Improved Hybrid Preprocessing Technique for Effective Segmentation of Wheat Canopies in Chlorophyll Fluorescence Images




Wheat Canopy, Chlorophyll Fluorescence, Denoising, Enhancement, Segmentation


Precision agriculture heavily relies on accurately segmenting wheat canopies from chlorophyll fluorescence (CHF) images. However, these images often face challenges due to inherent noise and illumination variations, primarily induced by the thermal activity of photons emitting a fluorescence effect. The unique nature of fluorescence introduces variations in illumination, especially during the crop's dark adaptation before experimentation. This adaptation aims to capture the full fluorescence effect, starting from minimum fluorescence and progressing to maximum fluorescence. In the initial stages of fluorescence, images tend to appear darker compared to those progressing towards maximum fluorescence. This variability necessitates the development of a sophisticated hybrid approach to eliminate noise and enhance contrast collaboratively, maximizing the benefits derived from CHF images. This paper introduces a novel hybrid preprocessing approach designed to address these challenges. The proposed method integrates five denoising techniques, namely Discrete Cosine Transform, Block Matching-3D, Low-Rank Matrix Approximation, Wiener Filtering, and Median Filtering, to mitigate the impact of noise in CHF images. Simultaneously, two enhancement techniques, Adaptive Histogram Specification and Gamma Correction, are employed to accentuate critical features, compensating for inherent variations in illumination during the fluorescence process. The hybrid preprocessing technique was proposed after analysing different combinations of denoising and enhancement techniques. Through qualitative and quantitative analysis of the results, it was observed that Block Matching-3D denoising with Gamma Correction produced the best output, with an Average PSNR of 0.54 and Average MSE of 0.07. This cascaded approach not only emphasizes noise reduction but also prioritizes the enhancement of crucial information within CHF images. By synergistically combining denoising and enhancement methods, the proposed approach optimizes the overall quality of the images, laying a foundation for improved wheat canopy segmentation. This research contributes a comprehensive and innovative solution to the challenges associated with CHF images in precision agriculture. The proposed hybrid approach holds promise for advancing the accuracy and reliability of wheat canopy segmentation, thereby enhancing the efficacy of precision agricultural practices.



Download data is not yet available.


H. M. T et al., FLIP: FLuorescence Imaging Pipeline for field-based chlorophyll fluorescence images, vol. 14. 2021. doi: 10.1016/J.SOFTX.2021.100685.

Z. Liya, Y. Yingchun, S. Yufei, W. Bin, and W. Yansong, Research on Estimation of Wheat Chlorophyll Using Image Processing Technology, vol. 128. 2017. doi: 10.1051/MATECCONF/201712801007.

H. Abbas and E. Yahya, Green-gradient based canopy segmentation: A multipurpose image mining technique with potential use in crop phenotyping and canopy studies. 2019.

C. Kapil, K. Narender, and S. V. K, Image Denoising Based on Diffusion Wavlet, MLP-LMMSE Algorithm. 2014. doi: 10.3850/978-981-09-5247-1_020.

K. B. K. Shreyamsha, Image denoising based on non-local means filter and its method noise thresholding, vol. 7. 2012. doi: 10.1007/S11760-012-0389-Y.

S. M. Elkheir, Z. Xuming, and D. Mingyue, Kernel PCA Based Non-Local Means Method for Speckle Reduction in Medical Ultrasound Images, vol. 09. 2022. doi: 10.4236/OALIB.1108618.

S. Shivani, S. Harjeet, and M. Muthukumaran, Image quality enhancement for Wheat rust diseased images using Histogram equalization technique. 2021. doi: 10.1109/ICCMC51019.2021.9418023.

Ankita Gupta, Lakhwinder Kaur, and Gurmeet Kaur. 2022. Impact of Image Pre-processing Operations on Wheat Canopy Segmentation. In Proceedings of the 2022 Fourteenth International Conference on Contemporary Computing (IC3-2022). Association for Computing Machinery, New York, NY, USA, 396–403.

P. Abanikanta and A. Aditya, Bi-Sigmoidal Function Based Adaptive Gamma Correction for Dark Image Enhancement. 2023. doi: 10.1109/CCPIS59145.2023.10291302.

F. Xueyang, W. Jiye, Z. Delu, H. Yue, and D. Xinghao, Remote Sensing Image Enhancement Using Regularized-Histogram Equalization and DCT, vol. 12. 2015. doi: 10.1109/LGRS.2015.2473164.

B. Filippo, G. Giacomo, D. Anthony, and P. Martina, Selection of chlorophyll fluorescence parameters as indicators of photosynthetic efficiency in large scale plant ecological studies, vol. 108. 2020. doi: 10.1016/J.ECOLIND.2019.105686.

