In modern society, one of the most frequent clinical cases involves location and extraction of firearms projectiles, usually made of lead, a non-ferromagnetic material. The development of a technique that allows the precise location of these projectiles will aid their surgical removal, which has a great relevance because it contributes directly to the increase of the survival rate of wounded patients. Thus, this dissertation presents and discusses two new approaches based on computational intelligence techniques, aiming at locating firearm projectiles inserted into the human body, by processing the information contained in magnetic field maps. On both approaches, the projectile is modeled by a sphere with radius a, located on a search space contained in a xy plane that is situated at a distance h from the sensor, along the z axis. The proposed location techniques require the generation of a primary alternating magnetic field by means of a solenoid, which aims at inducing eddy currents in a firearm projectile contained in the search space. In turn, these currents will produce a secondary magnetic field, which can be measured by a high-sensitivity sensor located at the bottom of the solenoid. In the first developed technique, the x and y positions of the projectile were estimated by a windowing algorithm that takes into account maximum and mean values contained on the secondary magnetic field maps. In turn, the distance h between the sphere and the sensor is inferred by a neural network, and the radius of the sphere a is estimated by a genetic algorithm. In the second technique, the four variables of interest (x, y, h and a) are inferred directly by a genetic algorithm. The results obtained are evaluated and compared.