Image compression algorithm of floral canopy based on mask hybrid coding for ROI

Sun Guoxiang, Wang Xiaochan, Ding Yongqian, Li Yuhua, Zhang Baohua, Li Yongbo, Zhang Yu


To achieve high-quality image compression of a floral canopy, a region of interest (ROI) mask of the wavelet domain was generated through the automatic identification of the canopy ROI and lifting the bit-plane of the ROI to obtain priority of coding for the ROI-set partitioning in hierarchical trees (ROI-SPIHT) coding. The embedded zerotree wavelet (EZW) coding was conducted for the background (BG) region of the image and a relatively more low-frequency wavelet coefficient was obtained using a relatively small amount of coding. Through the weighing factor r of the ROI coding amount, the proportion of the ROI and BG coding amount was dynamically adjusted to generate embedded, truncatable bit streams. Despite the location of truncation, the image information and ROI mask information required by the decoder can be guaranteed to achieve high-quality compression and reconstruction of the image ROI. The results indicated that under the same bit rate, the larger the r value is, the larger the peak-signal-to-noise ratio (PSNR) for the ROI reconstructed image and the smaller the PSNR for the BG reconstructed image. In the range of 0.07-1.09 bpp, the PSNR of the ROI reconstructed image was 42.65% higher on average than that of the BG reconstructed image, 43.95% higher on average than that of the composite image of the ROI and BG (ALL), and 16.84% higher on average than that of the standard SPIHT reconstructed image. Additionally, the mean square error of the quality evaluation index and similarity for the ROI reconstructed image were both better than those for the BG, ALL, and standard SPIHT reconstructed images. The texture distortion of the ALL image was smaller than that of the SPIHT reconstructed image, indicating that the image compression algorithm based on the mask hybrid coding for ROI (ROI-MHC) is capable of improving the reconstruction quality of an ROI image. When the weighing factor r is a fixed value, as the proportion of ROI (a) increases, the quality of ROI image reconstruction gradually decreases. Therefore, upon the application of the ROI-MHC image compression algorithm, high-quality reconstruction of the ROI image can be achieved through dynamically configuring r according to a. Under the same bit rate, the quality of the ROI-MHC image compression is higher than that of current compression algorithms of same classes and offers promising application opportunities.
Keywords: floral canopy, ROI, mask hybrid coding, image compression, algorithm, wavelet transform
DOI: 10.25165/j.ijabe.20171005.2772

Citation: Sun G X, Wang X C, Ding Y Q, Li Y H, Zhang B H, Li Y B, et al. Image compression algorithm of floral canopy based on mask hybrid coding for ROI. Int J Agric & Biol Eng, 2017; 10(5): 166–176.


flora, ROI, mask hybrid coding, image compression, wavelet transform


Sun G X, Li Y B, Zhang Y, Wang X C, Chen M, Li X, et al. Nondestructive measurement method for greenhouse cucumber parameters based on machine vision. Engineering in Agriculture, Environment and Food, 2016; 9(1): 70–78.

Xu Y, Xu Z Y, Zhang Q H, Zuo H R. A mask embedded spiht algorithm for arbitrary shape ROI coding. Opto-Electronic Engineering, 2009; 36(9): 118–124.

Xu Y, Xu Z Y, Zhang Q H. Arbitrary shaped ROI image coding using Run-length coding and generalized Exp-Golomb coding. Opt. Precision Eng., 2011; 19(1): 175–181.

Wang Y Y, Huang D Q. Compression for UAV reconnaissance images. Opt. Precision Eng.,, 2014; 22(5): 1363–1370.

Zuo Z Y, Lan X, Deng L H, Yao S K, Wang X P. An improved medical image compression technique with lossless region of interest. Optik, 2015; 126: 2825–2831.

Perez-Jimenez A, Lopez F, Benlloch J V, Christensen S. Color and shape analysis techniques for weed detection in cereal fields. Computer and Electronics in Agriculture, 2000; 25(3): 197–212.

Hunt E R, Cavigelli M, Daughtry C T, Mcmurtrey J, Walthall S L. Evaluation of digital photography from model aircraft for remote sensing of crop biomass. Precision Agriculture, 2005; 6(4): 359–378.

Meyer G E, João C N. Verification of color vegetation indices for automated crop imaging applications. Computer and Electronics in Agriculture, 2008; 63(2): 282–293.

Meyer G E, João C N, David D J, Timothy W H. Intensified fuzzy clusters for classifying plant, soil, and residue regions of interest from color images. Computer and Electronics in Agriculture, 2004; 42(3): 161–180.

Sun G X, Li Y B, Wang X C, Hu G Y, Wang X, Zhang Y. Image segmentation algorithm for greenhouse cucumber canopy under various natural lighting conditions. Int J Agric & Biol Eng, 2016; 9(3): 130–138.

Sun G X, Wang X C, Yan T T, Li X, Chen M, Shi Y Y. Inversion method of flora growth parameters based on machine vision. Transactions of the CSAE, 2014; 30(20): 187–195. (in Chinese)

Hao H W, Jiang R R, Shi Y S. An image compression algorithm for circle shaped ROI. Acta Automatica Sinica, 2008; 34(5): 601–604.

Kumarayapa A, Zhang Y. More efficient ground truth ROI image coding technique: implementation and wavelet based application analysis. Journal of Zhejiang University: Science A (S1673-565X), 2007; 8(6): 835–840.

Taubman D S, Marcellin M W. JPEG 2000 image compression fundamentals, standards and practice. Beijing: Publishing House of Electronics Industry, 2004.

Zhang L B, Yu X C. Multiple region of interest image coding based on classification bitplane shift. Opto-Electronic Engineering, 2007; 34(2): 100–104.

Charilaos C, Joel A, Mathias L. Efficient methods for encoding regions of interest in the upcoming JPEG 2000 still image coding standard. IEEE Signal Processing Letters, 2000; 7(9): 247–249.

Raphael G, Diego S C, Touradj E. New approach to JPEG 2000 compliant region of interest coding. SPIE, 2001; 4172: 267–275.

Rema N R, Binu A O, Mythili P. Image compression using SPIHT with modified spatial orientation tress. Procedia Computer Science, 2015; 46: 1732–1738.

Jcrome M S. Embedded image coding using zerotrees of wavelet coefficients. IEEE Tran on Signal Processing. 1993.

Zhai L, Tang X M, Li L, Hong Z G. A new quality assessment index for compressed RS image. Geomatics and Information Science of Wuhan University, 2007; 32(10): 872–875.

Full Text: PDF

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.