Skip to main content

Process image from webcam in colab

Project description

Author:KuoYuan Li

N|Solid
wrap the javascript code to handle image from webcam in colab
本package提供一系列在 colab 中操作webcam的方法
在colab中使用之前請先進行安裝

!pip install colabcam
webcam 拍照存檔
(take a photo from webcam and save to 1.jpg)
import colabcam
colabcam.take_photo("1.jpg")

動態顯示人臉框及文字(cv2只支援英數字)

(demo with mediapipe face_detection)

#Note:bbox(人臉框)是另外疊加顯示的,速度會有延遲是正常的
import mediapipe as mp
import colabcam
import numpy as np
import cv2
mp_face_detection = mp.solutions.face_detection
face_detection = mp_face_detection.FaceDetection()
# start streaming video from webcam
colabcam.video_stream()
# label for video
label_html = '顯示中...(點擊畫面以結束顯示)'
# initialze bounding box to empty
bbox = ''
while True:  
  js_reply = colabcam.video_frame(label_html, bbox)  
  if not js_reply:break  
  # convert JS response to OpenCV Image  
  img = colabcam.js_to_image(js_reply["img"])  
  results = face_detection.process(img)  
  frame_height,frame_width=np.shape(img)[0:2]  
  overlapImg = np.zeros([frame_height,frame_width,4], dtype=np.uint8)  
  if results.detections:  
    for detection in results.detections:  
      box = detection.location_data.relative_bounding_box  
      x, y, w, h =int(box.xmin*frame_width),int(box.ymin*frame_height), \
              int(box.width*frame_width),int(box.height*frame_height)         
      if w>0 and h>0:  
        overlapImg = cv2.rectangle(overlapImg,(x,y),(x+w,y+h),(255,0,0),2)  
        cv2.putText(overlapImg,'text test',(x,y-20),cv2.FONT_HERSHEY_SIMPLEX,1,(255,0,0),2)  
    bbox = colabcam.cvImg2bbox(overlapImg)  

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

colabcam-1.0.3.tar.gz (5.4 kB view details)

Uploaded Source

File details

Details for the file colabcam-1.0.3.tar.gz.

File metadata

  • Download URL: colabcam-1.0.3.tar.gz
  • Upload date:
  • Size: 5.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/47.3.1 requests-toolbelt/0.9.1 tqdm/4.43.0 CPython/3.6.8

File hashes

Hashes for colabcam-1.0.3.tar.gz
Algorithm Hash digest
SHA256 18ab3e407bf23bd0c044a45dd5010191b2551b40d57ede1ccbff65365026e1d6
MD5 9615ecab230b2a14ec176abb9b1dd1d3
BLAKE2b-256 4c40825fa07131d01c42078c314f0b87006ab1e231e8aa946e6ec3f86cef1cd0

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page