I'm trying to convert tiff images into jpg format and use it later in opencv. It is working fine in my local system but when I am executing it over linux server which is not connected to internet it is getting failed while saving the Image object as jpg format.
I'm using python3.8 and had installed all the libraries and its dependencies using wheel files over server using pip.
Here is the piece of code:
import PIL
import cv2
def face_detect(sourceImagepath1, processedFileName, imagename, pdfname):
temp_path = TEMP_PATH
processed_path = PROCESSED_PATH
misc_path = MISC_PATH
# cascade file path1
cascpath1 = misc_path + 'frontalface_cascade.xml'
# Create harr cascade
faceCascade = cv2.CascadeClassifier(cascpath1)
# Read image with PIL
image_pil = Image.open(sourceImagepath1)
# Save image in jpg format
image_pil.save(temp_path + processedFileName + '.jpg')
# Read image with opencv
image_cv = cv2.imread(temp_path + processedFileName + '.jpg')
# Convert image into grayscale
image_gray = cv2.cvtColor(image_cv, cv2.COLOR_BGR2GRAY)
# Detect faces in the image
face = faceCascade.detectMultiScale(
image_gray,
scaleFactor=1.3,
minNeighbors=5,
minSize=(30, 30)
# flags = cv2.CASCADE_SCALE_IMAGE
)
if len(face) > 0:
# Coordinates based on auto-face detection
x, y, w, h = face[0][0], face[0][1], face[0][2], face[0][3]
crop_image = image_pil.crop([x - 20, y - 30, x + w + 40, y + h + 60])
crop_image.save(processed_path + imagename)
# Save tif file as pdf
image_pil.save(processed_path + pdfname, save_all=True)
# Close image object
image_pil.close()
return len(face)
Here TEMP_PATH,PROCESSED_PATH,MISC_PATH are global variables of syntax like '/Users/user/Documents/Temp/'. I'm getting error on line:
image_pil.save(temp_path + processedFileName + '.jpg')
Below is the error i'm getting when executing the file
Traceback (most recent call last):
File "*path_from_root_directory*/PYTHON_SCRIPTS/Script/staging.py", line 363, in <module>
auto_face_count = face_detect(sourceImagepath1, processedFileName, imagename, pdfname)
File "*path_from_root_directory*/PYTHON_SCRIPTS/Script/staging.py", line 71, in greyScaleCheck
image_pil.save(temp_path + processedFileName + '.jpg')
File "*path_from_root_directory*/python3.8/site-packages/PIL/Image.py", line 2201, in save
self._ensure_mutable()
File "*path_from_root_directory*/python3.8/site-packages/PIL/Image.py", line 624, in _ensure_mutable
self._copy()
File "*path_from_root_directory*/python3.8/site-packages/PIL/Image.py", line 617, in _copy
self.load()
File "*path_from_root_directory*/python3.8/site-packages/PIL/TiffImagePlugin.py", line 1122, in load
return self._load_libtiff()
File "*path_from_root_directory*/python3.8/site-packages/PIL/TiffImagePlugin.py", line 1226, in _load_libtiff
raise OSError(err)
OSError: -2
I have provided full privileges to python directory and its sub-directories/files. Anyone have any idea why I'm getting this error ?
I want to use object detection using tensorflow lite in order to detect a clear face or a covered face where the statement "door opens" is printed when a clear face is detected. I could run this code smoothly previously but later after rebooting raspberry pi 4, although the tensorflow lite runtime is initialized, the raspberry pi 4 disconnects with the ssh completely. The following is the code:
