نوع مقاله: مقاله علمی-پژوهشی لاتین

نویسندگان

1 واحد شوشتر، دانشگاه آزاد اسلامی

2 دانشگاه تربیت مدرس

چکیده

به‌منظور افزایش دقت بخش‌بندی تصاویر گل محمدی، چند روش متعادل‌سازی هیستوگرام برای بهبود کیفیت تصاویر رنگی این گل‌ها و چند روش آستانه‌گیری برای بخش‌بندی گل‌های مذکور در تصویر، مورد بررسی قرار گرفت. قابل ذکر است که تصویربرداری در فضای باز و ساعات مختلف روز و شرایط متفاوتی از شدت نور انجام گرفت. برای بررسی دقیق‌تر، یک آزمایش فاکتوریل در قالب یک طرح کاملاً تصادفی با دو عامل روش متعادل‌سازی هیستوگرام، در 8 سطح و روش آستانه‌گیری، در 15 سطح به‌کار گرفته شد. روش‌های متعادل‌سازی هیستوگرام عبارت بودند از: CHE, BBHE, BHEPL-D, DQHEPL, DSIHE, RMSHE, RSIHE و تیمار شاهد بدون متعادل‌سازی هیستوگرام (NHE). همچنین روش‌های آستانه‌گیری عبارت بودند از: Huang, Intermodes, Isodata, Li, maximum entropy, mean, minimum, moments, Otsu, percentile, Renyi’s entropy, Shanbhag, Yen, constant  و global basic thresholding method. تاثیر این دو عامل بر خصوصیات تصویر بخش‌بندی شده از قبیل: درصد سطوحی که به اشتباه بخش‌بندی شده‌اند (PISA)، درصد هم‌پوشانی سطوح (POA)، درصد سطوحی که تشخیص داده نشده‌اند (PUA) و درصد سطوح تشخیص داده شده گل‌ها (PDF) مورد بررسی قرار گرفت. نتیجه روش‌های متعادل‌سازی هیستوگرام نشان داد که DQHEPL و NHE پایین‌ترین میزان PUA (به‌ترتیب 13/11% و 32/8%)، بالاترین POA (به‌ترتیب 35/89% و 07/92%) و بالاترین PDF (به‌ترتیب 88/61% و 94/64%) را از لحاظ آماری دارا می‌باشند. روش‌های آستانه‌گیری تاثیر معنی‌داری بر PISA, PUA, POA و PDF داشتند. بزرگ‌ترین مقادیر PDF به روش آستانه‌گیری constant، minimum و Intremodes (به‌ترتیب 07/75%، 08/73% و 30/74%)، همچنین کمترین مقدار PISA مربوط به این موارد بود (به‌ترتیب 35/0%، 29/1% و 35/0%) و PUA (به‌ترتیب 72/33%، 09/23% و 56/15%). این روش‌ها بزرگ‌ترین مقدار POA را نشان دادند (به‌ترتیب 73/80%، 70/76% و 67/84%). لذا روش‌های مناسبی برای بخش‌بندی گل محمدی در تصویر رنگی محسوب می‌گردند.

کلیدواژه‌ها

عنوان مقاله [English]

Evaluating Histogram Equalization and Thresholding Methods for Segmentation of Rosa Damascena Flowers in Color Images

نویسندگان [English]

  • A Kohan 1
  • S Minaei 2

1 Shoushtar Branch, Islamic Azad University

2 Tarbiat Modares University

چکیده [English]

