# configure connection to mongodb
conn = pymongo.MongoClient(cfg['DEFAULT']['_URI'])
try:
conn.server_info()
except Exception as e:
logging.error("Unable to connect to {s}".format(s=cfg['DEFAULT']['_URI']))
conn = None
sys.exit(1)
handle = conn[cfg['DEFAULT']['_DBNAME']][cfg['DEFAULT']['_COLNAME']]
print("Connected to Atlas!")
# configure connection to watson VisualRecognitionV3 api
visual_recognition = VisualRecognitionV3(
cfg['DEFAULT']['_WATSONAPIVER'],
iam_apikey=cfg['DEFAULT']['_WATSONAPIKEY'])
#########
# configure web interface
#########
class MainHandler(tornado.web.RequestHandler):
def get(self):
self.render("Web/index.html", title="Welcome")
class WebSockHandler(tornado.websocket.WebSocketHandler):
def open(self):
print("New client connected")
_clients.append(self)
!pip install --upgrade "watson-developer-cloud>=2.4.1"
!pip install simplejson
import json
from watson_developer_cloud import VisualRecognitionV3
visual_recognition = VisualRecognitionV3(
'2018-03-19',
iam_apikey='1ILZkyzgNMH6FTgPJ8WtT6WR4scQj_LNmkHRFsMN78Pj')
# File path will change when run on colab.
with open('/images/image1', 'rb') as images_file:
classes = visual_recognition.classify(
images_file,
threshold='0.6',
classifier_ids='default').get_result()
print(json.dumps(classes, indent=2))
import json
from watson_developer_cloud import VisualRecognitionV3
visual_recognition = VisualRecognitionV3(
'2018-03-19',
iam_apikey='tDYM20kS5sD2jkAApAOrb83RdBO0I2nl-rCuVp10gsJH')
with open('./image.jpg', 'rb') as images_file:
classes = visual_recognition.classify(
images_file,
threshold='0.6',
classifier_ids='DefaultCustomModel_877446449').get_result()
a=classes['images'][0]['classifiers'][0]['classes'][0]['class']
print(a)
if a=='persons' :
print("authorized person entered")
else:
print("unauthorized person not entered")
from os.path import join, dirname
from os import environ
from watson_developer_cloud import VisualRecognitionV3
visual_recognition = VisualRecognitionV3(
'2016-05-20', api_key='4a5dce0273f76cfc7fdebaec7d43f6828a512194')
def classify(url):
return visual_recognition.classify(images_url=url)
def __init__(self):
self.url = "https://gateway-a.watsonplatform.net/visual-recognition/api"
self.note = "It may take up to 5 minutes for this key to become active"
self.api_key = "bbe846d049b62bb116e525f0ad3c6b2989d99613"
visual_recognition = VisualRecognitionV3('2016-05-20',
api_key=self.api_key)
import time
from datetime import datetime
import os
#using Google Text-to-Speech
from gtts import gTTS
from pygame import mixer
import cv2
import json
from watson_developer_cloud import VisualRecognitionV3
import RPi.GPIO as GPIO
#Detecting the object using visual recognition service{IBM CLOUD)
visual_recognition = VisualRecognitionV3(
'2018-03-19', iam_apikey='RLYVVSSFLFSjrr9pueeCaL4pTjEqs-7cLuCaG4njjqym')
GPIO.setmode(GPIO.BCM)
