This thesis focuses on the development and deployment of a sophisticated licence plate recognition (LPR) system, utilising machine learning and computer vision methodologies, specifically targeting residential regions. The main aim of this study is to develop a resilient system that can effectively detect and categorise licence plates in real-time from both pictures and video feeds. This system will be optimised to enhance access control within residential complexes. The objective of this study is to overcome the current deficiencies observed in residential-focused Licence Plate Recognition systems. The aforementioned restrictions pertain to difficulties associated with achieving accuracy, adjusting to diverse environmental circumstances, and the requirement for uninterrupted, instantaneous data processing. The objective of this thesis is to further the development of licence plate recognition technology, with a specific focus on addressing the challenges posed by residential contexts.