def to_string(self, res_crnn):
strings = []
for i in range(len(res_crnn)):
chars = [alphabet[c] for c in np.argmax(res_crnn[i], axis=1)]
res_str = decode(chars)
strings.append(res_str)
return strings
if len(words) > 0:
res_crnn = rec_model.predict(words)
xy = rboxes[:,:2]
xy[:,0] = xy[:,0] - rboxes[:,2] / 2
xy = xy / input_size * [vid_w, vid_h]
for i in range(len(words)):
idxs = np.argmax(res_crnn[i], axis=1)
confs = res_crnn[i][range(len(idxs)),idxs]
non_blank_mask = idxs != len(alphabet)-1
if np.any(non_blank_mask):
mean_conf = np.mean(confs[non_blank_mask])
chars = [alphabet[c] for c in idxs]
res_str = decode(chars)
# filter based on recognition threshold
#if mean_conf > 0.7-0.4*np.exp(-0.1*np.sum(non_blank_mask)):
if mean_conf > 0.6:
b = boxes[i].reshape((-1,1,2)) * [vid_w, vid_h]
b = np.asarray(np.round(b), dtype=np.int32)
cv2.polylines(img1, [b], True, (0,0,255))
#cv2.imwrite('croped_word_%03i.png' % (i), words[i])
cv2.putText(img2, res_str, tuple(xy[i].astype(int)),
cv2.FONT_HERSHEY_SIMPLEX, 0.35, (255,255,255), 1)
else:
#print('drop %5.3f %s' % (mean_conf, res_str))
pass