GPIO.setwarnings(False)
#connect ultrasonic sensor to the following pins of the raspberrypi
TRIG = 23
ECHO = 24
print "Distance Mesurement In Progress"
GPIO.setup(TRIG, GPIO.OUT)
GPIO.setup(ECHO, GPIO.IN)
print "Waiting for Sensor Data"
import json
from os.path import join, dirname
from watson_developer_cloud import VisualRecognitionV3
test_url = 'https://www.ibm.com/ibm/ginni/images' \
'/ginni_bio_780x981_v4_03162016.jpg'
visual_recognition = VisualRecognitionV3('2016-05-20', api_key='YOUR API KEY')
# with open(join(dirname(__file__), '../resources/cars.zip'), 'rb') as cars, \
# open(join(dirname(__file__), '../resources/trucks.zip'), 'rb') as
# trucks:
# print(json.dumps(visual_recognition.create_classifier('Cars vs Trucks',
# cars_positive_examples=cars,
#
# negative_examples=trucks), indent=2))
car_path = join(dirname(__file__), '../resources/car.jpg')
with open(car_path, 'rb') as image_file:
car_results = visual_recognition.classify(
images_file=image_file,
threshold=0.1,
classifier_ids=['CarsvsTrucks_1479118188', 'default'])
print(json.dumps(car_results, indent=2))
# print(json.dumps(visual_recognition.get_classifier('YOUR CLASSIFIER ID'),
# indent=2))
# with open(join(dirname(__file__), '../resources/car.jpg'), 'rb') as
# image_file:
# print(json.dumps(visual_recognition.update_classifier(
import json
from watson_developer_cloud import VisualRecognitionV3
visual_recognition = VisualRecognitionV3(
'2016-05-20',
api_key='6c9bd2eebc2ca826e9ef864eb8934fdd4c5d259a')
classifiers = visual_recognition.list_classifiers(verbose=True)
print(json.dumps(classifiers, indent=2))
# !!!!!!! NOTE: this service currently doesnt work since free trial of this service expired on the day of thesis submition
import json
from os.path import join, dirname
from watson_developer_cloud import VisualRecognitionV3
import sys
imagefile = str(sys.argv[1])
visual_recognition = VisualRecognitionV3('2016-05-20', api_key='93bc4d7f17a8d0bd011394b97e14b8be369b11ee')
with open(imagefile, 'rb') as img:
result = visual_recognition.classify(images_file=img,
threshold=0.75)
jsonresult = json.dumps(result,indent=2)
jsonarr = json.loads(jsonresult)
i=0
while True:
try:
label = jsonarr["images"][0]["classifiers"][0]["classes"][i]["class"]
score = jsonarr["images"][0]["classifiers"][0]["classes"][i]["score"]
print(label + ":" + str(score))
i=i+1
except IndexError:
break
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
import json
from io import StringIO
from PIL import Image
from watson_developer_cloud import VisualRecognitionV3
import matplotlib.pyplot as plt
import matplotlib.patches as patches
# Replace with your api key
visual_recognition = VisualRecognitionV3('2016-05-20', api_key='INSERT_API_KEY_HERE')
MAX_NUMBER_OF_BOXES = 10
MINIMUM_CONFIDENCE = 0.6
COLORS = ['b', 'g', 'r', 'c', 'm', 'y', 'b', 'w']
