location:Home > 2020 Vol.3 Jun. No.3 > Super resolution reconstruction of medical instrument image based on deep learning

2020 Vol.3 Jun. No.3

  • Title: Super resolution reconstruction of medical instrument image based on deep learning
  • Name: Shaohua Nie
  • Company: College of Teacher Education,Pingdingshan University
  • Abstract:

    Current image reconstruction has some problems, such as low image segmentation and denoising precision, slow convergence speed, and poor image integrity after reconstruction. In this regard, this study proposed a super-resolution reconstruction of crop disease images based on deep learning. The improved neighborhood averaging method is used to denoise the low frequency subband image, and the enhanced wavelet coefficients are replaced by the wavelet inverse transform to realize the high frequency subband image denoising. The image enhancement results are introduced, and the image initial segmentation area is obtained by using the color roughness concept and the incremental region growth method. According to the fusion of the distance between the image color and the spatial information, the classification and merging of the initial segmentation area are realized. When the stop condition is satisfied, the best result is output. The small feature extraction of image segmentation results is carried out, and the feature vectors are transformed from low resolution space to high resolution space by nonlinear mapping. After the mapping, the feature is aggregated and reconstructed to form the super resolution image. Feature extraction, nonlinear mapping and image reconstruction are fused into a deep convolution neural network, and the final reconstruction results are obtained. The experiment showed that the method improves the image segmentation and denoising precision, and the integrity coefficient of the image reconstruction is high and the reliability is strong.

  • Keyword: Deep Learning; Crops; Disease Images; Super-Resolution; Reconstruction;
  • DOI: 10.12250/jpciams2020030109
  • Citation form: Shaohua Nie.Super resolution reconstruction of medical instrument image based on deep learning[J]. Computer Informatization and Mechanical System, 2020, vol. 3, pp. 102-113.
Reference:

[1]Burgess A J, Retkute R, Pound M P, Mayes S & Murchie E H (2017). Image-based 3D canopy reconstruction to determine potential productivity in complex multi-species crop systems. Annals of Botany 119:517-532.
[2]Wei D (2017). Image super-resolution reconstruction using the high-order derivative interpolation associated with fractional filter functions. Iet Signal Processing 10:1052-1061.
[3]Mao X D & Shi Z (2016). Method about Reconstruction of SEM Image Based on Gradient. Computer Science 43:297-301.
[4]Song J H (2016). Image Reconstruction of SRM Cross-Section Based on Compressed Sensing. Computer Simulation 33:132-137.
[5]Yu J P, Chen D Y & Wang L L (2016). A Novel Image Reconstruction Algorithm Based on Improved Taboo Search for Electrical Capacitance Tomography. Journal of Harbin University of Science and Technology 21:51-56.
[6]Li C (2016). Super Resolution Image Reconstruction Based on Support Vector Machine. Laser Journal 37:138-141.
[7]Guo B H & Cen Z S (2016). Super Resolution Image Reconstruction Based on Wavelet Denoising and Neural Network. Laser Journal 37:61-64.
[8]Giuliani M, Vissa A, Driouchi A & Yip C M (2016). Effect of Data Pre-processing on Super-Resolution reconstruction and Pattern Recognition. Biophysical Journal 110:331a-331a.
[9]Lal A, Shan C & Xi P (2016). Structured Illumination Microscopy Image Reconstruction Algorithm. IEEE Journal of Selected Topics in Quantum Electronics 22:50-63.
[10]Olafsson V T, Noll D C & Fessler J A (2017). Fast Spatial Resolution Analysis of Quadratic Penalized Least-Squares Image Reconstruction with Separate Real and Imaginary Roughness Penalty: Application to fMRI. IEEE Transactions on Medical Imaging PP:1-1.
[11]Katsevich A & Katsevich A (2017). A Local Approach to Resolution Analysis of Image Reconstruction in Tomography. Siam Journal on Applied Mathematics 77:1706-1732.
[12]Pagnanelli R & Borgesneto S (2016). Technical aspects of resolution recovery reconstruction. Journal of Nuclear Cardiology 23:149-152.
[13]Wu G H, Zhang H D, Li X K & Dai J Y (2016). FR-CoSaMP image reconstruction algorithm based on improved measurement. Computer Engineering and Design 37:1555-1559.
[14]Zhou L Y, Su C X & Cao Y F (2016). Image super-resolution via sparse representation. Computer Engineering and Design 37:3290-3294.
[15]Salehi B, Daneshfar B & Davidson A M (2017). Accurate crop-type classification using multi-temporal optical and multi-polarization SAR data in an object-based image analysis framework. International Journal of Remote Sensing 38:4130-4155.

Tsuruta Institute of Medical Information Technology
Address:[502,5-47-6], Tsuyama, Tsukuba, Saitama, Japan TEL:008148-28809 fax:008148-28808 Japan,Email:jpciams@hotmail.com,2019-09-16