Sorting misorganized books in libraries based on ant colony algorithm
With open libraries becoming the main mode of operation for libraries in various regions, the difficulty of book management has sharply increased for management personnel. This study proposes a misorganized book sorting model on the basis of ant colony optimization algorithm. This model uses the inf...
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/S2772941925001917 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | With open libraries becoming the main mode of operation for libraries in various regions, the difficulty of book management has sharply increased for management personnel. This study proposes a misorganized book sorting model on the basis of ant colony optimization algorithm. This model uses the information transmission and search capabilities of ant colony algorithm to identify the edges of the target, and then segments the image using the two-dimensional maximum between-class variance method to extract the location information of the book. The global optimization possessed by ant colony algorithm can also make the convergence value of the model close to the optimal value, thereby improving the overall operational efficiency of the model. At the same time, the two-dimensional maximum between-class variance method itself has a certain ability to resist noise interference. The experimental results show that the proposed algorithm achieves a contour detection accuracy of 82.31 % on the Iris dataset, which is 12.15 % and 3.72 % higher than the traditional ACO algorithm (70.16 %) and the Laplace algorithm (78.59 %) respectively. Its progressiveness is reflected in the fact that the loss rate converges to 0.02 after 300 iterations. It reaches a stable state 150 iterations earlier than the ACO algorithm. In the anti-noise interference test, the algorithm reduced the false detection rate of the Aerial dataset from 22.3 % of ACO to 9.8 % through the neighborhood gray-scale fusion mechanism of two-dimensional OTSU. Moreover, it still maintained a positioning accuracy rate of 89.4 % when the bookshelf spacing changed dynamically by ±10 mm, verifying the adaptability of the model to complex physical environments. Furthermore, tests on the self-made book dataset show that the recognition recall rate of the algorithm for worn book spints reaches 83.2 %, which is 7.8 % higher than that of the Canny operator. Its progressive optimization ability stems from the collaborative mechanism of the ACO pheromone matrix and the OTSU threshold search, effectively balancing the contradiction between global exploration and local feature preservation. |
|---|---|
| ISSN: | 2772-9419 |