location:Home > 2023 Vol.6 Apr.N0.2 > Image texture enhancement method based on convolutional neural network

2023 Vol.6 Apr.N0.2

  • Title: Image texture enhancement method based on convolutional neural network
  • Name: Pingping ZENG
  • Company: College of Science and Technology, Nanchang University Jiujiang 332020, China
  • Abstract:

    The existing image texture enhancement methods have the problem of imperfect image structure and texture layer decomposition process, resulting in low definition. A novel image texture enhancement algorithm based on convolutional neural network is designed in this research. The local gray changes of the image are measured to obtain the texture mapping index of the image. The convolutional neural network decompresses the image structure and texture layer to remove the information does not conform to the given scale. By introducing the histogram matching constraint, the deblurring model is constructed to increase the gradient value of the image detail area and improve the image texture enhancement mode. Experimental results: The average sharpness of the image texture enhancement method in this paper and the other two image texture enhancement methods are 63.952, 53.340 and 54.952 respectively, indicating that the image texture enhancement method integrated with convolutional neural network has higher application value.


  • Keyword: convolutional neural network; image texture; feature fusion; the texture layer; image edge; brightness;
  • DOI: 10.12250/jpciams2023090404
  • Citation form: Pingping ZENG.Image texture enhancement method based on convolutional neural network [J]. Computer Informatization and Mechanical System,2023,Vol.6,pp.17-21
Reference:

[1] Niladri, Chakraborty, Priyambada, et al. Shock filter-based morphological scheme for texture enhancement[J]. Image Processing Iet, 2019.

[2] Yang L , Wang P ,  Zhang X , et al. Region-adaptive Texture Enhancement for Detailed Person Image Synthesis[J]. IEEE International Conference on Multimedia and Expo (ICME), 2020.

[3] Mj A ,  Hb A ,  Ms B . Echocardiography Image Enhancement using Texture-cartoon Separation[J]. Computers in Biology and Medicine, 2021.

[4] Wu H , Sun Z ,  Zhang Y , et al. Direction-aware Neural Style Transfer with Texture Enhancement[J]. Neurocomputing, 2019, 370(22):39-55.

[5] Chakraborty, Niladri, Subudhi, et al. Shock filter-based morphological scheme for texture enhancement[J]. IET Image Processing, 2019.

[6] Qiu J , Yue W U ,  Hui B , et al. Fractional differential algorithm based on wavelet transform applied on texture enhancement of liver tumor in CT image[J]. Journal of Computer Applications, 2019.

[7] Xia K J , Yin H S ,  Wang J Q . A novel improved deep convolutional neural network model for medical image fusion[J]. Cluster Computing, 2019.

[8] Gorban A N , Mirkes E M ,  Tukin I Y . How deep should be the depth of convolutional neural networks: a backyard dog case study[J]. Cognitive Computation, 2020, 12(1):388–397.

[9] George C P . Convolutional Neural Networks: Alternate Drivers' Visual Perception[J]. IEEE Potentials, 2020, 39(1):19-24.

[10] Hababeh I , Mahameed I ,  Abdelhadi A , et al. Utilizing Convolutional Neural Networks for Image Classification and Securing Mobility of People With Physical and Mental Disabilities in Cloud Systems[J]. IEEE Access, 2020, PP(99):1-1.

[11] Alamir M A . A novel acoustic scene classification model using the late fusion of convolutional neural networks and different ensemble classifiers[J]. Applied Acoustics, 2020, 172(3).

[12] Liu C ,  Pang M ,  Zhao R . Novel superpixel-based algorithm for segmenting lung images via convolutional neural network and random forest[J]. IET Image Processing, 2020, 14(3).

[13] Bilal E . Heart sounds classification using convolutional neural network with 1D-local binary pattern and 1D-local ternary pattern features[J]. Applied Acoustics, 2021, 180:108152.

[14] Unnikrishna N S , Sreelekha G . Video stabilization performance enhancement for low-texture videos[J]. Journal of Real-Time Image Processing, 2019.

[15] Kaur B A ,  Kumar S R ,  Deepti M . Ultrasound Image Despeckling and Enhancement using Modified Multiscale Anisotropic Diffusion Model in Non-Subsampled Shearlet Domain[J]. The Computer Journal, 2019.


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