Intelligent library shelf management system for open-access environments: A CNN-based approach with enhanced image recognition and disorder detection
With the development of information technology, libraries have become an important way for people to acquire knowledge. However, the phenomenon of disorderly books has brought considerable inconvenience to reading. The study is conducted to solve the problem of unorganized placement of books faced b...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Systems and Soft Computing |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772941925001565 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850111765071790080 |
|---|---|
| author | Xueqi Zhang |
| author_facet | Xueqi Zhang |
| author_sort | Xueqi Zhang |
| collection | DOAJ |
| description | With the development of information technology, libraries have become an important way for people to acquire knowledge. However, the phenomenon of disorderly books has brought considerable inconvenience to reading. The study is conducted to solve the problem of unorganized placement of books faced by traditional library management systems in an open-shelf lending environment. The existing library shelf management systems often struggle to effectively organize and locate books, leading to user dissatisfaction and low operational efficiency. To address this issue, an improved library shelf management system based on the convolutional neural network algorithm has been proposed. The new system adopts an optimized convolutional kernel design to improve the accuracy of feature extraction. It incorporates batch normalization techniques to mitigate the occurrence of overfitting and utilizes multi-scale feature fusion technology to enhance the ability to recognize book images. Experimental results demonstrated that the improved algorithm exhibited superior performance to convolutional neural networks and support vector machine algorithms. The accuracy increased by 2.11% and 4.76%, the root mean square error decreased by 0.12 and 0.21, and the average percentage error decreased by 0.14 and 0.28, respectively. User feedback emphasized the convenience of finding books and the significant improvement in overall user experience, indicating higher user acceptance and satisfaction. The new algorithm has higher accuracy and image recognition ability than traditional systems. In addition, the seamless integration of the improved system with existing library settings has demonstrated its practical applicability and the potential to fundamentally change library management. The research effectively addresses the limitations of existing research and provides new technological ideas and methods for library management. |
| format | Article |
| id | doaj-art-4e50487e19b54907ad1c744f273367ab |
| institution | OA Journals |
| issn | 2772-9419 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Systems and Soft Computing |
| spelling | doaj-art-4e50487e19b54907ad1c744f273367ab2025-08-20T02:37:33ZengElsevierSystems and Soft Computing2772-94192025-12-01720033810.1016/j.sasc.2025.200338Intelligent library shelf management system for open-access environments: A CNN-based approach with enhanced image recognition and disorder detectionXueqi Zhang0Corresponding author.; The Library, Daqing Normal University, Daqing, 163712, ChinaWith the development of information technology, libraries have become an important way for people to acquire knowledge. However, the phenomenon of disorderly books has brought considerable inconvenience to reading. The study is conducted to solve the problem of unorganized placement of books faced by traditional library management systems in an open-shelf lending environment. The existing library shelf management systems often struggle to effectively organize and locate books, leading to user dissatisfaction and low operational efficiency. To address this issue, an improved library shelf management system based on the convolutional neural network algorithm has been proposed. The new system adopts an optimized convolutional kernel design to improve the accuracy of feature extraction. It incorporates batch normalization techniques to mitigate the occurrence of overfitting and utilizes multi-scale feature fusion technology to enhance the ability to recognize book images. Experimental results demonstrated that the improved algorithm exhibited superior performance to convolutional neural networks and support vector machine algorithms. The accuracy increased by 2.11% and 4.76%, the root mean square error decreased by 0.12 and 0.21, and the average percentage error decreased by 0.14 and 0.28, respectively. User feedback emphasized the convenience of finding books and the significant improvement in overall user experience, indicating higher user acceptance and satisfaction. The new algorithm has higher accuracy and image recognition ability than traditional systems. In addition, the seamless integration of the improved system with existing library settings has demonstrated its practical applicability and the potential to fundamentally change library management. The research effectively addresses the limitations of existing research and provides new technological ideas and methods for library management.http://www.sciencedirect.com/science/article/pii/S2772941925001565Library disorderImage recognition |
| spellingShingle | Xueqi Zhang Intelligent library shelf management system for open-access environments: A CNN-based approach with enhanced image recognition and disorder detection Systems and Soft Computing Library disorder Image recognition |
| title | Intelligent library shelf management system for open-access environments: A CNN-based approach with enhanced image recognition and disorder detection |
| title_full | Intelligent library shelf management system for open-access environments: A CNN-based approach with enhanced image recognition and disorder detection |
| title_fullStr | Intelligent library shelf management system for open-access environments: A CNN-based approach with enhanced image recognition and disorder detection |
| title_full_unstemmed | Intelligent library shelf management system for open-access environments: A CNN-based approach with enhanced image recognition and disorder detection |
| title_short | Intelligent library shelf management system for open-access environments: A CNN-based approach with enhanced image recognition and disorder detection |
| title_sort | intelligent library shelf management system for open access environments a cnn based approach with enhanced image recognition and disorder detection |
| topic | Library disorder Image recognition |
| url | http://www.sciencedirect.com/science/article/pii/S2772941925001565 |
| work_keys_str_mv | AT xueqizhang intelligentlibraryshelfmanagementsystemforopenaccessenvironmentsacnnbasedapproachwithenhancedimagerecognitionanddisorderdetection |