Resume Parsing and Skill Extraction using Custom Pattern Matching algorithm and Gemini API

In the realm of contemporary recruitment, efficient resume parsing is essential for talent acquisition. This paper investigates resume parsing using advanced OCR technology and NLP methods. We begin with preprocessing, enhancing scanned resumes for legibility. Leveraging the Tesseract OCR engine, we convert images to machine-readable text. Through NLP techniques with spaCy, we extract key information like personal details, education, experience, and skills.Our approach integrates the Gemini Pro Vision API for semantic analysis and question-answering. This enriches our framework, enabling deeper insights and implicit attribute inference. Empirical validation across diverse datasets demonstrates the robustness of our methodology. This work sheds light on performance metrics and challenges in automated resume parsing, paving the way for future enhancements.