E. Irsa et al., Detection of combined frost and drought stress in wheat using hyperspectral and chlorophyll fluorescence imaging, vol. 30. 2023. doi: 10.1016/J.ETI.2023.103051.

S. J, N. M, . V, and . M, Chlorophyll fluorescence parameters to assess utilization of excitation energy in photosystem II independently of changes in leaf absorption., vol. 197. 2019. doi: 10.1016/J.JPHOTOBIOL.2019.111535.

S. Abebe, A. Solomon, and S. K. V., Mapping the spatial and temporal variation of agricultural and meteorological drought using geospatial techniques, Ethiopia, vol. 10. 2021. doi: 10.1186/S40068-020-00204-2.

H. M. Al-Amin, P. Biswajeet, and A. Naser, Assessing drought vulnerability using geospatial techniques in northwestern part of Bangladesh., vol. 705. 2019. doi: 10.1016/J.SCITOTENV.2019.135957.

Z. Zheng, M. Yaqoob, N. G. Diverres, and G. E. M.T, Assessment for crop water stress with infrared thermal imagery in precision agriculture: A review and future prospects for deep learning applications, vol. 182. 2021. doi: 10.1016/J.COMPAG.2021.106019.

G. Ankita, K. Lakhwinder, and K. Gurmeet, Drought stress detection technique for wheat crop using machine learning, vol. 9. 2023. doi: 10.7717/PEERJ-CS.1268.

A. G. L. Kaur and undefined undefined, Pre-processing of drought/water stress detection chlorophyll fluorescence wheat images for efficient segmentation. 2022. doi: 10.17632/4y8s925fkm.5.

P. R. Suryadi, T. undefined, and S. Saib, Analysis and Improvement of JPEG Compression Performance with Discrete Cosine Transform and Convolution Gaussian Filtering. 2023. doi: 10.1109/ICOCICS58778.2023.10277096.

K. R. A., L. V. V., V. Benoit, and C. Kacem, Filtering of dual-polarization radar images based on discrete cosine transform. 2014. doi: 10.1109/IRS.2014.6869301.

L. De-Xing and Z. Zhao-Qiong, Ultrasound-guided peripheral trunk block technique: A new approach gradually stepping onto the stage of clinical anesthesia., vol. 7. 2021. doi: 10.1002/J.2769-2795.2021.TB00085.X.

S. Xiaolei, F. Sergey, and Y. Lexing, Lowrank finite-differences and lowrank Fourier finite-differences for seismic wave extrapolation in the acoustic approximation, vol. 193. 2013. doi: 10.1093/GJI/GGT017.

I. R. Rizal, W. Y. Eko, and M. M. Victorina, Assessment on Image Quality Changes as a Result of Implementing Median Filtering, Wiener Filtering, Histogram Equalization, and Hybrid Methods on Noisy Images. 2020. doi: 10.1109/ICITACEE50144.2020.9239153.

I. Kohei, O. Naoki, and H. Kenji, Local Contrast-Based Pixel Ordering for Exact Histogram Specification., vol. 8. 2022. doi: 10.3390/JIMAGING8090247.

N. P. G and D. M. S, Effective valorization of blackstrap molasses to poly gamma glutamic acid (-PGA) using L-glutamic acid independent feeding approach and its significance as drought mitigator in wheat plant, vol. 202. 2023. doi: 10.1016/J.INDCROP.2023.116985.

K. M. K. H, R. G. Lloyds, and S. Somnath, An Introduction to Wavelet-Based Image Processing and Its Applications. 2018. doi: 10.4018/978-1-5225-5204-8.CH005.

J. Jiale et al., Analysis and Evaluation of the Image Preprocessing Process of a Six-Band Multispectral Camera Mounted on an Unmanned Aerial Vehicle for Winter Wheat Monitoring., vol. 19. 2019. doi: 10.3390/S19030747.

D. R. and S. N., An Analysis Study of Various Image Preprocessing Filtering Techniques based on PSNR for Leaf Images. 2022. doi: 10.1109/ICACTA54488.2022.9753444.

Singh, P., and S. Singla. "Estimation of Land Surface Temperature of Srinagar City, India Using Landsat 8 Data. Sustainability, Agri." Food and Environmental Research 12.1 (2023).

Gupta, A., Kaur, L., & Kaur, G. (2023). Drought stress detection technique for wheat crop using machine learning. PeerJ. Computer science, 9, e1268.




How to Cite

A. Gupta, “Improved Hybrid Preprocessing Technique for Effective Segmentation of Wheat Canopies in Chlorophyll Fluorescence Images”, EAI Endorsed Trans AI Robotics, vol. 3, Jan. 2024.