Abstract




 
   

IJE TRANSACTIONS A: Basics Vol. 27, No. 1 (January 2014) 91-100   

downloaded Downloaded: 209   viewed Viewed: 2153

  A NEW METHOD FOR ROOT DETECTION IN MINIRHIZOTRON IMAGES: HYPOTHESIS TESTING BASED ON ENTROPY-BASED GEOMETRIC LEVEL SET DECISION
 
S. V. Shojaedini and M. Heidari
 
( Received: June 10, 2013 – Accepted in Revised Form: September 14, 2013 )
 
 

Abstract    In this paper a new method is introduced for root detection in minirhizotron images for root investigation. In this method firstly a hypothesis testing framework is defined to separate roots from background and noise. Then the correct roots are extracted by using an entropy-based geometric level set decision function. Performance of the proposed method is evaluated on real captured images in two different scenarios. In the first scenario images contain several roots however the second scenario belongs to no-root images, which increases the chance of false detection error. The obtained results show the greater ability of the proposed method in root detection compared with present approaches in all examined images. Furthermore it can be shown that better detection of roots in proposed algorithm not only doesn't lead to extracting more false particles but also it decreases rate of false detections compared to existing algorithms.

 

Keywords    Root Detection, Minirhizotron Images, Hypothesis testing, Entropy, Geometric Level Set

 

چکیده    در این مقاله روشی جدید به منظور آشکارسازی ریشه های گیاهان در تصاویر اخذ شده توسط سیستم مینی رایزوترون ارایه می شود. در روش پیشنهادی به منظور تفکیک ریشه ها از پس زمینه و نویز موجود در تصاویر ابتدا مساله با استفاده از مفهوم آزمون فرضها بازتعریف می شود. در گام بعدی تابع تصمیمی که با استفاده از سطوح همتراز مبتنی بر آنتروپی تصاویر تعریف می شود، محاسبه می گردد. مقدار این تابع می تواند فرضیه صحیح را مشخص نموده و لذا ریشه را از پس زمینه و نویز تصاویر تفکیک نماید. عملکرد روش پیشنهادی با استفاده از تصاویر اخذ شده توسط سیستم مینی رایزوترون در دو سناریوی مختلف آزموده می شود. در اولین سناریو تصاویر مورد آزمون شامل ریشه هستند، در حالی که سناریوی دوم مربوط به تصاویری است که شامل هیچ ریشه ای نمی باشند. نتایج حاصل از مقایسه عملکرد روش پیشنهادی و چند روش موجود حاکی از برتری روش پیشنهادی این مقاله در استخراج ریشه های صحیح هستند. همچنین نتایج به دست آمده نشان می دهند که به موازات برتری مزبور، روش پیشنهادی این مقاله ریشه های نادرست کمتری را نیز نسبت به سایر روش های آزموده شده به دست می دهد.

References   

1.     Hodge, A., Berta, G., Doussan, C., Merchan, F. and Crespi, M., "Plant root growth, architecture and function", Plant and Soil,  Vol. 321, No. 1-2, (2009), 153-187.

2.     Genc, Y., Huang, C. Y. and Langridge, P., "A study of the role of root morphological traits in growth of barley in zinc-deficient soil", Journal of Experimental Botany,  Vol. 58, No. 11, (2007), 2775-2784.

3.     Himmelbauer, M., "Estimating length, average diameter and surface area of roots using two different image analyses systems", Plant and Soil,  Vol. 260, No. 1-2, (2004), 111-120.

4.     Ping, X., Zhou, G., Zhuang, Q., Wang, Y., Zuo, W., Shi, G., Lin, X., and Wang, Y., "Effects of sample size and position from monolith and core methods on the estimation of total root biomass in a temperate grassland ecosystem in inner mongolia", Geoderma,  Vol. 155, No. 3, (2010), 262-268.

5.     Silva, D. D. and Beeson, R. C., "A large-volume rhizotron for evaluating root growth under natural-like soil moisture conditions", HortScience,  Vol. 46, No. 12, (2011), 1677-1682.

6.     Hendricks, J. J., Hendrick, R. L., Wilson, C. A., Mitchell, R. J., Pecot, S. D., and Guo, D., "Assessing the patterns and controls of fine root dynamics: An empirical test and methodological review", Journal of Ecology,  Vol. 94, No. 1, (2006), 40-57.

