This paper provides a comprehensive survey of local feature matching techniques, focusing on the integration of deep learning models. The authors categorize these methods into two main segments: Detector-based and Detector-free. Detector-based methods include models such as Detect-then-Describe, Joint Detection and Description, Describe-then-Detect, and Graph-Based techniques, while Detector-free methods encompass CNN-based, Transformer-based, and Patch-Based approaches. The paper evaluates prevalent datasets and metrics to facilitate a quantitative comparison of state-of-the-art techniques and explores practical applications in domains like Structure from Motion, Remote Sensing Image Registration, and Medical Image Registration. It also discusses current challenges and future research directions, emphasizing the importance of adapting to diverse and dynamic scenarios. The survey covers the evolution of local feature matching, from traditional handcrafted methods to modern deep learning technologies, and highlights the role of large foundation models in feature matching. Key contributions include a detailed overview of various local feature matching algorithms, real-world applications, and a thorough analysis of recent mainstream methods. The paper aims to serve as a reference for researchers in the field of local feature matching and its interconnected domains.This paper provides a comprehensive survey of local feature matching techniques, focusing on the integration of deep learning models. The authors categorize these methods into two main segments: Detector-based and Detector-free. Detector-based methods include models such as Detect-then-Describe, Joint Detection and Description, Describe-then-Detect, and Graph-Based techniques, while Detector-free methods encompass CNN-based, Transformer-based, and Patch-Based approaches. The paper evaluates prevalent datasets and metrics to facilitate a quantitative comparison of state-of-the-art techniques and explores practical applications in domains like Structure from Motion, Remote Sensing Image Registration, and Medical Image Registration. It also discusses current challenges and future research directions, emphasizing the importance of adapting to diverse and dynamic scenarios. The survey covers the evolution of local feature matching, from traditional handcrafted methods to modern deep learning technologies, and highlights the role of large foundation models in feature matching. Key contributions include a detailed overview of various local feature matching algorithms, real-world applications, and a thorough analysis of recent mainstream methods. The paper aims to serve as a reference for researchers in the field of local feature matching and its interconnected domains.