Finger print pattern recognition using Kohonen/SOM

3 次查看（过去 30 天）
Bheki Ngobe
Bheki Ngobe 2015-12-9
I am trying to create an application where I can identify a person based on finger print. I have trained my SOM, but for now I just loaded one image and I got results. My problems are 1. How do I save trained network ? 2. How will I be able to load other images for testing ? I thank you in advance members. Attached in my code
clear all clc % Image aquisition p1 =imread('C:\Users\Makhosi\Desktop\Wrut\SoftComputing\Project\finger_Print_Images\fp1.jpg'); p1 = rgb2gray(p1); level = graythresh(p1); BW = im2bw(p1,level);
% BW2 = bwmorph(BW,'remove');
X = BW; net = selforgmap([8 8]); % layer 5 and 6 will be used to train neurons net = configure(net,X); plotsompos(net) net.trainParam.epochs = 1; net = train(net,X); plotsompos(net) x = [0.5;0.3] y = net(x)

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Self-Organizing Maps 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by