Working code for my image detection script. This is functional code.

I'm loading a number of images into an array, and using two classes to generate the two main components I need for my detection; Vision and WindowCapture.

WindowCapture will grab a cropped section of your primary monitor to run detection on, while any images sitting inside the avoid directory will attempt to be found within the screen.

import cv2 as cv
import os
import glob
from windowcapture import WindowCapture
from vision import Vision

# Change the working directory to the folder this script is in.

avoid = glob.glob(r"C:\Users\coyle\OneDrive\froggy-pirate-master\avoidShips\avoidShipActual\defeat\*.png")

def loadImages(directory):
    # Intialise empty array
    image_list = []
    # Add images to array
    for i in directory:
        img = cv.imread(i, cv.IMREAD_UNCHANGED)
        image_list.append((img, i))
    return image_list

# initialize the WindowCapture class
wincap = WindowCapture()

def keypoint_detection(image_list):

    for i in image_list:
        needle_img = i[0]
        needle_name = i[1]
        sliced_name = needle_name.split("\\")[-1]

        # load image to find
        objectToFind = Vision(needle_img)
        # get an updated image of the screen
        keypoint_haystack = wincap.get_haystack()
        # crop the image
        x, w, y, h = [600,700,20,50]
        keypoint_haystack = keypoint_haystack[y:y+h, x:x+w]

        kp1, kp2, matches, match_points = objectToFind.match_keypoints(keypoint_haystack, sliced_name)
        match_image = cv.drawMatches(objectToFind.needle_img, kp1, keypoint_haystack, kp2, matches, None)

        if match_points:
            # find the center point of all the matched features
            center_point = objectToFind.centeroid(match_points)
            # account for the width of the needle image that appears on the left
            center_point[0] += objectToFind.needle_w
            # drawn the found center point on the output image
            match_image = objectToFind.draw_crosshairs(match_image, [center_point])

            # move somewhere/do something

        # display the processed image
        cv.imshow('Keypoint Search', match_image)

        # press 'q' with the output window focused to exit.
        if cv.waitKey(1) == ord('q'):
    ships_to_avoid = loadImages(avoid)

Vision Class:

import cv2 as cv
import numpy as np

class Vision:
# properties
needle_img = None
needle_w = 0
needle_h = 0

# constructor
def __init__(self, needle_img_path):
    self.needle_img = needle_img_path

    # Save the dimensions of the needle image
    self.needle_w = self.needle_img.shape[1]
    self.needle_h = self.needle_img.shape[0]

def draw_crosshairs(self, haystack_img, points):
    # these colors are actually BGR
    marker_color = (255, 0, 255)
    marker_type = cv.MARKER_CROSS

    for (center_x, center_y) in points:
        # draw the center point
        cv.drawMarker(haystack_img, (center_x, center_y), marker_color, marker_type)

    return haystack_img

def match_keypoints(self, original_image, name, patch_size=32):
    min_match_count = 30

    orb = cv.ORB_create(edgeThreshold=0, patchSize=patch_size)
    keypoints_needle, descriptors_needle = orb.detectAndCompute(self.needle_img, None)
    orb2 = cv.ORB_create(edgeThreshold=0, patchSize=patch_size, nfeatures=2000)
    keypoints_haystack, descriptors_haystack = orb2.detectAndCompute(original_image, None)

    index_params = dict(algorithm=FLANN_INDEX_LSH, table_number=6, key_size=12, multi_probe_level=1)
    search_params = dict(checks=50)

        flann = cv.FlannBasedMatcher(index_params, search_params)
        matches = flann.knnMatch(descriptors_needle, descriptors_haystack, k=2)
    except cv.error:
        return None, None, [], [], None

    # store all the good matches as per Lowe's ratio test.
    good = []
    points = []

    for pair in matches:
        if len(pair) == 2:
            if pair[0].distance < 0.7*pair[1].distance:

    if len(good) > min_match_count:
        print(str(name) + ' - ' + '%03d keypoints matched - %03d' % (len(good), len(keypoints_needle)))
        for match in good:
    return keypoints_needle, keypoints_haystack, good, points

def centeroid(self, point_list):
    point_list = np.asarray(point_list, dtype=np.int32)
    length = point_list.shape[0]
    sum_x = np.sum(point_list[:, 0])
    sum_y = np.sum(point_list[:, 1])
    return [np.floor_divide(sum_x, length), np.floor_divide(sum_y, length)]

WindowCapture Class:

import numpy as np
import win32gui, win32ui, win32con

class WindowCapture:

# properties
w = 0
h = 0
hwnd = None
cropped_x = 0
cropped_y = 0
offset_x = 0
offset_y = 0

# constructor
def __init__(self, window_name=None):
    # find the handle for the window we want to capture.
    # if no window name is given, capture the entire screen
    if window_name is None:
        self.hwnd = win32gui.GetDesktopWindow()
        self.hwnd = win32gui.FindWindow(None, window_name)
        if not self.hwnd:
            raise Exception('Window not found: {}'.format(window_name))

    # get the window size
    window_rect = win32gui.GetWindowRect(self.hwnd)
    self.w = window_rect[2] - window_rect[0]
    self.h = window_rect[3] - window_rect[1]

    # account for the window border and titlebar and cut them off
    border_pixels = 0
    titlebar_pixels = 0
    self.w = self.w - (border_pixels * 2)
    self.h = self.h - titlebar_pixels - border_pixels
    self.cropped_x = border_pixels
    self.cropped_y = titlebar_pixels

    # set the cropped coordinates offset so we can translate screenshot
    # images into actual screen positions
    self.offset_x = window_rect[0] + self.cropped_x
    self.offset_y = window_rect[1] + self.cropped_y

def get_haystack(self):

    # get the window image data
    wDC = win32gui.GetWindowDC(self.hwnd)
    dcObj = win32ui.CreateDCFromHandle(wDC)
    cDC = dcObj.CreateCompatibleDC()
    dataBitMap = win32ui.CreateBitmap()
    dataBitMap.CreateCompatibleBitmap(dcObj, self.w, self.h)
    cDC.BitBlt((0, 0), (self.w, self.h), dcObj, (self.cropped_x, self.cropped_y), win32con.SRCCOPY)

    # convert the raw data into a format opencv can read
    # dataBitMap.SaveBitmapFile(cDC, 'debug.bmp')
    signedIntsArray = dataBitMap.GetBitmapBits(True)
    img = np.fromstring(signedIntsArray, dtype='uint8')
    img.shape = (self.h, self.w, 4)

    # free resources
    win32gui.ReleaseDC(self.hwnd, wDC)
    img = img[...,:3]
    img = np.ascontiguousarray(img)

    return img

def list_window_names():
    def winEnumHandler(hwnd, ctx):
        if win32gui.IsWindowVisible(hwnd):
            print(hex(hwnd), win32gui.GetWindowText(hwnd))
    win32gui.EnumWindows(winEnumHandler, None)

# translate a pixel position on a screenshot image to a pixel position on the screen.
# pos = (x, y)
def get_screen_position(self, pos):
    return (pos[0] + self.offset_x, pos[1] + self.offset_y)


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Browse other questions tagged or ask your own question.