This works presents a study of images generated from a surface plasmons resonance (SPR) sensor. The images from the SPR sensor present noise and deformations, that affect the quality of the response in the incidence of the curve in certain points of the image. Smoothing and enhancement techniques were applied in order to improve the quality of the images generated by the sensor and consequently the SPR curves generated from these images. After applying the Digital Image Processing (DIP) techniques, the statistical resampling strategy provided by Bootstrap was used to estimate the confidence intervals between the rows/columns of the images, and thus obtain the RPS curves that maximize the sensitivity of the sensor for H2O substances (deionized and degassed water), PBS buffer solution (Phosphate-buffered saline) and Hypochlorite solution. The results of the sensitivity analysis showed a better interpretation of this work through the Bootstrap method used, estimating between the confidence intervals a better SPR response.