Abstract
Traditional methods for ancient mural segmentation have drawbacks, including fuzzy target boundaries and low efficiency. Targeting these problems, this study proposes a pyramid scene parsing MobileNetV2 network (PSP-M) by fusing a deep separable convolution-based lightweight neural network with a multiscale image segmentation model. In this model, deep separable convolution-fused MobileNetV2, as the backbone network, is embedded in the image segmentation model, PSPNet. The pyramid scene parsing structure, particularly owned by the two models, is used to process the background features of images, which aims to reduce feature loss and to improve the efficiency of image feature extraction. In the meantime, atrous convolution is utilized to expand the perceptive field, aiming to ensure the integrity of image semantic information without changing the number of parameters. Compared with traditional image segmentation models, PSP-M increases the average training accuracy by 2%, increases the peak signal-to-noise ratio by 1–2 dB and improves the structural similarity index by 0.1–0.2.
Highlights
With the continuous development of computer software and hardware, as well as the gradual deepening of social informatization, cultural relic protection institutions have introduced advanced digital technology to iteratively update traditional technology, while improving the work efficiency of relevant workers, reducing workloads and enhancing the values of traditional culture
According to the complex composition of ancient mural images, as we leverage the powerful learning capacity of the deep learning network, we propose a new model that can be applied in image segmentation for ancient mural images, the pyramid scene parsing MobileNetV2 Network (PSP-M), by fusing a deep separable convolution network with the spatial pyramid pooling modules of the scene parsing model, PSPNet [16]
Comparison of the time for segmentation To validate the satisfactory performance of the deep separable network in segmenting the neighborhood regions of the ancient mural image, we assess the proposed model in terms of segmentation time, accuracy and segmentation effect
Summary
With the continuous development of computer software and hardware, as well as the gradual deepening of social informatization, cultural relic protection institutions have introduced advanced digital technology to iteratively update traditional technology, while improving the work efficiency of relevant workers, reducing workloads and enhancing the values of traditional culture. As a traditional cultural carrier, ancient murals play an important role in Chinese culture, and their contents reflect the charm of traditional Chinese culture from multiple aspects, such as the geographical environment and local traditions and customs. The first step for mural image digital protection is to understand the image. Influenced by traditional culture, ancient Chinese murals are characterized by bright colors and rich content. Analyzing the image is one of the most difficult problems in Chinese mural image protection. Image segmentation is an important method for image understanding. This technique can divide an image into several noninteractive regions according to grayscale, color and texture. As different regions have different exhibitions, this technique calibrates them based on the discontinuity of the gray levels at their boundaries to achieve image analysis.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