# What model to download.
MODEL_NAME = 'ssd_mobilenet_v1_coco_11_06_2017'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'
# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'
print('Downloading model... (This may take over 5 minutes)')
import json
from os.path import join, dirname
from os import environ
from watson_developer_cloud import VisualRecognitionV3
from face import show_webcam
test_url = 'http://www.talentedprofiles.com/wp-content/uploads/2016/10/25906514-600x600_t.png'
visual_recognition = VisualRecognitionV3(
'2016-05-20', api_key='aa3972acdbfb2a4df1cbbab7aaab2686755da530')
show_webcam()
#print(json.dumps(visual_recognition.create_collection("testcollect"), indent=2))
# with open(join(dirname(__file__), '../FullSizeRender.jpg'), 'rb')\
# as image_file:
# print(json.dumps(visual_recognition.add_image("testcollect_baf4a0", image_file, {'name' : 'Johnny Wu'}), indent = 2))
ok = input("Please input your name")
print("The image added should be in the resources folder")
with open(join(dirname(__file__), '../TartanHacks_S17/resources/vince.png'),
'rb') as image_file:
print(
json.dumps(visual_recognition.add_image("testcollect_baf4a0",
image_file, {'name': ok}),
indent=2))
def main(params):
visual_recognition = VisualRecognitionV3('2016-05-20', api_key=params["api_key"], url=params["url"])
return visual_recognition.classify(images_url=params["image_url"])
from SimpleCV import Color, Camera, Display
import json
from os.path import join, dirname
from os import environ
from watson_developer_cloud import VisualRecognitionV3
visual_recognition = VisualRecognitionV3(
'2016-05-20', api_key='30a8e58eb3163f8319ebea84ecd1b1b0027b6038')
cam = Camera()
img = cam.getImage()
img.save("/home/pi/tamara/snap.jpg")
with open(join(dirname(__file__), './snap.jpg'), 'rb') as image_file:
print(
json.dumps(visual_recognition.classify(images_file=image_file,
classifier_ids=[
'greenpepper_194357852',
'orange_2010321797',
'banana_760231312',
'default'
]),
indent=2))
#for ibm iot platform
import time
import sys
import ibmiotf.application
import ibmiotf.device
import random
# importing web browser to prepare for simulation
import webbrowser
#visual recognition
import json
from watson_developer_cloud import VisualRecognitionV3
visual_recognition = VisualRecognitionV3(
'2018-03-19', iam_apikey='KL11qNCtdmrm3mpty13OfABOvu2IVCIMHl2xV06fnFCm')
#Provide your IBM Watson Device Credentials
organization = "61f75s"
deviceType = "raspberrypi"
deviceId = "123456"
authMethod = "token"
authToken = "1234567890"
# Initialize GPIO
def myCommandCallback(cmd):
print("Command received: %s" % cmd.data)
#print(type(cmd.data))
i = cmd.data['cmd']
if i == 'alert':
import json
from watson_developer_cloud import VisualRecognitionV3
visual_recognition = VisualRecognitionV3(
'2019-05-7',
iam_apikey='L9k7HYkIssnQ-rrT7_oEWQUJAbyyzKSPv0n_VKfKA-M8')
test_url = 'http://192.168.1.8:8080/shot.jpg' #Contains the link to the IPWebcam stream
faces = visual_recognition.detect_faces(parameters=json.dumps({'url': test_url}))
#faces = visual_recognition.detect_faces(url).get_result()
print(json.dumps(faces, indent=2))
import json
from watson_developer_cloud import VisualRecognitionV3
visual_recognition = VisualRecognitionV3(
'2018-03-19', iam_apikey='*************************************')
with open('./fruitbowl.jpg', 'rb') as images_file:
classes = visual_recognition.classify(images_file,
classifier_ids=["default"
]).get_result()
print(json.dumps(classes, indent=2))
#expects python delete_classifier.py classifier_id
import sys
import json, argparse
from watson_developer_cloud import VisualRecognitionV3
parser = argparse.ArgumentParser(
description='Send Data for Modeling and Validation')
parser.add_argument('--k',
help='1 to use the IBM account',
type=int,
required=True)
parser.add_argument('--id',
help='classifier ID you wish to delete',
type=str,
required=True)
args = parser.parse_args()
free_key = '988d558c4a7e45a98f2aa9f1d52a66d5be30287d'
IBM_key = '2dc79bad5c8e2677012abe8fbff37d296cec070c'
if (args.k == 1):
key = IBM_key
else:
key = free_key
visual_recognition = VisualRecognitionV3('2016-05-20', api_key=key)
response = visual_recognition.delete_classifier(classifier_id=args.id)
print(json.dumps(response, indent=2))
import cognitive_face as CF
import sys
import json
from watson_developer_cloud import VisualRecognitionV3
# keys ibm e azure
ibm_key = 'u-wtKNFlyFRyCLQbTqr05wBPeZ3H7h-ZuY3hCC3a1NSc'
azure_key = '8943a700f3ca47d7bdd126b59a27f2d9'
sys.path.append('./')
# ibm: detecta idade e sexo
visual_recognition = VisualRecognitionV3('2018-03-19', iam_apikey=ibm_key)
with open('./foto.jpg', 'rb') as images_file:
classes = visual_recognition.detect_faces(
images_file, threshold='0.6', classifier_ids='default').get_result()
print('==========IBM: detecta idade e sexo ============')
print(json.dumps(classes, indent=2))
print('================================================\n\n')
# azure localização da face
azure_key = '8943a700f3ca47d7bdd126b59a27f2d9' # Replace with a valid subscription key (keeping the quotes in place).
