A novel two-stage optimized model for logo-based document image retrieval based on a soft computing framework

The rapid development of internet helps in organizing documents based on their specific data for large-scale organizations to small-scale organizations. Document retrieval system aims to organize the relevant documents and its information based on specific terms. The availability of information stored by organization requires inexpensive storage, and the searching mechanism needs to get the information-based documents very quickly in real time. This research aims to provide such document retrieval system through logo-based identification model to analyse and organize the documents. A two-stage optimization is implemented to obtain the proposed logo-based document retrieval system using genetic algorithm and inverted ant colony optimization. Utilization of genetic operators in document retrieval classification based on index terms reduces time consumption, and inverted ant colony optimization improves the retrieval efficiency. Parameters such as classification accuracy, precision, retrieval efficiency are observed and compared with existing conventional and hybrid models experimentally to validate the proposed model.