PreProcessing.py

"""
get_info() function reads the image using openCV and performs thresholding, dilation, noise removal, and
contouring to finally retrieve bounding boxes from the contour.


Below are some of the additional available functions from openCV for preprocessing:

Median filter: median filter blurs out noises by taking the medium from a set of pixels
cv2.medianBlur()

Dilation and erosion: dilation adds pixels to boundaries of pixels, erosion removes it
cv2.dilate()
cv2.erode()
cv2.opening() #This is an erosion followed by a dilation
"""

def get_info(path):
    font     = cv2.FONT_HERSHEY_SIMPLEX
    fontScale = 0.5
    fontColor  = (255,0,0)
    lineType = 1

    #Threshold
    image = cv2.imread(path)

    height,width,channel = image.shape
    
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    T = threshold_local(gray, 15, offset = 6, method = "gaussian") # generic, mean, median, gaussian
    thresh = (gray > T).astype("uint8") * 255
    thresh = ~thresh

    #Dilation
    kernel =np.ones((1,1), np.uint8)
    ero = cv2.erode(thresh, kernel, iterations= 1)
    img_dilation = cv2.dilate(ero, kernel, iterations=1)

    # Remove noise
    nlabels, labels, stats, centroids = cv2.connectedComponentsWithStats(img_dilation, None, None, None, 8, cv2.CV_32S)
    sizes = stats[1:, -1] #get CC_STAT_AREA component
    final = np.zeros((labels.shape), np.uint8)
    for i in range(0, nlabels - 1):
        if sizes[i] >= 10:   #filter small dotted regions
            final[labels == i + 1] = 255

    #Find contours
    kern = np.ones((5,15), np.uint8)
    img_dilation = cv2.dilate(final, kern, iterations = 1)
    contours, hierarchy = cv2.findContours(img_dilation, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
    # Map contours to bounding rectangles, using bounding_rect property
    rects = map(lambda c: cv2.boundingRect(c), contours)
    # Sort rects by top-left x (rect.x == rect.tl.x)
    sorted_rects = sorted(rects, key =lambda r: r[0])
    sorted_rects = sorted(sorted_rects, key =lambda r: r[1])

    etfo=''
    for rect in sorted_rects:
        x,y,w,h = rect
        if(w<20 or h<20):
            continue
        temp = image[y:y+h, x:x+w]
        temp = cv2.cvtColor(temp, cv2.COLOR_BGR2RGB)
        hi = pytesseract.image_to_data(temp, config=r'--psm 6')
        hi = hi.split()
        ind = 22
        while(True):
            if (ind>len(hi)):
                break
            if(int(hi[ind])==-1):
                ind+=11
            else:
                etfo=etfo+hi[ind+1]
                etfo=etfo+" "
                x+=len(hi[ind+1])*20
                ind+=12
        etfo=etfo+'\n'
    return etfo

This is great solution, I have images saved in pdf files with multiple pages. can you suggest how to apply this on the pdfs which are basically scanned documents save as pdf.

pil_images = pdf2image.convert_from_path(your_multipage_pdf_file_here, dpi=200, output_folder='/tmp', first_page=None, last_page=None, fmt='JPG', thread_count=1, userpw=None, use_cropbox=False, strict=False)

this is just the meat, I let your figure out the rest.

Here where is the image path, you're not assigning any image or pdf to the path? Then how do you take the tested image or pdf file?