FingerprintSOM / app.py
Overglitch's picture
Update app.py
051a67b verified
raw
history blame
3.28 kB
from fastapi import FastAPI, File, UploadFile, HTTPException
from PIL import Image
import numpy as np
import pickle
app = FastAPI()
# Cargar el modelo SOM previamente entrenado
with open("som.pkl", "rb") as tf:
som = pickle.load(tf)
# Funci贸n para realizar la predicci贸n de huellas dactilares
def predict_fingerprint(image):
try:
# Preprocesar la imagen para que coincida con las dimensiones esperadas por el SOM
processed_image = preprocess_image(image)
# Obtener la ubicaci贸n del nodo ganador en el SOM
winner = som.winner(processed_image)
# Asignar la etiqueta correspondiente a la ubicaci贸n ganadora en el SOM
fingerprint_type = get_fingerprint_type(winner)
return fingerprint_type
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
def preprocess_image(image):
return image
def get_fingerprint_type(winner):
# Usar la matriz M del c贸digo SOM para asignar la etiqueta correspondiente
labels = {0: "LL", 1: "RL", 2: "WH", 3: "AR"} # Mapa de etiquetas
fingerprint_type = labels[int(M[winner[0], winner[1]])]
return fingerprint_type
@app.post("/predict/")
async def predict_fingerprint_api(file: UploadFile = File(...)):
try:
contents = await file.read()
image = Image.open(BytesIO(contents))
fingerprint_type = predict_fingerprint(image)
return {"prediction": fingerprint_type}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
def sobel(I):
m,n = I.shape# I de 254x254
Gx = np.zeros([m-2,n-2],np.float32)# Gx de 252x252
Gy = np.zeros([m-2,n-2],np.float32)# Gy de 252x252
gx = [[-1,0,1],[ -2,0,2],[ -1,0,1]]
gy = [[1,2,1],[ 0,0,0],[ -1,-2,-1]]
for j in range(1,m-2):
for i in range(1,n-2):
Gx[j-1,i-1] = sum(sum(I[j-1:j+2,i-1:i+2]*gx))
Gy[j-1,i-1] = sum(sum(I[j-1:j+2,i-1:i+2]*gy))
return Gx,Gy
def medfilt2(G,d=3):
m,n = G.shape
temp = np.zeros([m+2*(d//2),n+2*(d//2)],np.float32)
salida = np.zeros([m,n],np.float32)
temp[1:m+1,1:n+1] = G
for i in range(1,m):
for j in range(1,n):
A = np.asarray(temp[i-1:i+2,j-1:j+2]).reshape(-1)
salida[i-1,j-1] = np.sort(A)[d+1]
return salida
def orientacion(patron,w):
Gx,Gy = sobel(patron)# patron de 254x254
Gx = medfilt2(Gx)# Gx de 252x252
Gy = medfilt2(Gy)# Gy de 252x252
m,n = Gx.shape
mOrientaciones = np.zeros([m//w,n//w],np.float32)# de una matriz de 18x18
for i in range(m//w):
for j in range(n//w):
YY = sum(sum(2*Gx[i*w:(i+1)*w,j:j+1]*Gy[i*w:(i+1)*w,j:j+1]))
XX = sum(sum(Gx[i*w:(i+1)*w,j:j+1]**2-Gy[i*w:(i+1)*w,j:j+1]**2))
#YY = sum(sum(2*Gx[i*w:(i+1)*w,0:1]*Gy[i*w:(i+1)*w,0:1]))
#XX = sum(sum(Gx[i*w:(i+1)*w,0:1]**2-Gy[i*w:(i+1)*w,0:1]**2))
mOrientaciones[i,j] = (0.5*math.atan2(YY,XX) + math.pi/2.0)*(180.0/math.pi)
return mOrientaciones
def representativo(archivo):
im = Image.open(archivo)
m,n = im.size
imarray = np.array(im,np.float32)
patron = imarray[1:m-1,1:n-1]# de 256x256 a 254x254
EE = orientacion(patron,14)# retorna EE de 18x18
return np.asarray(EE).reshape(-1)