Traditional identification methods of pathogenic Candida albicans are time-consuming due to the long-term incubation. The purpose of this study is to develop a noninvasive biomolecular sensing technology for rapid identification of Candida albicans. Surface enhanced Raman scattering (SERS) based on colloidal sliver was used to rapidly detect specific molecules on the surface of cells cultured on SDA plate. A homemade fluidic chamber was fabricated to enlarge the random sampling area, increase the path length and avoid sampling error caused by disturbance or evaporation. SERS signal was detected by a 514 nm laser with a 10x objective lens. The exposure time of CCD was 10 s. Normalization, second derivative, principal component analysis (PCA) and hierarchical cluster analysis (HCA) were also integrated for discrimination of Candida albicans by spectral patterns precisely. The results show that SERS can be used to detect high-concentration suspended cells of Candida albicans. Candida albicans can be discriminated to genus and species level by principal component analysis and hierarchical cluster analysis of high frequency features of SERS spectral patterns.