International Journal of Scientific Research and Engineering Development

The rapid advancement of Artificial Intelligence (AI) has significantly transformed various domains, including recruitment and talent assessment. Traditional interview processes are often time-consuming, subjective, and lack scalability, making it difficult for organizations to evaluate a large number of candidates efficiently. To address these challenges, this paper presents 'Smart Vision', a web-based intelligent interview platform designed to automate and enhance recruitment via multimodal evaluation. The proposed system integrates machine learning, natural language processing (NLP), and computer vision to simulate a real-world interview environment. The platform conducts interviews across multiple stages: Aptitude, Technical, Coding, and Human Resource (HR) rounds. A core capability is the integration of the Google Gemini API to dynamically generate personalized questions and objectively evaluate text/voice responses. Furthermore, robust proctoring mechanisms—including tab-switch detection, full-screen enforcement, and real-time facial emotion recognition using DeepFace and MediaPipe—safeguard assessment integrity. Experimental evaluations confirm that the platform effectively reduces manual recruitment overhead, mitigates human bias, and delivers granular analytics reports.

T. Lakshmi Anusha, Mr. K. Subhash Chandra, Dr.P.Chiranjeevi,"Smart Vision - AI Intelligent Emotion-Aware Interview Assessment System" International Journal of Scientific Research and Engineering Development, V9(3): Page(2439-2445) May-June 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.