Application of Information Technology in Woodcut Prints: Abstract
Application of Information Technology in Woodcut Prints: Abstract
in Woodcut Prints
Wei Huang(B)
Fujian Putian Xiamen Academy of Arts and Design, Fuzhou University, Fuzhou 361000, China
[email protected]
1 Introduction
Woodcut print is the oldest type of print, which has the characteristics of image trans-
mission from the beginning and hides its artistic value. With the rapid development of
image technology, the function of woodcut prints as communication has been weakened.
By 180, the original print movement jointly carried out by France and Britain gradually
built woodcuts with independent artistic significance. By the early 20th century, German
expressionist woodcuts had certain characteristics. China’s woodcut prints developed in
the 1920s and became one of the most important artistic achievements in the 20th cen-
tury. With the update and popularization of information technology, it provides a lot of
convenience for the production of woodcut prints. Therefore, how to apply information
technology to woodcut prints has become a concern of many producers.
editing dialog box, in which the list on the right side Load Texture selects the processed
file, and sets the Scaling value to 100%. After confirmation, you can get the final effect
image depicted by the woodblock.
The style image style of woodcut prints is characterized to determine the correlation
among all channel feature maps in the same convolution layer of VGG19 model. Gram
matrix is used to calculate the correlation of each feature map of all convolution layers in
the network as the style representation, Gram matrix Gl ∈ Nl * Nl , where Nl represents
the total amount of convolution kernels in the 1st layer, and Gijl represents the product of
the ith convolution kernel feature map and the jth convolution kernel feature map after
the image is subjected to the 1st vectorization. The specific formula is as follows:
Gijl = Fikl Fjk
l
i,j
696 W. Huang
Content Style
image image
the graph
The initialization image g of the generated graph is defined, and the woodcut style
image is set as a. G and A respectively represent the style representation of the generated
image and woodcut style image in the ith layer of the network [6]. The mean square
error is used to determine the style difference between the living layer picture and the
woodcut print style image. In this way, you can define the loss function of the ith layer
woodcut style, as follows:
1
El = (Gijl − Alij )2
4Nl2 Ml2 i,j
Application of Information Technology in Woodcut Prints 697
Wl indicates that all convolution layers of the network activate the corresponding
weight factors, and the derivative formula of this formula function with respect to the
response value of the I-th layer number is as follows:
⎧
∂Lc ⎨ 1 F l T G l − Al , if F l > 0
2 2 ij
= Nl Ml
∂Fijl ⎩ 0, if F l < 0ij
In the above formula, Lc represents the loss function between the content image and
the generated image, and Ls represents the loss function between the woodcut image
and the generated image. α and β respectively represent the content loss function and the
style of woodcut prints, and the weight of the loss function can effectively control the
stylization level of woodcut prints by using α and β. Through the style transformation, the
creator can directly transform the image materials into woodcut prints, and directly make
the prints [7]. In this way, the time required for image design is greatly reduced, and the
final effect of the pictures is significantly improved, which is of positive significance for
promoting the development of woodcut prints. The effect of regional style transformation
of woodcut prints is shown in Fig. 4.
From the point of view of image space control, there will be some problems such
as inconspicuous woodcut notch texture and chaotic distribution in the living layer map
with neural style conversion algorithms such as Gatys, which will destroy the semantic
information to some extent. The reason is that Gram matrix can only refine the global
average characteristics of the image, and lacks the restriction on the spatial information
of objects. Therefore, this paper uses the mask image as a guide and adds a space guide
channel to solve the above problems. Firstly, the spatial guide feature map is generated
to complete the image segmentation and transformation. Combining the network mask
image to form a space guide channel Tlr on all convolution layer channels, where Tlr
represents the R space guide channel on the L layer in the network, and multiplying
Tlr and the vectorized feature map by corresponding elements to obtain a space guide
feature map:
where Flr (x) represents the ith column vector. Save the spatial guidance feature map
as a two-dimensional matrix Flr to obtain the spatial guidance feature representation,
and define the spatial guidance content loss function on the spatial guidance feature
representation as follows:
1 l
Lcss(p, g, l) = (Fr (g) − Grl (a))2ij
2
r=1 i,j
Similarly, in the aspect of space guiding characteristics, the guiding Gram matrix is
defined, and all guiding matrices are used as spaces to guide the optimization goal of
the channel area. The style loss of each floor is as follows:
1
Els = 2 2
(Grl (g) − Grl (a))2ij
4Nl Ml r=1 i,j
By using the control of the space guide channel, the image optimization is carried
out in the corresponding space guide channel area, ensuring that the pattern is only
transmitted in this area, so as to avoid the chaotic distribution of the notch texture
characteristics of the image [8].
5 Conclusion
As an art form, woodcut prints are sensitive and avant-garde. Creators should accept
new ideas as soon as possible, and reasonably introduce the advanced technology of
information technology, so that woodcut printmaking, a traditional art form, can be inte-
grated with advanced information technology. Although information technology cannot
completely replace woodcut prints, it does provide help and new development courses
for the design of woodcut prints, and promotes the production efficiency and quality of
woodcut prints. The organic integration of woodcut prints and information technology
has also attracted the attention of many scholars.
References
1. Lin Y (2020) Analysis of the application of printmaking in animation design-taking black and
white woodcut as an example. J Pu’er Univ 36(6):83–84
2. Zhou L (2020) The design of monochrome woodcut style printing pattern-from Dior women’s
style. Screen Print 9:5–14
3. Chen Y (2021) The integration and innovation of woodcut art in visual design-taking “Graphic
Creativity” and “Classroom Revolution” as an example. Brand Res 23:49–50,158
4. Tian M (2019) Exploration of higher vocational woodcut printmaking teaching based on
information technology. Sci Consultation 24:88
5. Cao X (2018) Comparison between Ukiyo-e prints and Ming-Qing woodblock New Year
pictures in terms of prevalence and development context. China Nat Expo 18:179–180
6. Cui Z (2018) The application of digital technology in woodcut prints. Digit Technol Appl
36(9):200–201
7. Qiu T (2020) Cultivation of students’ quality and ability in woodcut and printmaking teaching.
Digit Des (Part 2), 9(12):176
8. Ye Z (2018) Research on the integration and innovation of digital printmaking and traditional
printmaking. China Nat Expo 18:177–178
Application of Information Technology in Woodcut Prints 699
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-
NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/),
which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any
medium or format, as long as you give appropriate credit to the original author(s) and the source,
provide a link to the Creative Commons license and indicate if changes were made.
The images or other third party material in this chapter are included in the chapter’s Creative
Commons license, unless indicated otherwise in a credit line to the material. If material is not
included in the chapter’s Creative Commons license and your intended use is not permitted by
statutory regulation or exceeds the permitted use, you will need to obtain permission directly from
the copyright holder.