AL-2020/coder/rocognizer.py

import cv2
import matplotlib.pyplot as plt
import torch
from PIL.Image import Image
from torch import nn
from torchvision.transforms import transforms

def white_bg_square(img):
    "return a white-background-color image having the img in exact center"
    size = (max(img.size),)*2
    layer = Image.new('RGB', size, (255, 255, 255))
    layer.paste(img, tuple(map(lambda x:(x[0]-x[1])/2, zip(size, img.size))))
    return layer

code = []
path = "test5.jpg"

transform = transforms.Compose([transforms.ToTensor(),
                                transforms.Normalize((0.5,), (0.5,)),
                                ])

img = cv2.imread(path)

img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_gray = cv2.GaussianBlur(img_gray, (5, 5), 0)

ret, im_th = cv2.threshold(img_gray, 90, 255, cv2.THRESH_BINARY_INV)

ctrs, hier = cv2.findContours(im_th.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

rects = [cv2.boundingRect(ctr) for ctr in ctrs]

# load nn model
input_size = 784 # = 28*28
hidden_sizes = [128, 128, 64]
output_size = 10
model = nn.Sequential(nn.Linear(input_size, hidden_sizes[0]),
                      nn.ReLU(),
                      nn.Linear(hidden_sizes[0], hidden_sizes[1]),
                      nn.ReLU(),
                      nn.Linear(hidden_sizes[1], hidden_sizes[2]),
                      nn.ReLU(),
                      nn.Linear(hidden_sizes[2], output_size),
                      nn.LogSoftmax(dim=-1))
model.load_state_dict(torch.load('digit_reco_model2.pt'))
model.eval()

for rect in rects:
    # Crop image
    crop_img = img[rect[1]:rect[1] + rect[3] + 10, rect[0]:rect[0] + rect[2] + 10, 0]
    # Resize the image
    roi = cv2.resize(crop_img, (28, 28), interpolation=cv2.INTER_LINEAR)
    roi = cv2.dilate(roi, (3, 3))
    plt.imshow(roi)
    plt.show()
    im = transform(roi)
    im = im.view(1, 784)
    with torch.no_grad():
        logps = model(im.float())
    ps = torch.exp(logps)
    probab = list(ps.numpy()[0])
    print("Predicted Digit =", probab.index(max(probab)))

cv2.imshow("Code", img)
cv2.waitKey()