Several histogram equalization methods for enhancing the color images of Rosa Damascena flowers and some thresholding methods for segmentation of the flowers were examined. Images were taken outdoors at different times of day and light conditions. A factorial experiment in the form of a Completely Randomized Design with two factors of histogram equalization method at 8 levels and thresholding method at 15 levels, was implemented. Histogram equalization methods included: CHE, BBHE, BHEPL-D, DQHEPL, DSIHE, RMSHE, RSIHE, and no histogram equalization (NHE) as the control. Thresholding method levels were: Huang, Intermodes, Isodata, Li, maximum entropy, mean, minimum, moments, Otsu, percentile, Renyi’s entropy, Shanbhag, Yen, constant, and global basic thresholding method. The effect of these factors on the properties of the segmented images such as the Percentage of Incorrectly Segmented Area (PISA), Percentage of Overlapping Area (POA), Percentage of Undetected Area (PUA), and Percentage of Detected Flowers (PDF) was investigated. Results of histogram equalization analysis showed that DQHEPL and NHE have the statistically significant lowest PUA (11.13% and 8.32%, respectively), highest POA (89.35% and 92.07%, respectively), and highest PDF (61.88% and 64.94%, respectively). Thresholding methods had a significant effect on PISA, PUA, POA, and PDF. The highest PDF belonged to constant, minimum, and Intermodes (75.07%, 73.08% and 74.30%, respectively) They also had the lowest PISA (0.35%, 1.29%, and 1.85%, respectively) and PUA (33.72%, 23.09%, and 15.56%, respectively). These methods had the highest POA (80.73%, 76.70%, and 84.67%, respectively). Hence, they are suitable methods for segmentation of Rosa Damascena flowers in color images.

کلیدواژه‌ها [English]

  • Histogram equalization
  • Image processing
  • Image Segmentation
  • Rosa Damascena
  • Thresholding

