Distance Between Vector-Valued Representations of Objects in Images with Application in Object Detection and Classification
We present a novel approach to measuring distances between objects in images, suitable for information-rich object representations which simultaneously capture several properties in each image pixel. Multiple spatial fuzzy sets on the image domain, unified in a vector-valued fuzzy set, are used to model such representations. Distance between such sets is based on a novel point-to-set distance suitable for vector-valued fuzzy representations. The proposed set distance may be applied in, e.g., template matching and object classification, with an advantage that a number of object features are simultaneously considered. The distance measure is of linear time complexity w.r.t. the number of pixels in the image. We evaluate the performance of the proposed measure in template matching in presence of noise, as well as in object detection and classification in low resolution Transmission Electron Microscopy images.
The authors acknowledge Amit Suveer, Anca Dragomir, and Ida-Maria Sintorn for acquired and annotated TEM images of Cilia. Ministry of Science of the Republic of Serbia is acknowledged for support through the Projects ON 174008 and III 44006 of MI-SANU. N. Sladoje is also supported by Swedish Governmental Agency for Innovation Systems (VINNOVA).
- 6.Lindblad, J., Ćurić, V., Sladoje, N.: On set distances and their application to image registration. In: Proceedings of the IEEE International Symposium Image Signal Processing and Analysis (ISPA), pp. 449–454 (2009)Google Scholar
- 13.Sladoje, N., Lindblad, J.: High precision boundary length estimation by utilizing gray-level information. IEEE Trans. Pattern Anal. Mach. Intell. 31(2), 357–363 (2009)Google Scholar
- 15.Suveer, A., Sladoje, N., Lindblad, J., Dragomir, A., Sintorn, I.-M.: Automated detection of cilia in low magnification transmission electron microscopy images using template matching. In: Proceedings of IEEE International Symposium on Biomedical Imaging (ISBI), pp. 386–390 (2016)Google Scholar
- 17.Öfverstedt, J., Sladoje, N., Lindblad, J.: Distance between vector-valued fuzzy sets based on intersection decomposition with applications in object detection. In: Angulo, J., et al. (eds.) ISMM 2017. LNCS, vol. 10225, pp. 395–407. Springer, Cham (2017). doi: 10.1007/978-3-319-57240-6_32 Google Scholar