Medical diagnosis judges the status of polyp fromthe size and the 3D shape of the polyp fromits medical endoscope image.However\nthemedical doctor judges the status empirically fromthe endoscope image and more accurate 3D shape recovery fromits 2Dimage\nhas been demanded to support this judgment. As a method to recover 3D shape with high speed, VBW (Vogel-Breu�Ÿ-Weickert)\nmodel is proposed to recover 3D shape under the condition of point light source illumination and perspective projection. However,\nVBWmodel recovers the relative shape but there is a problem that the shape cannot be recovered with the exact size. Here, shape\nmodification is introduced to recover the exact shape with modification fromthat with VBWmodel. RBF-NN is introduced for the\nmapping between input and output. Input is given as the output of gradient parameters of VBW model for the generated sphere.\nOutput is given as the true gradient parameters of true values of the generated sphere. Learning mapping with NN can modify the\ngradient and the depth can be recovered according to the modified gradient parameters. Performance of the proposed approach is\nconfirmed via computer simulation and real experiment.
Loading....