app.py

import cv2
import numpy as np
from PIL import Image
import mediapipe as mp
import time
import gradio as gr
import glob

DOMINANT_HAND = "Right"

width_, height_, = 144, 96

drawing_flag = False
sleepy_time = time.time()

output_frames = []


def find_hands(brain, img):
    if img is not None:
        # print(type(img))
        img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)  # opencv image is in BGR form but mp is trained with RGB
        results = brain.process(
            img_rgb)  # process finds the hands and outputs classification and 21 landmarks for each hand
        all_hands = []  # initializing array to hold the dictionary for the hands
        h, w, _ = img.shape  # get height and width of image for scaling
        if results.multi_hand_landmarks:
            for hand_type, hand_lms in zip(results.multi_handedness,
                                           results.multi_hand_landmarks):  # elegant solution for mp list object traversal
                hand = {}  # initializing dict for each hand
                lm_list = []  # landmarks array for all 21 point of the hand
                for lm in hand_lms.landmark:
                    px, py, pz = int(lm.x * w), int(lm.y * h), int(
                        lm.z * w)  # scaling landmark points to image size for frame coordinates
                    lm_list.append([px, py, pz])

                hand["lm_list"] = lm_list  # add "lm_list" key for all landmark points of the hand
                hand["type"] = hand_type.classification[0].label  # adds the label (left/right) for the hand
                all_hands.append(hand)  # appends the dict
        return all_hands

    else:
        return 0



def is_drawing(index, thumb):  # proximity function with arbitrary threshold
    npindex = np.array((index[0], index[1]))
    npthumb = np.array((thumb[0], thumb[1]))
    if np.linalg.norm(npindex - npthumb) < 30:
        return True
    else:
        return False


def save(landmarks):  # brute force finger orientation checking
    if landmarks[8][1] < landmarks[6][1]:
        if landmarks[12][1] < landmarks[10][1]:
            if landmarks[16][1] < landmarks[14][1]:
                if landmarks[20][1] < landmarks[18][1]:
                    return True
    else:
        return False


def clear(landmarks):  # brute force finger orientation checking
    if landmarks[4][1] < landmarks[3][1] < landmarks[2][1] < landmarks[8][1]:
        return True
    else:
        return False


def show(video): # main
    cam = cv2.VideoCapture(video)  # get the video file from path
    width = cam.get(cv2.CAP_PROP_FRAME_WIDTH)
    height = cam.get(cv2.CAP_PROP_FRAME_HEIGHT)

    detector = mp.solutions.hands.Hands(min_detection_confidence=0.8)  # initialize detector
    # paper = np.zeros((width, height, 4), np.uint8)
    paper = np.zeros((int(height), int(width), 3), dtype=np.uint8)  # create blank page
    paper.fill(255)

    past_holder = ()  # hold previous index coordinates
    palette = cv2.imread('palette_small.jpg')

    page_num = 0  # iterating for saving (not a viable function for gradio)

    color = (0, 0, 0)

    global sleepy_time  # get sleep time for multiple gestures

    while cam.isOpened():
        # runny -= 1
        x, rgb_image = cam.read()
        rgb_image_f = cv2.flip(rgb_image, 1)  # mirrored video

        hands = find_hands(detector, rgb_image_f)

        if x:  # return flag for cv2
            try:  # for error handling
                if hands:
                    hand1 = hands[0] if hands[0]["type"] == DOMINANT_HAND else hands[1]
                    lm_list1 = hand1["lm_list"]  # List of 21 Landmarks
                    handedness = hand1["type"]

                    if handedness == DOMINANT_HAND:
                        idx_coords = lm_list1[8][0], lm_list1[8][1]  # 0 is width (bigger)
                        # print(idx_coords)
                        cv2.circle(rgb_image_f, idx_coords, 5, color, cv2.FILLED)

                        if idx_coords[1] < 72: # brute force but should be extremely marginally faster lol
                            if idx_coords[0] < 71:  # red
                                color = (0, 0, 255)
                            if 71 < idx_coords[0] < 142:  # orange
                                color = (0, 115, 255)
                            if 142 < idx_coords[0] < 213:  # yellow
                                color = (0, 229, 255)
                            if 213 < idx_coords[0] < 284:  # green
                                color = (0, 195, 88)
                            if 284 < idx_coords[0] < 356:  # blue
                                color = (195, 85, 0)
                            if 356 < idx_coords[0] < 427:  # indigo
                                color = (195, 0, 68)
                            if 427 < idx_coords[0] < 498:  # violet
                                color = (195, 0, 143)
                            if 498 < idx_coords[0] < 569:  # black
                                color = (0, 0, 0)
                            if 569 < idx_coords[0]:  # white / eraser
                                color = (255, 255, 255)

                        if len(past_holder) and drawing_flag: # start drawing
                            cv2.line(paper, past_holder, idx_coords, color, 5)
                            cv2.line(rgb_image_f, past_holder, idx_coords, color, 5)
                            # paper[idx_coords[0]][idx_coords[1]][0] = 255
                            # paper[idx_coords[0]][idx_coords[1]][3] = 255
                            cv2.circle(rgb_image_f, idx_coords, 5, color, cv2.FILLED)

                        # if save(lm_list1) and time.time() - sleepy_time > 3: # save / output
                        #     paper[0:height_, w - width_: w] = 255 # presenter eraser
                        #     paper = cv2.cvtColor(paper, cv2.COLOR_BGR2RGB)
                        #     im = Image.fromarray(paper)
                        #     im.save("paper%s.png" % page_num)
                        #     print("saved")
                        #     sleepy_time = time.time()
                        #     paper = cv2.cvtColor(paper, cv2.COLOR_RGB2BGR)
                        #     page_num += 1

                        if clear(lm_list1) and time.time() - sleepy_time > 3: # reset paper
                            paper = np.zeros((height, width, 3), dtype=np.uint8)
                            paper.fill(255)
                            print("page cleared")
                            sleepy_time = time.time()

                        past_holder = idx_coords

                if is_drawing(idx_coords, lm_list1[4]):  # 4 is thumb
                    drawing_flag = True
                else:
                    drawing_flag = False

            except:
                pass

            finally:
                if True:
                    rgb_image_f[0:48, ] = palette # 48 small
                    presenter = cv2.resize(rgb_image_f, (width_, height_))
                    h, w, _ = rgb_image_f.shape
                    paper[0:height_, w - width_: w] = presenter

        else:
            break

        paper = cv2.cvtColor(paper, cv2.COLOR_RGB2BGR)
        im = Image.fromarray(paper)
        output_frames.append(paper)
        im.save("paper%s.png" % page_num)
        page_num += 1

    img_array = []
    for filename in glob.glob('*.png'):
        imggg = cv2.imread(filename)
        img_array.append(imggg)

    video_output = cv2.VideoWriter('any.webm', cv2.VideoWriter_fourcc(*'VP80'), 30, (640, 480))

    for i in range(len(img_array)):
        video_output.write(img_array[i])
    video_output.release()

    return 'any.webm'


iface = gr.Interface(fn=show, inputs=gr.inputs.Video(source="webcam"), outputs='video')

iface.launch(share=True, enable_queue=True)