In this paper, we established the prediction capability for uniaxial compressive strength (UCS) from microfabric characterization of banded amphibolite schists using fuzzy inference system (FIS) and multiple linear regression (MLR) techniques. In this study, the method of semi-automatic petrographic image analysis (PIA) was adopted to calculate and measure the microfabric parameters. Based on statistical analysis, more influential microfabrics parameters that affect the UCS more than the others have been selected to predict UCS, which include grain size, shape factor, and quartz content. Multi-variate regression relations were established using the same input variables as the FIS model. To assess the performance of both models, some performance indices such as correlation coefficient (R), variance accounted for (VAF), and root mean square error (RMSE) were calculated and compared for the two models. The results show that both models reliably predict the UCS, with the multiple regression model being better based on the performance indices criteria. One of the most significant findings to emerge from this study is that the microfabrics-based PIA approach can be easily extended to the modeling of strength and deformation behavior of rocks in the absence of adequate geological information or abundant data.