After you are done with Object Detection, you can perform text detection which can be passed on to tesseract. There can multiple variation to enhance image before passing it to detector function.
Reference Papers
https://arxiv.org/abs/1704.03155v2
https://arxiv.org/pdf/2002.07662.pdf
def text_detector(image):
#hasFrame, image = cap.read()
orig = image
(H, W) = image.shape[:2]
(newW, newH) = (640, 320)
rW = W / float(newW)
rH = H / float(newH)
image = cv2.resize(image, (newW, newH))
(H, W) = image.shape[:2]
layerNames = [
"feature_fusion/Conv_7/Sigmoid",
"feature_fusion/concat_3"]
blob = cv2.dnn.blobFromImage(image, 1.0, (W, H),
(123.68, 116.78, 103.94), swapRB=True, crop=False)
net.setInput(blob)
(scores, geometry) = net.forward(layerNames)
(numRows, numCols) = scores.shape[2:4]
rects = []
confidences = []
for y in range(0, numRows):
scoresData = scores[0, 0, y]
xData0 = geometry[0, 0, y]
xData1 = geometry[0, 1, y]
xData2 = geometry[0, 2, y]
xData3 = geometry[0, 3, y]
anglesData = geometry[0, 4, y]
# loop over the number of columns
for x in range(0, numCols):
# if our score does not have sufficient probability, ignore it
if scoresData[x] < 0.5:
continue
# compute the offset factor as our resulting feature maps will
# be 4x smaller than the input image
(offsetX, offsetY) = (x * 4.0, y * 4.0)
# extract the rotation angle for the prediction and then
# compute the sin and cosine
angle = anglesData[x]
cos = np.cos(angle)
sin = np.sin(angle)
# use the geometry volume to derive the width and height of
# the bounding box
h = xData0[x] + xData2[x]
w = xData1[x] + xData3[x]
# compute both the starting and ending (x, y)-coordinates for
# the text prediction bounding box
endX = int(offsetX + (cos * xData1[x]) + (sin * xData2[x]))
endY = int(offsetY - (sin * xData1[x]) + (cos * xData2[x]))
startX = int(endX - w)
startY = int(endY - h)
# add the bounding box coordinates and probability score to
# our respective lists
rects.append((startX, startY, endX, endY))
confidences.append(scoresData[x])
boxes = non_max_suppression(np.array(rects), probs=confidences)
for (startX, startY, endX, endY) in boxes:
startX = int(startX * rW)
startY = int(startY * rH)
endX = int(endX * rW)
endY = int(endY * rH)
# draw the bounding box on the image
cv2.rectangle(orig, (startX, startY), (endX, endY), (0, 255, 0), 3)
return orig