Text Removal for Trademark Images Based on Self-Prompting Mechanisms and Multi-Scale Texture Aggregation
With the rapid development of electronic business, there has been a surge in incidents of trademark infringement, making it imperative to improve the accuracy of trademark retrieval systems as a key measure to combat such illegal behaviors. Evidently, the textual information encompassed within trade...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/3/1553 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850068066729197568 |
|---|---|
| author | Wenchao Zhou Xiuhui Wang Boxiu Zhou Longwen Li |
| author_facet | Wenchao Zhou Xiuhui Wang Boxiu Zhou Longwen Li |
| author_sort | Wenchao Zhou |
| collection | DOAJ |
| description | With the rapid development of electronic business, there has been a surge in incidents of trademark infringement, making it imperative to improve the accuracy of trademark retrieval systems as a key measure to combat such illegal behaviors. Evidently, the textual information encompassed within trademarks substantially influences the precision of search results. Considering the diversity of trademark text and the complexity of its design elements, accurately locating and analyzing this text poses a considerable challenge. Against this background, this research has developed an original self-prompting text removal model, denoted as “Self-prompting Trademark Text Removal Based on Multi-scale Texture Aggregation” (abbreviated as MTF-STTR). This model astutely applies a text detection network to automatically generate the required input cues for the Segment Anything Model (SAM) while incorporating the technological benefits of diffusion models to attain a finer level of trademark text removal. To further elevate the performance of the model, we introduce two innovative architectures to the text detection network: the Integrated Differentiating Feature Pyramid (IDFP) and the Texture Fusion Module (TFM). These mechanisms are capable of efficiently extracting multilevel features and multiscale textual information, which enhances the model’s stability and adaptability in complex scenarios. The experimental validation has demonstrated that the trademark text erasure model designed in this paper achieves a peak signal-to-noise ratio as high as 40.1 dB on the SCUT-Syn dataset, which is an average improvement of 11.3 dB compared with other text erasure models. Furthermore, the text detection network component of the designed model attains an accuracy of up to 89.9% on the CTW1500 dataset, representing an average enhancement of 10 percentage points over other text detection networks. |
| format | Article |
| id | doaj-art-5d113e4141cd469e8212e58a4b4781f0 |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-5d113e4141cd469e8212e58a4b4781f02025-08-20T02:48:09ZengMDPI AGApplied Sciences2076-34172025-02-01153155310.3390/app15031553Text Removal for Trademark Images Based on Self-Prompting Mechanisms and Multi-Scale Texture AggregationWenchao Zhou0Xiuhui Wang1Boxiu Zhou2Longwen Li3Computer Science and Technology Department, China Jiliang University, Hangzhou 310018, ChinaComputer Science and Technology Department, China Jiliang University, Hangzhou 310018, ChinaComputer Science and Technology Department, China Jiliang University, Hangzhou 310018, ChinaComputer Science and Technology Department, China Jiliang University, Hangzhou 310018, ChinaWith the rapid development of electronic business, there has been a surge in incidents of trademark infringement, making it imperative to improve the accuracy of trademark retrieval systems as a key measure to combat such illegal behaviors. Evidently, the textual information encompassed within trademarks substantially influences the precision of search results. Considering the diversity of trademark text and the complexity of its design elements, accurately locating and analyzing this text poses a considerable challenge. Against this background, this research has developed an original self-prompting text removal model, denoted as “Self-prompting Trademark Text Removal Based on Multi-scale Texture Aggregation” (abbreviated as MTF-STTR). This model astutely applies a text detection network to automatically generate the required input cues for the Segment Anything Model (SAM) while incorporating the technological benefits of diffusion models to attain a finer level of trademark text removal. To further elevate the performance of the model, we introduce two innovative architectures to the text detection network: the Integrated Differentiating Feature Pyramid (IDFP) and the Texture Fusion Module (TFM). These mechanisms are capable of efficiently extracting multilevel features and multiscale textual information, which enhances the model’s stability and adaptability in complex scenarios. The experimental validation has demonstrated that the trademark text erasure model designed in this paper achieves a peak signal-to-noise ratio as high as 40.1 dB on the SCUT-Syn dataset, which is an average improvement of 11.3 dB compared with other text erasure models. Furthermore, the text detection network component of the designed model attains an accuracy of up to 89.9% on the CTW1500 dataset, representing an average enhancement of 10 percentage points over other text detection networks.https://www.mdpi.com/2076-3417/15/3/1553electronic businesstrademark retrievalself-prompting mechanismtexture aggregation |
| spellingShingle | Wenchao Zhou Xiuhui Wang Boxiu Zhou Longwen Li Text Removal for Trademark Images Based on Self-Prompting Mechanisms and Multi-Scale Texture Aggregation Applied Sciences electronic business trademark retrieval self-prompting mechanism texture aggregation |
| title | Text Removal for Trademark Images Based on Self-Prompting Mechanisms and Multi-Scale Texture Aggregation |
| title_full | Text Removal for Trademark Images Based on Self-Prompting Mechanisms and Multi-Scale Texture Aggregation |
| title_fullStr | Text Removal for Trademark Images Based on Self-Prompting Mechanisms and Multi-Scale Texture Aggregation |
| title_full_unstemmed | Text Removal for Trademark Images Based on Self-Prompting Mechanisms and Multi-Scale Texture Aggregation |
| title_short | Text Removal for Trademark Images Based on Self-Prompting Mechanisms and Multi-Scale Texture Aggregation |
| title_sort | text removal for trademark images based on self prompting mechanisms and multi scale texture aggregation |
| topic | electronic business trademark retrieval self-prompting mechanism texture aggregation |
| url | https://www.mdpi.com/2076-3417/15/3/1553 |
| work_keys_str_mv | AT wenchaozhou textremovalfortrademarkimagesbasedonselfpromptingmechanismsandmultiscaletextureaggregation AT xiuhuiwang textremovalfortrademarkimagesbasedonselfpromptingmechanismsandmultiscaletextureaggregation AT boxiuzhou textremovalfortrademarkimagesbasedonselfpromptingmechanismsandmultiscaletextureaggregation AT longwenli textremovalfortrademarkimagesbasedonselfpromptingmechanismsandmultiscaletextureaggregation |