CF.Key.set(azure_key)
BASE_URL = 'https://centralus.api.cognitive.microsoft.com/face/v1.0/' # Replace with your regional Base URL
CF.BaseUrl.set(BASE_URL)
# You can use this example JPG or replace the URL below with your own URL to a JPEG image.
img_url = './foto.jpg'
faces = CF.face.detect(img_url)
print('==============Azure: localizacao da face=============')
import json
from watson_developer_cloud import VisualRecognitionV3
from Xlib import display, X
from PIL import Image #PIL
import time
print("HE")
visual_recognition = VisualRecognitionV3(
'2018-03-19', api_key='3995db77bd70aa498157544096c84c5741b30668')
W, H = 800, 650
dsp = display.Display()
root = dsp.screen().root
x = 0
while x < 2:
raw = root.get_image(200, 200, W, H, X.ZPixmap, 0xffffffff)
image = Image.frombytes("RGB", (W, H), raw.data, "raw", "BGRX")
time.sleep(.5)
classes = visual_recognition.classify(image,
threshold='0.6',
classifier_ids='humans_1546902740')
x += 1
print(json.dumps(classes, indent=2))
import json
from watson_developer_cloud import VisualRecognitionV3
import cv2
import os
# connecting to the IBM visual recognition instance, insert version and ibm_key respectively below
visual_recognition = VisualRecognitionV3(
'2018-03-19',
iam_apikey=os.environ.get('IBMBETHKEY'))
# uncomment this if you already have a video file
# vidcap = cv2.VideoCapture('output.avi')
# otherwise capture form video cam
cap = cv2.VideoCapture(0)
vidcap = cap
# loop through the video if still recording
while(True):
# ret, frame = cap.read()
# # Display the resulting frame
# cv2.imshow('black and white',frame)
def getFrame(sec):
vidcap = cap
vidcap.set(cv2.CAP_PROP_POS_MSEC,sec*1000)
hasFrames,image = vidcap.read()
if hasFrames:
