LostNet: A smart way for lost and find

TL;DR

LostNet is an image matching system that efficiently identifies lost items by comparing owner-provided images with new photos, achieving high accuracy and practical usability on standard laptops.

Contribution

The paper introduces LostNet, a novel photo matching network combining MobileNetv2 with CBAM Attention for effective lost item identification.

Findings

Achieved 96.8% testing accuracy.

Operates efficiently on a regular laptop.

Uses only 3.5 million training parameters.

Abstract

Due to the enormous population growth of cities in recent years, objects are frequently lost and unclaimed on public transportation, in restaurants, or any other public areas. While services like Find My iPhone can easily identify lost electronic devices, more valuable objects cannot be tracked in an intelligent manner, making it impossible for administrators to reclaim a large number of lost and found items in a timely manner. We present a method that significantly reduces the complexity of searching by comparing previous images of lost and recovered things provided by the owner with photos taken when registered lost and found items are received. In this research, we will primarily design a photo matching network by combining the fine-tuning method of MobileNetv2 with CBAM Attention and using the Internet framework to develop an online lost and found image identification system. Our implementation gets a testing accuracy of 96.8% using only 665.12M GLFOPs and 3.5M training parameters. It can recognize practice images and can be run on a regular laptop.