######## Webcam Object Detection Using Tensorflow-trained Classifier #########
#
# Author: Evan Juras
# Date: 10/27/19
# Description:
# This program uses a TensorFlow Lite model to perform object detection on a live webcam
# feed. It draws boxes and scores around the objects of interest in each frame from the
# webcam. To improve FPS, the webcam object runs in a separate thread from the main program.
# This script will work with either a Picamera or regular USB webcam.
#
# This code is based off the TensorFlow Lite image classification example at:
# https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/examples/python/label_image.py
#
# I added my own method of drawing boxes and labels using OpenCV.
# Import packages
import os
import argparse
import cv2
import numpy as np
import sys
import time
from threading import Thread
import importlib.util
import simpleaudio as sa
# Define VideoStream class to handle streaming of video from webcam in separate processing thread
# Source - Adrian Rosebrock, PyImageSearch: https://www.pyimagesearch.com/2015/12/28/increasing-raspberry-pi-fps-with-python-and-opencv/
class VideoStream:
"""Camera object that controls video streaming from the Picamera"""
def __init__(self,resolution=(640,480),framerate=30):
# Initialize the PiCamera and the camera image stream
self.stream = cv2.VideoCapture(0)
ret = self.stream.set(cv2.CAP_PROP_FOURCC, cv2.VideoWriter_fourcc(*'MJPG'))
ret = self.stream.set(3,resolution[0])
ret = self.stream.set(4,resolution[1])
# Read first frame from the stream
(self.grabbed, self.frame) = self.stream.read()
# Variable to control when the camera is stopped
self.stopped = False
def start(self):
# Start the thread that reads frames from the video stream
Thread(target=self.update,args=()).start()
return self
def update(self):
# Keep looping indefinitely until the thread is stopped
while True:
# If the camera is stopped, stop the thread
if self.stopped:
# Close camera resources
self.stream.release()
return
# Otherwise, grab the next frame from the stream
(self.grabbed, self.frame) = self.stream.read()
def read(self):
# Return the most recent frame
return self.frame
def stop(self):
# Indicate that the camera and thread should be stopped
self.stopped = True
# Define and parse input arguments
parser = argparse.ArgumentParser()
parser.add_argument('--modeldir', help='Folder the .tflite file is located in',
required=True)
parser.add_argument('--graph', help='Name of the .tflite file, if different than detect.tflite',
default='masktracker.tflite')
parser.add_argument('--labels', help='Name of the labelmap file, if different than labelmap.txt',
default='facelabelmap.txt')
parser.add_argument('--threshold', help='Minimum confidence threshold for displaying detected objects',
default=0.5)
parser.add_argument('--resolution', help='Desired webcam resolution in WxH. If the webcam does not support the resolution entered, errors may occur.',
default='640x480')
parser.add_argument('--edgetpu', help='Use Coral Edge TPU Accelerator to speed up detection',
action='store_true')
args = parser.parse_args()
MODEL_NAME = args.modeldir
GRAPH_NAME = args.graph
LABELMAP_NAME = args.labels
min_conf_threshold = float(args.threshold)
resW, resH = args.resolution.split('x')
imW, imH = int(resW), int(resH)
use_TPU = args.edgetpu
# Import TensorFlow libraries
# If tflite_runtime is installed, import interpreter from tflite_runtime, else import from regular tensorflow
# If using Coral Edge TPU, import the load_delegate library
pkg = importlib.util.find_spec('tflite_runtime')
if pkg:
from tflite_runtime.interpreter import Interpreter
if use_TPU:
from tflite_runtime.interpreter import load_delegate
else:
from tensorflow.lite.python.interpreter import Interpreter
if use_TPU:
from tensorflow.lite.python.interpreter import load_delegate
# If using Edge TPU, assign filename for Edge TPU model
if use_TPU:
# If user has specified the name of the .tflite file, use that name, otherwise use default 'edgetpu.tflite'
if (GRAPH_NAME == 'masktracker.tflite'):
GRAPH_NAME = 'edgetpu.tflite'
# Get path to current working directory
CWD_PATH = os.getcwd()
# Path to .tflite file, which contains the model that is used for object detection
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,GRAPH_NAME)
# Path to label map file
PATH_TO_LABELS = os.path.join(CWD_PATH,MODEL_NAME,LABELMAP_NAME)
# Load the label map
with open(PATH_TO_LABELS, 'r') as f:
labels = [line.strip() for line in f.readlines()]
# Have to do a weird fix for label map if using the COCO "starter model" from
# https://www.tensorflow.org/lite/models/object_detection/overview
# First label is '???', which has to be removed.
if labels[0] == '???':
del(labels[0])