cv2.imwrite("image"+str(count)+".jpg", image) # save frame as JPG file
return hasFrames
# -*- coding: utf-8 -*-
# Form implementation generated from reading ui file 'AvO.ui'
#
# Created by: PyQt5 UI code generator 5.11.2
#
# WARNING! All changes made in this file will be lost!
from PyQt5 import QtCore, QtGui, QtWidgets
import pandas as pd
from watson_developer_cloud import VisualRecognitionV3
from PyQt5 import QtCore, QtGui, QtWidgets
from PyQt5.QtCore import QSize
from PyQt5.QtGui import QImage, QPalette, QBrush
visual_recognition = VisualRecognitionV3(version='{version}',
iam_apikey='{apikey}')
import json
import os
from watson_developer_cloud import VisualRecognitionV3
visual_recognition = VisualRecognitionV3('2018-03-19',
iam_apikey='Enter_your_apikey')
class Ui_MainWindow(QtWidgets.QMainWindow):
def setupUi(self, MainWindow):
MainWindow.setObjectName("MainWindow")
MainWindow.resize(800, 600)
self.centralwidget = QtWidgets.QWidget(MainWindow)
self.centralwidget.setObjectName("centralwidget")
self.frame = QtWidgets.QFrame(self.centralwidget)
self.frame.setGeometry(QtCore.QRect(0, 0, 791, 571))
import json
from watson_developer_cloud import VisualRecognitionV3
visual_recognition = VisualRecognitionV3(
'2018-03-19', iam_apikey='GfBGcjYPrd-38OXXTbV1uPjKZ5Xp4o-20av0onxqqUIF')
# url = 'https://watson-developer-cloud.github.io/doc-tutorial-downloads/visual-recognition/640px-IBM_VGA_90X8941_on_PS55.jpg'
url = "https://upload.wikimedia.org/wikipedia/commons/thumb/5/5d/Leopard_2_A7.JPG/220px-Leopard_2_A7.JPG"
classes_result = visual_recognition.classify(url=url).get_result()
print(json.dumps(classes_result, indent=2))
maxscore, maxind = 0, 0
for i in range(len(classes_result["images"][0]["classifiers"][0]["classes"])):
if classes_result["images"][0]["classifiers"][0]["classes"][i][
"score"] > maxscore:
maxscore = classes_result["images"][0]["classifiers"][0]["classes"][i][
"score"]
maxind = i
print(classes_result["images"][0]["classifiers"][0]["classes"][maxind])
from watson_developer_cloud import VisualRecognitionV3
import json
visual_recognition = VisualRecognitionV3(
version='2018-03-19',
iam_apikey='yxu1EPLR_Ry65MXOkWItzzA4VSDhghPSKLt07UIxAD8F')
with open('./banana1.jpg', 'rb') as images_file:
classes = visual_recognition.classify(
images_file,
threshold='0.6',
classifier_ids='DefaultCustomModel_793529682').get_result()
print(json.dumps(classes, indent=2))
import json
from watson_developer_cloud import VisualRecognitionV3
visual_recognition = VisualRecognitionV3(
'2018-03-19',
iam_apikey='znv5zrsn6pxQsFGAOKtqMw6GJrIYz7XSblKEuN-Kih2d')
with open('./images/images.zip', 'rb') as images_file:
classes = visual_recognition.classify(
images_file,
#classifier_ids=["food"]).get_result()
classifier_ids=["default"]).get_result()
#print(json.dumps(classes, indent=2))
#with open('./response.json', 'w') as outfile:
# json.dump(classes, outfile)
with open("./response.json", "w") as outfile:
json.dump(classes, outfile, indent=4, sort_keys=True)