7.     Munoz-Romero, V., Benítez-Vega, J., López-Bellido, L. and López-Bellido, R. J., "Monitoring wheat root development in a rainfed vertisol: Tillage effect", European Journal of Agronomy,  Vol. 33, No. 3, (2010), 182-187.

8.     Zeng, G., Birchfield, S. T. and Wells, C. E., "Automatic discrimination of fine roots in minirhizotron images", New Phytologist,  Vol. 177, No. 2, (2008), 549-557.

9.     Andrén, O., Elmquist, H. and Hansson, A.-C., "Recording, processing and analysis of grass root images from a rhizotron", Plant and Soil,  Vol. 185, No. 2, (1996), 259-264.

10.   Hassanpour, H. and Yousefian, H., "An improved pixon-based approach for image segmentation", International Journal of Engineering-Transactions A: Basics,  Vol. 24, No. 1, (2010), 25.

11.   Smit, A. L., "Root methods: A handbook", Springer,  (2000).

12.   Vamerali, T., Ganis, A. and Mosca, G., "Methods for thresholding minirhizotron root images", International Symposium of Root Research and Applications, Vienna, Austria,, (2009), 1-2.

13.   Vamerali, T., Ganis, A., Bona, S. and Mosca, G., "An approach to minirhizotron root image analysis", Plant and Soil,  Vol. 217, No. 1-2, (1999), 183-193.

14.   Erz, G. and Posch, S., A region based seed detection for root detection in minirhizotron images, in Pattern recognition., Springer. (2003) 482-489.

15.   Vamerali, T., Guarise, M., Ganis, A., Bona, S. and Mosca, G., Analysis of root images from auger sampling with a fast procedure: A case of application to sugar beet, in Roots: The dynamic interface between plants and the earth., Springer. (2003), 387-397.

16.   Nater, E. A., Nater, K. D. and Baker, J. M., "Application of artificial neural system algorithms to image analysis of roots in soil, i. Initial results", Geoderma,  Vol. 53, No. 3, (1992), 237-253.

17.   Zeng, G., Birchfield, S. T. and Wells, C. E., "Detecting and measuring fine roots in minirhizotron images using matched filtering and local entropy thresholding", Machine Vision and Applications,  Vol. 17, No. 4, (2006), 265-278.

18.   Baraldi, A. and Parmiggiani, F., "An investigation of the textural characteristics associated with gray level cooccurrence matrix statistical parameters", Geoscience and Remote Sensing, IEEE Transactions on,  Vol. 33, No. 2, (1995), 293-304.

19.   Kekre, H., Thepade, S. D., Sarode, T. K. and Suryawanshi, V., "Image retrieval using texture features extracted from glcm, lbg and kpe", International Journal of Computer Theory and Engineering,  Vol. 2, No. 5, (2010), 1793-8201.

20.   Horng, M.-H., "Multilevel minimum cross entropy threshold selection based on the honey bee mating optimization", Expert Systems with Applications,  Vol. 37, No. 6, (2010), 4580-4592.

21.   Pal, N. R. and Pal, S. K., "Image model, poisson distribution and object extraction", International Journal of Pattern Recognition and Artificial Intelligence,  Vol. 5, No. 03, (1991), 459-483.

22.   Lee, S.-K., Lo, C.-S., Wang, C.-M., Chung, P.-C., Chang, C.-I., Yang, C.-W., and Hsu, P.-C., "A computer-aided design mammography screening system for detection and classification of microcalcifications", International Journal of Medical Informatics,  Vol. 60, No. 1, (2000), 29-57.

23.   Caselles, V., Kimmel, R. and Sapiro, G., "Geodesic active contours", International Journal of Computer Vision,  Vol. 22, No. 1, (1997), 61-79.

24.   Osher, S. and Fedkiw, R., "Level set methods and dynamic implicit surfaces", Springer,  Vol. 153,  (2003).

25.           Zhao, H.-K., Chan, T., Merriman, B. and Osher, S., "A variational level set approach to multiphase motion", Journal of Computational Physics,  Vol. 127, No. 1, (1996), 179-195.





International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir