The system based on Fiber Bragg Grating (FBG) sensor is used in various fields, because of its advantages of high detection accuracy, good repeatability and adaptability. While the FBG sensor is a wavelength modulation type sensor, so the outside parameter detection is the center wavelength of FBG detection. At the same time, the FBG center wavelength corresponding to the peak value of the FBG reflection spectrum. Therefore, the core of demodulation system is the demodulation of FBG reflection spectrum during peak-seeking, and the high-precision peak detecting algorithm is the key technology of the system demodulation. The current peak detecting algorithms has a precondition for peak detection on FBG reflective spectrum, that the FBG reflective spectrum was a standard Gaussian model. But FBG reflective spectrum is not a standard Gaussian spectrum owing to the practical manufacture process and the individual environment; actually, it is an asymmetrical Gaussian spectrum. The experiment would achieve a lower accuracy because of this asymmetric property during peak-seeking. Based on the defect of the existing algorithm, an Exponent Modified Gaussian (EMG) Curve Fitting peak detecting algorithm is proposed in this paper. In the proposed algorithm, the coarse location was first determined by three times judgments and it can remove the false peak and peak invalid at the same time. Based on this, as the center of the coarse localization point to reconstruct the spectrum, and using the integral to judge the peak bias; then according to different peak bias, it revised the peak by the prepared exponential modified function. Simulation results show that at normal temperature or under variable temperature conditions, by comparing with direct peak searching algorithm, Gaussian fitting algorithm and the algorithm proposed by literature, the error of EMG peak detection algorithm is the minimum and high peak detecting precision. The algorithm proposed in this paper considers the FBG reflection spectrum characteristic of asymmetric effect. From its spectrum character, the EMG algorithm solves the problem of the limits of traditional peak detecting algorithm, meanwhile also guarantees a high-precision peak search results.