Abstract：An RFID and Computer Vision Fusion System for Book Inventory using Mobile Robot Mobile robot-assisted book inventory such as book identification and book order detection has become increasingly popular in smart libraryreplacing the manual book inventory which is time-consuming and error-proneThe existing systems are either comput Library AutomationAutomating book inventory through mobile robotsCollection ClassificationUsing RFID and CV to identify and detect book orderRetrieval and IndexingAccurately extracting spine information and sorting books through deep neural network models and video information extraction patternsDiscusses the increasing popularity of using mobile robots to assist in book inventorysuch as book identification and book order detectionin smart librariesThe study proposes a novel RFID and CV fusion system for book inventory using mobile robotsRC-BISpecificallythe study addresses three technical challengesdesigning a deep neural networkDNNmodel using multiple inputs and hybrid data to filter interference from other layersRFID tagsproposing a video information extraction pattern to accurately extract spine informationand using strong links to align and match RFID-and CV-based timestamp pairs to book title sequences to avoid errors during fusion