LostNet: A smart way for lost and find

• Published in: PloS one Vol. 19; no. 10; p. e0310998
• Main Authors: Zhou, Meihua, Fung, Ivan, Yang, Li, Wan, Nan, Di, Keke, Wang, Tingting
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 30.10.2024; Public Library of Science (PLoS)
• Subjects: Accuracy; Algorithms; Biology and Life Sciences; Classification; Computer and Information Sciences; Datasets; Deep learning; Efficiency; Electronic equipment; Hash based algorithms; Humans; Image Processing, Computer-Assisted - methods; Image retrieval; Innovations; Internet; Java; Lost & found property; Lost articles (Law); Machine learning; Management; Medical imaging equipment; Methods; Multilingualism; Neural networks; Neural Networks, Computer; Parameter identification; Photography; Physical Sciences; Population growth; Public transportation; Python; Research and Analysis Methods; Search process; Semantics; Smartphones; Social Sciences; Transfer learning; Urban areas; User interface; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0310998

The rapid population growth in urban areas has led to an increased frequency of lost and unclaimed items in public spaces such as public transportation, restaurants, and other venues. Services like Find My iPhone efficiently track lost electronic devices, but many valuable items remain unmonitored, resulting in delays in reclaiming lost and found items. This research presents a method to streamline the search process by comparing images of lost and recovered items provided by owners with photos taken when items are registered as lost and found. A photo matching network is proposed, integrating the transfer learning capabilities of MobileNetV2 with the Convolutional Block Attention Module (CBAM) and utilizing perceptual hashing algorithms for their simplicity and speed. An Internet framework based on the Spring Boot system supports the development of an online lost and found image identification system. The implementation achieves a testing accuracy of 96.8%, utilizing only 0.67 GFLOPs and 3.5M training parameters, thus enabling the recognition of images in real-world scenarios and operable on standard laptops.