ABSTRACT
In this paper, we present a comparative study of segmentation methods, tested for an issue of tree leaves extraction. Approaches implemented include processes using thresholding, clustering, or even active contours. The observation criteria, such as the Dice index, Hamming measure or SSIM for example, allow us to highlight the performance obtained by the guided active contour algorithm that is specially dedicated to tree leaf segmentation (G. Cerutti et al., Guiding Active Contours for Tree Leaf Segmentation and Identification. ImageCLEF2011). We currently offer a dedicated segmentation tree leaf benchmark, comparing fourteen segmentation methods (ten automatic and four semi-automatic) following twenty evaluation criteria.
- {Beuc79} S. Beucher and C. Lantuéjoul, Use of watersheds in contour detection. REMD, 1979.Google Scholar
- {Beuc93} S. Beucher and F. Meyer, The morphological approach to segmentation: the watershed transformation. MMIP, 1993, p. 433--481.Google Scholar
- {Boyk01} Y. Boykov and M. Jolly, Interactive graph cuts for optimal boundary and region segmentation. ICCV, 2001, vol. 1, p. 105--112.Google ScholarCross Ref
- {Brig00} P. Brigger and al., B-spline snakes: a exible tool for parametric contour detection. Trans. on Image Processing, 2000, vol. 9(9), p. 1484--1496. Google ScholarDigital Library
- {Cann86} J. Canny, A computational approach to edge detection. PAMI, 1986, vol. 8(6), p. 679--698. Google ScholarDigital Library
- {Ceru11} G. Cerutti and al., Guiding Active Contours for Tree Leaf Segmentation and Identification. CLEF, 2011.Google Scholar
- {Chan01} T. Chan and L. Vese, Active Contours Without Edges. Trans. on Image Processing, 2001, vol. 10(2), p. 266--277. Google ScholarDigital Library
- {Chen95} Y. Cheng, Mean Shift, Mode Seeking, and Clustering. PAMI, 1995, vol. 17(8), p. 790--799. Google ScholarDigital Library
- {Felz04} P. Felzenszwalb and D. Huttenlocher, Efficient Graph-Based Image Segmentation. IJCV, 2004, vol. 59(2), p. 167--181. Google ScholarDigital Library
- {Goëa11} H. Goëau and al., The clef 2011 plant images classification task. 2011.Google Scholar
- {Grei89} D. Greig and al., Exact maximum a posteriori estimation for binary images. JRSS, 1989, vol. 51, p. 21--279.Google Scholar
- {Horo74} S. Horowitz and T. Pavlidis, Picture segmentation by a directed split and merge procedure. ICPR, 1974, p. 424--433.Google Scholar
- {Horv06} J. Horvath, Image segmentation using fuzzy c-means. SAMI, 2006.Google Scholar
- {Kass87} M. Kass and al., Snakes: Active contour model. IJCV, 1987, p. 321--331.Google Scholar
- {Kuma12} N. Kumar and al., Leafsnap: a computer vision system for automatic plant species identification. ECCV, 2012, p. 502--516. Google ScholarDigital Library
- {Kurt10} C. Kurtz and al., Multiresolution region-based clustering for urban analysis. IJRS, 2010, vol. 31(22), p. 5941--5973. Google ScholarDigital Library
- {Lync06} M. Lynch and al., Automatic segmentation of the left ventricle cavity and myocardium in MRI data. CBM, 2006, vol. 36(4), p. 389--407. Google ScholarDigital Library
- {Marr80} D. Marr and E. Hildreth, Theory of Edge Detection. Biological Sciences, 1980, vol. 207(1167), p. 187--217.Google Scholar
- {Neto06} J. Neto and al., Individual leaf extractions from young canopy images using Gustafson-Kessel clustering and a genetic algorithm. CEA, 2006, vol. 51(1), p. 66--85. Google ScholarDigital Library
- {Otsu79} N. Otsu, A threshold selection method from gray-level histograms. TSMC, 1979, vol. 9(1), p. 62--66.Google Scholar
- {Roth04} C. Rother and al., "Grabcut": interactive foreground extraction using iterated graph cuts. SIGGRAPH, 2004, p. 39--314. Google ScholarDigital Library
- {Salm06} N. Salman, Image segmentation based on watershed and edge detection techniques. IAJIT, 2006, vol. 3(2), p. 104--110.Google Scholar
- {Teng11} C. Teng and al., Leaf segmentation, classification, and three-dimensional recovery from a few images with close viewpoints. Opt. Eng., 2011, vol. 50(3).Google Scholar
- {Vall12} N. Valliammal and S. Geethalakshmi, Plant Leaf Segmentation Using Non Linear K means Clustering. IJCSI, 2012, vol. 9(1), p. 212--218.Google Scholar
- {Wang84} S. Wang and R. Haralick, Automatic multi-threshold selection. CVGIP, 1984, vol. 25, p. 46--67.Google Scholar
- {Wang04} Z. Wang and al., Image quality assessment: From error visibility to structural similarity. TIP, 2004, vol. 13(4), p. 600--612. Google ScholarDigital Library
- {Zimm02} C. Zimmer and al., Segmentation and tracking of migrating cells in videomicroscopy with parametric active contours: a toll for cell-base drug testing. Medical Imaging, 2002, vol. 21(10), p. 1212--1221.Google ScholarCross Ref
Index Terms
- Comparative study of segmentation methods for tree leaves extraction
Recommendations
Tree Leaves Extraction in Natural Images: Comparative Study of Preprocessing Tools and Segmentation Methods
In this paper, we propose a comparative study of various segmentation methods applied to the extraction of tree leaves from natural images. This study follows the design of a mobile application, developed by Cerutti et al. (published in ReVeS ...
Review of brain MRI image segmentation methods
Brain image segmentation is one of the most important parts of clinical diagnostic tools. Brain images mostly contain noise, inhomogeneity and sometimes deviation. Therefore, accurate segmentation of brain images is a very difficult task. However, the ...
Survey on liver CT image segmentation methods
The segmentation of liver using computed tomography (CT) data has gained a lot of importance in the medical image processing field. In this paper, we present a survey on liver segmentation methods and techniques using CT images, recent methods presented ...
Comments