from watson_developer_cloud import VisualRecognitionV3, WatsonApiException
import glob
import cv2
import time
# KEY = open("../apikey.ini").read()
# If service instance provides IAM API key authentication
service = VisualRecognitionV3(
"2018-03-19",
# url is optional, and defaults to the URL below.
url="https://gateway.watsonplatform.net/visual-recognition/api",
iam_apikey="{apikey}",
)
# 画像のパスを投げて顔のjsonデータを返す
def detect_face(face_path):
try:
with open(face_path, "rb") as image_file:
return service.detect_faces(images_file=image_file).get_result()
# return json.dumps(face_result, indent=2)
except WatsonApiException as ex:
print(ex)
# 認識したjsonを投げて切り取った画像をフォルダに分けて配置する
def trimming(img_path, json_data):
try:
# ファイル名の取得
file_name = img_path.replace("./../image/original/", "")
image = json_data["images"][0]
###############################################
# author: Gilton Bosco
# date: 14 July 2020
# twitter: @giltwizy
###############################################
import os
from dotenv import load_dotenv
import json
from watson_developer_cloud import VisualRecognitionV3
#loading the .env file from the root directory
load_dotenv()
#getting API key from the .env file
my_api_key = os.getenv('api_key')
visual_recognition = VisualRecognitionV3(
'2018-03-19',
my_api_key)
#getting the image from the root directory
with open('./testimage.jpg', 'rb') as images_file:
classes = visual_recognition.classify(
images_file,
threshold='0.6',
classifier_ids='default').get_result()
print(json.dumps(classes, indent=2))
if counter != 0:
commentSentiment = total / counter
sentimentComments[str(submission)] = commentSentiment
else:
sentimentComments[str(submission)] = 0.5
for key in sentimentComments:
print(key, sentimentComments[key])
f.close()
objectSent = dict()
objectOccur = dict()
objectIDs = dict()
imageObjects = dict()
visual_recognition = VisualRecognitionV3(
'2016-05-20', api_key='8d7aced8efa9ce11cca985d203dce5989cc20148')
for key in submissionUrls:
hashmap = dict()
listOfClasses = list()
wholejson = (visual_recognition.classify(images_url=submissionUrls[key]))
images = (json.dumps(wholejson['images'], indent=2)).splitlines()
print("Identifying objects in " + submissionUrls[key])
for line in images:
if "\"class\":" in line:
line = line.replace(",", "")
line = line.replace("\"class\": \"", "")
line = line.replace("\"", "")
line = line.strip()
listOfClasses.append(line)
# print(line)
if line in objectOccur:
from __future__ import print_function
import json
from os.path import join, dirname
from watson_developer_cloud import VisualRecognitionV3, WatsonApiException
test_url = 'https://www.ibm.com/ibm/ginni/images' \
'/ginni_bio_780x981_v4_03162016.jpg'
visual_recognition = VisualRecognitionV3(
'2016-05-20', api_key='kjdV1UXXqdNQRfuQG-DC08BgffvabZEZlgBURQdGzMkn')
# with open(join(dirname(__file__), '../resources/cars.zip'), 'rb') as cars, \
# open(join(dirname(__file__), '../resources/trucks.zip'), 'rb') as
# trucks:
# print(json.dumps(visual_recognition.create_classifier('Cars vs Trucks',
# cars_positive_examples=cars,
#
# negative_examples=trucks), indent=2))
car_path = join(dirname(__file__), '../resources/cars.zip')
with open(car_path, 'rb') as images_file:
parameters = json.dumps({'threshold': 0.1, 'classifier_ids': ['default']})
car_results = visual_recognition.classify(images_file=images_file,
parameters=parameters)
print(json.dumps(car_results, indent=2))
# Example with no deprecated
try:
with open(car_path, 'rb') as images_file:
car_results = visual_recognition.classify(images_file=images_file,
threshold='0.1',
from __future__ import print_function
import json
from os.path import abspath
from watson_developer_cloud import VisualRecognitionV3, WatsonApiException
import os
visual_recognition = VisualRecognitionV3(
'2018-03-19',
url='https://gateway.watsonplatform.net/visual-recognition/api',
iam_apikey='_rTi9ExzLh2F_cNt6NRksfQz_sAJ7NhdlXchff5poiF0')
def visRec():
clothes = []
filelist = os.listdir("assets/images/")
thinking = 0
for i in filelist:
if thinking == 5:
print("...")
thinking = 0
else:
thinking += 1
if i.endswith(".jpg") or i.endswith(".jpeg"):
with open("assets/images/" + i, 'rb') as images_file:
classes = visual_recognition.classify(
images_file,
threshold='0.5',
classifier_ids='DefaultCustomModel_2095219532').get_result()
thisItem = classes['images'][0].get('classifiers')[0].get('classes')
if len(thisItem) > 1:
import json
from watson_developer_cloud import VisualRecognitionV3
visual_recognition = VisualRecognitionV3(
version='2018-09-16',
api_key='rOzTu6mBpvPgKP96UCVUZ-1m_4CrklQXUqRK1_HkbxXR')
with open('./fruitbowl.jpg', 'rb') as images_file:
classes = visual_recognition.classify(images_file,
threshold='0.6',
classifier_ids='default')
print(json.dumps(classes, indent=2))
