," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Venice, Italy, 2017, pp. 4817-4825, DOI:10.1109/ICCV.2017.516
[10] G. Wang, C. Lopez-Molina, and B. De Baets, "Automated blob detection using iterative laplacian of gaussian filtering and unilateral second-order gaussian kernels," Digital Signal Processing, vol. 96, pp. 102592, 2020, DOI:10.1016/j.dsp.2019.102592
[11] C. Nguyen Dinh, M. Delalandre, D. Conte, and T. A. Pham, "Fast rt-log operator for scene text detection," Journal of Real-Time Image Processing, 18(1)19-36, 2021, DOI:10.1007/s11554-020-00942-7
[12] V. L. Petrović, "A method for real-time memory efficient implementation of blob detection in large images," Serbian Journal of Electrical Engineering, 14(1):67-84, 2017, DOI:10.2298/SJEE1701067P
[13] R. Acevedo-Avila, M. Gonzalez-Mendoza, and A. Garcia-Garcia, "A linked list-based algorithm for blob detection on embedded vision-based sensors," Sensors, 16(6):782, 2016, DOI:10.3390/s16060782
[14] X. Descombes, "Multiple objects detection in biological images using a marked point process framework," Methods, vol. 115, pp. 2-8, 2017, DOI:10.1016/j.ymeth.2016.09.009
[15] K. Esbensen and P. Geladi, "Principal component analysis: Concept, geometrical interpretation, mathematical background, algorithms, history, practice," in Comprehensive Chemometrics: Chemical and Biochemical Data Analysis, vol. 2, S. D. Brown, R. Tauler, and B. Walczak, Eds. Amsterdam, Netherlands: Elsevier, 2020, pp. 3-15, DOI:10.1016/b978-0-444-64165-6.05002-3
[16] T. Lindeberg, "Feature detection with automatic scale selection," International Journal of Computer Vision, vol. 30, pp. 79-116, 1998, DOI:10.1023/A:1008045108935
[17] Y. Cho, D. Kim, S. Saeed, M. U. Kakli, S.-H. Jung, and J. Seo, "Keypoint detection using higher order laplacian of gaussian," IEEE Access, vol. 8, pp. 10416–10425, 2020, DOI:10.1109/ACCESS.2020.2965169
[18] K. Mikolajczyk et al., "A comparison of affine region detectors," International Journal of Computer Vision, vol. 65, pp. 43-72, 2005, DOI:10.1007/s11263-005-3848-x
[19] X. Jiang, B. Mandal, and A. Kot, "Eigenfeature regularization and extraction in face recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(3):383-394, 2008, DOI:10.1109/TPAMI.2007.70708