Microplastics (MPs) in aquatic organisms are raising increasing concerns regarding their potential damage to ecosystems. To date, Raman and Fourier transform infrared spectroscopy techniques have been widely used for detection of MPs in aquatic organisms, which requires complex protocols of tissue digestion and MP separation and are time- and reagent-consuming. This novel approach directly separates, identifies, and characterizes MPs from the hyperspectral image (HSI) of the intestinal tract content in combination with a support vector machine classification model, instead of using the real digestion/separation protocols. The procedures of HSI acquisition (1 min) and data analysis (5 min) can be completed within 6 min plus the sample preparation and drying time (30 min) where necessary. This method achieved a promising efficiency (recall >98.80%, precision >96.22%) for identifying five types of MPs (particles >0.2 mm). Moreover, the method was also demonstrated to be effective on field fish from three marine fish species, revealing satisfying detection accuracy (particles >0.2 mm) comparable to Raman analysis. The present technique omits the digestion protocol (reagent free), thereby significantly reducing reagent consumption, saving time, and providing a rapid and efficient method for MP analysis.