  1. Bachche S. 2015. Deliberation on Design Strategies of Automatic Harvesting Systems: A Survey. Robotics 4: 194-222.
  2. Dorj U. O., M. Lee, and S. S. Yun 2017. A Yield Estimation in Citrus Orchards via Fruit Detection and Counting Using Image Processing. Computers and Electronics in Agriculture 140: 103-112.
  3. Doyle, W. 1962. Operation Useful for Similarity-Invariant Pattern Recognition. Journal of the Association for Computing Machinery 9: 259-267.
  4. Farhan Khan, M., E. Khan, and Z. A. Abbasi. 2015. Image Contrast Enhancement Using Normalized Histogram Equalization. Optik-International Journal for Light and Electron Optics 126: 4868 4875.
  5. Gonzalez, R. C., and R. E. Woods. 1992. Digital Image Processing. Pearson Prentice Hall. Delhi.
  6. Hajhashemi, V., A. Ghannadi, and M. Hajiloo. 2010. Analgesic and Anti-inflammatory Effects of Rosa damascenaHydroalcoholic Extract and its Essential Oil in Animal Models. Iranian Journal of Pharmaceutical Research 9 (2): 163-168.
  7. Huang, L. K., and M. J. J. Wang. 1995. Image Thresholding by Minimizing the Measures of Fuzziness. Pattern Recognition 28 (1): 41-51.
  8. Ibrahim, H., and N. S. P. Kong. 2007. Brightness Preserving Dynamic Histogram Equalization for Image Contrast Enhancement. IEEE Transactions on Consumer Electronics 53: 1752-1758.
  9. Jahanbakhshi, A., and K. Kheiralipour. 2018. Carrot Sorting Based on Shape using Image Processing, Artificial Neural Network, and Support Vector Machine. Journal of Agricultural Machinery 9 (2): 295-307.
  10. Jidong, L., L. De-An, J. Wei, and D. Shihong. 2016. Recognition of Apple Fruit in Natural Environment. Optik-International Journal for Light and Electron Optics 127: 1354-1362.
  11. Kapur N., P. K. Sahoo, and A. K. C. Wong. 1985. A New Method for Gray-Level Picture Thresholding Using the Entropy of the Histogram. Computer Vision, Graphics, and Image Processing 29 (3): 273-285.
  12. Kim, Y. T. 1997. Contrast Enhancement Using Brightness Preserving Bi-Histogram Equalization. IEEE Transactions on Consumer Electronics 43 (1): 1-8.
  13. Kohan, A., A. M. Borghaee, M. Yazdi, S. Minaei, and M. J. Sheykhdavudi. 2011. Robotic Harvesting of Rosa Damascena Using Stereoscopic Machine Vision. World Applied Sciences Journal 12 (2): 231-237.
  14. Li C. H., and P. K. S. Tam. 1998. An Iterative Algorithm for Minimum Cross Entropy Thresholding. Pattern Recognition Letters 19: 771-776.
  15. Li H., W. S. Lee, and K. Wang. 2014. Identifying Blueberry Fruit of Different Growth Stages Using Natural Outdoor Color Images. Computers and Electronics in Agriculture 106: 91-101.
  16. Mohamadi Monavar, H., R. Alimardani, and M. Omid. 2013. Computer Vision Utilization for Detection of Green House Tomato under Natural Illumination. Journal of Agricultural Machinery 3 (1): 9-15. (In Farsi).
  17. Okamoto, H., and W. S. Lee. 2009. Green Citrus Detection Using Hyperspectral Imaging. Computers and Electronics in Agriculture 66: 201-208.
  18. Ooi, C. H., N. S. P. Kong, and H. Ibrahim. 2009. Bi-Histogram Equalization with a Plateau limit for Digital Image Enhancement. IEEE Transactions on Consumer Electronics 55: 2072-2080.
  19. Ooi, C. H., and N. A. M. Isa. 2010a. Adaptive Contrast Enhancement Methods with Brightness Preserving. IEEE Transactions on Consumer Electronics 56: 2543-2551.
  20. Ooi, C. H., and N. A. M. Isa. 2010b. Quadrants Dynamic Histogram Equalization for Contrast Enhancement. IEEE Transactions on Consumer Electronics 56: 2552-2559.
  21. Otsu, N. 1979. A Threshold Selection Method from Gray Level Histograms. IEEE Transaction on Systems, Man and Cybernetics 9 (1): 62-66.
  22. Patel, O., P. S. Yogendra, M. Sharma, and S. Sharma. 2013. A Comparative Study of Histogram Equalization Based Image Enhancement Techniques for Brightness Preservation and Contrast Enhancement. Signal & Image Processing: An International Journal 4 (5): 11-25.
  23. Prewitt, J. M. S., and M. L. Mendelsohn. 1966. The Analysis of Cell Images. Annals of the New York Academy of Sciences 128: 1035-1053.
  24. Qiao, X., J. Bao, L. Zeng, J. Zou, and D. Li. 2017. An Automatic Active Contour Method for Sea Cucumber Segmentation in Natural Underwater Environments. Computers and Electronics in Agriculture 135: 134-142.
  25. Ramos, P. J., F. A. Prieto, E. C. Montoya, and C. E. Oliveros. 2017. Automatic Fruit Count on Coffee Branches Using Computer Vision. Computers and Electronics in Agriculture 137: 9-22.
  26. Ridler, T. W., and S. Calvard. 1978. Picture Thresholding Using an Iterative Selection Method. IEEE Transactions on Systems, Man and Cybernetics 8 (8): 630-632.
  27. Rong, Z., Z. Li, and L. I. Dong-nan. 2015. Studyof Color Heritage Image Enhancement Algorithms Based on Histogram Equalization. Optik- International Journal for Light and Electron Optics 126 (24): 5665-5667.
  28. Sahoo, P., C. Wilkins, and J. Yeager. 1997. Threshold Selection Using Renyi’s Entropy. Pattern Recognition 30 (1): 71-84.
  29. Shanbhag, A. G. 1994. Utilization of Information Measure as a Means of Image Thresholding. CVGIP: Graphical Models and Image Processing 56 (5): 414-419.
  30. Sim, K. S., C. P. Tso, and Y. Y. Tan. 2007. Recursive Sub-Image Histogram Equalization Applied to Gray Scale Images. Pattern Recognition Letters 28: 1209-1221.
  31. Tanigaki, K., T. Fujiura, A. Akase, and J. Imagawa. 2008. Cherry-Harvesting Robot. Computers and Electronics in Agriculture 63: 65-72.
  32. Tsai, W. 1985. Moment-Preserving Thresholding: a New Approach. Computer Vision, Graphics, and Image Processing 29: 377-393.
  33. Wang, Y., Q. Chen, and B. Zhang. 1999. Image Enhancement Based On Equal Area Dualistic Sub Image Histogram Equalization Method. IEEE Transactions on Consumer Electronics 45 (1): 68-75.
  34. Yamamoto, K., W. Guo, Y. Yoshioka, and S. Ninomiya. 2014. On Plant Detection of Intact Tomato Fruits Using Image Analysis and Machine Learning Methods. Sensors 14: 12191-12206.
  35. Yen, J. C., F. J. Chang, and S. Chang. 1995. A New Criterion for Automatic Multilevel Thresholding. IEEE Transaction on Image Processing 4 (3): 370-378.