Paint Loss Detection and Segmentation Based on YOLO: An Improved Model for Ancient Murals and Color Paintings
Paint loss is one of the major forms of deterioration in ancient murals and color paintings, and its detection and segmentation are critical for subsequent restoration efforts. However, existing methods still suffer from issues such as incomplete segmentation, patch noise, and missed detections duri...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Heritage |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2571-9408/8/4/136 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849714254015365120 |
|---|---|
| author | Yunsheng Chen Aiwu Zhang Jiancong Shi Feng Gao Juwen Guo Ruizhe Wang |
| author_facet | Yunsheng Chen Aiwu Zhang Jiancong Shi Feng Gao Juwen Guo Ruizhe Wang |
| author_sort | Yunsheng Chen |
| collection | DOAJ |
| description | Paint loss is one of the major forms of deterioration in ancient murals and color paintings, and its detection and segmentation are critical for subsequent restoration efforts. However, existing methods still suffer from issues such as incomplete segmentation, patch noise, and missed detections during paint loss extraction, limiting the automation of paint loss detection and restoration. To tackle these challenges, this paper proposes PLDS-YOLO, an improved model based on YOLOv8s-seg, specifically designed for the detection and segmentation of paint loss in ancient murals and color paintings. First, the PA-FPN network is optimized by integrating residual connections to enhance the fusion of shallow high-resolution features with deep semantic features, thereby improving the accuracy of edge extraction in deteriorated areas. Second, a dual-backbone network combining CSPDarkNet and ShuffleNet V2 is introduced to improve multi-scale feature extraction and enhance the discrimination of deteriorated areas. Third, SPD-Conv replaces traditional pooling layers, utilizing space-to-depth transformation to improve the model’s ability to perceive deteriorated areas of varying sizes. Experimental results on a self-constructed dataset demonstrate that PLDS-YOLO achieves a segmentation accuracy of 86.2%, outperforming existing methods in segmentation completeness, multi-scale deterioration detection, and small target recognition. Moreover, the model maintains a favorable balance between computational complexity and inference speed, providing reliable technical support for intelligent paint loss monitoring and digital restoration. |
| format | Article |
| id | doaj-art-8ed87e81f29e47e89de153a1085de6df |
| institution | DOAJ |
| issn | 2571-9408 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Heritage |
| spelling | doaj-art-8ed87e81f29e47e89de153a1085de6df2025-08-20T03:13:45ZengMDPI AGHeritage2571-94082025-04-018413610.3390/heritage8040136Paint Loss Detection and Segmentation Based on YOLO: An Improved Model for Ancient Murals and Color PaintingsYunsheng Chen0Aiwu Zhang1Jiancong Shi2Feng Gao3Juwen Guo4Ruizhe Wang5Key Laboratory of 3D Information Acquisition and Application, Ministry of Education, Capital Normal University, Beijing 100048, ChinaKey Laboratory of 3D Information Acquisition and Application, Ministry of Education, Capital Normal University, Beijing 100048, ChinaKey Laboratory of 3D Information Acquisition and Application, Ministry of Education, Capital Normal University, Beijing 100048, ChinaChina Academy of Cultural Heritage, Beijing 100029, ChinaChina Academy of Cultural Heritage, Beijing 100029, ChinaKey Laboratory of 3D Information Acquisition and Application, Ministry of Education, Capital Normal University, Beijing 100048, ChinaPaint loss is one of the major forms of deterioration in ancient murals and color paintings, and its detection and segmentation are critical for subsequent restoration efforts. However, existing methods still suffer from issues such as incomplete segmentation, patch noise, and missed detections during paint loss extraction, limiting the automation of paint loss detection and restoration. To tackle these challenges, this paper proposes PLDS-YOLO, an improved model based on YOLOv8s-seg, specifically designed for the detection and segmentation of paint loss in ancient murals and color paintings. First, the PA-FPN network is optimized by integrating residual connections to enhance the fusion of shallow high-resolution features with deep semantic features, thereby improving the accuracy of edge extraction in deteriorated areas. Second, a dual-backbone network combining CSPDarkNet and ShuffleNet V2 is introduced to improve multi-scale feature extraction and enhance the discrimination of deteriorated areas. Third, SPD-Conv replaces traditional pooling layers, utilizing space-to-depth transformation to improve the model’s ability to perceive deteriorated areas of varying sizes. Experimental results on a self-constructed dataset demonstrate that PLDS-YOLO achieves a segmentation accuracy of 86.2%, outperforming existing methods in segmentation completeness, multi-scale deterioration detection, and small target recognition. Moreover, the model maintains a favorable balance between computational complexity and inference speed, providing reliable technical support for intelligent paint loss monitoring and digital restoration.https://www.mdpi.com/2571-9408/8/4/136muralcolor paintingpaint lossdetection and segmentationdigital preservation |
| spellingShingle | Yunsheng Chen Aiwu Zhang Jiancong Shi Feng Gao Juwen Guo Ruizhe Wang Paint Loss Detection and Segmentation Based on YOLO: An Improved Model for Ancient Murals and Color Paintings Heritage mural color painting paint loss detection and segmentation digital preservation |
| title | Paint Loss Detection and Segmentation Based on YOLO: An Improved Model for Ancient Murals and Color Paintings |
| title_full | Paint Loss Detection and Segmentation Based on YOLO: An Improved Model for Ancient Murals and Color Paintings |
| title_fullStr | Paint Loss Detection and Segmentation Based on YOLO: An Improved Model for Ancient Murals and Color Paintings |
| title_full_unstemmed | Paint Loss Detection and Segmentation Based on YOLO: An Improved Model for Ancient Murals and Color Paintings |
| title_short | Paint Loss Detection and Segmentation Based on YOLO: An Improved Model for Ancient Murals and Color Paintings |
| title_sort | paint loss detection and segmentation based on yolo an improved model for ancient murals and color paintings |
| topic | mural color painting paint loss detection and segmentation digital preservation |
| url | https://www.mdpi.com/2571-9408/8/4/136 |
| work_keys_str_mv | AT yunshengchen paintlossdetectionandsegmentationbasedonyoloanimprovedmodelforancientmuralsandcolorpaintings AT aiwuzhang paintlossdetectionandsegmentationbasedonyoloanimprovedmodelforancientmuralsandcolorpaintings AT jiancongshi paintlossdetectionandsegmentationbasedonyoloanimprovedmodelforancientmuralsandcolorpaintings AT fenggao paintlossdetectionandsegmentationbasedonyoloanimprovedmodelforancientmuralsandcolorpaintings AT juwenguo paintlossdetectionandsegmentationbasedonyoloanimprovedmodelforancientmuralsandcolorpaintings AT ruizhewang paintlossdetectionandsegmentationbasedonyoloanimprovedmodelforancientmuralsandcolorpaintings |