# Load the Tensorflow Lite model.
# If using Edge TPU, use special load_delegate argument
if use_TPU:
interpreter = Interpreter(model_path=PATH_TO_CKPT,
experimental_delegates=[load_delegate('libedgetpu.so.1.0')])
print(PATH_TO_CKPT)
else:
interpreter = Interpreter(model_path=PATH_TO_CKPT)
interpreter.allocate_tensors()
# Get model details
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
height = input_details[0]['shape'][1]
width = input_details[0]['shape'][2]
floating_model = (input_details[0]['dtype'] == np.float32)
input_mean = 127.5
input_std = 127.5
# Initialize frame rate calculation
frame_rate_calc = 1
freq = cv2.getTickFrequency()
global image_capture
image_capture = 0
# Initialize video stream
videostream = VideoStream(resolution=(imW,imH),framerate=30).start()
time.sleep(1)
#for frame1 in camera.capture_continuous(rawCapture, format="bgr",use_video_port=True):
while True:
# Start timer (for calculating frame rate)
t1 = cv2.getTickCount()
# Grab frame from video stream
frame1 = videostream.read()
# Acquire frame and resize to expected shape [1xHxWx3]
frame = frame1.copy()
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
frame_resized = cv2.resize(frame_rgb, (width, height))
input_data = np.expand_dims(frame_resized, axis=0)
# Normalize pixel values if using a floating model (i.e. if model is non-quantized)
if floating_model:
input_data = (np.float32(input_data) - input_mean) / input_std
# Perform the actual detection by running the model with the image as input
interpreter.set_tensor(input_details[0]['index'],input_data)
interpreter.invoke()
# Retrieve detection results
boxes = interpreter.get_tensor(output_details[0]['index'])[0] # Bounding box coordinates of detected objects
classes = interpreter.get_tensor(output_details[1]['index'])[0] # Class index of detected objects
scores = interpreter.get_tensor(output_details[2]['index'])[0] # Confidence of detected objects
#num = interpreter.get_tensor(output_details[3]['index'])[0] # Total number of detected objects (inaccurate and not needed)
# Loop over all detections and draw detection box if confidence is above minimum threshold
for i in range(len(scores)):
if ((scores[i] > min_conf_threshold) and (scores[i] <= 1.0)):
# Get bounding box coordinates and draw box
# Interpreter can return coordinates that are outside of image dimensions, need to force them to be within image using max() and min()
ymin = int(max(1,(boxes[i][0] * imH)))
xmin = int(max(1,(boxes[i][1] * imW)))
ymax = int(min(imH,(boxes[i][2] * imH)))
xmax = int(min(imW,(boxes[i][3] * imW)))
# Draw label
object_name = labels[int(classes[i])] # Look up object name from "labels" array using class index
if (object_name=="face unclear" ):
color = (0, 255, 0)
cv2.rectangle(frame, (xmin,ymin), (xmax,ymax),color, 2)
print("Face Covered: Door Not Opened")
if(image_capture == 0):
path = r'/home/pi/Desktop/tflite_1/photographs'
date_string = time.strftime("%Y-%m-%d_%H%M%S")
#print(date_string)
cv2.imwrite(os.path.join(path, (date_string + ".jpg")),frame)
#cv2.imshow("Photograph",frame)
#mp3File = input(alert_audio.mp3)
print("Photo Taken")
#w_object = sa.WaveObject.from_wave_file('alert_audio.wav')
#p_object = w_object.play()
#p_object.wait_done()
image_capture = 1
else:
color = (0, 0, 255)
cv2.rectangle(frame, (xmin,ymin), (xmax,ymax),color, 2)
print("Face Clear: Door Opened")
image_capture = 0
#cv2.rectangle(frame, (xmin,ymin), (xmax,ymax),color, 2)
#image = np.asarray(ImageGrab.grab())
label = '%s: %d%%' % (object_name, int(scores[i]*100)) # Example: 'person: 72%'
labelSize, baseLine = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.7, 2) # Get font size
label_ymin = max(ymin, labelSize[1] + 10) # Make sure not to draw label too close to top of window
cv2.rectangle(frame, (xmin, label_ymin-labelSize[1]-10), (xmin+labelSize[0], label_ymin+baseLine-10), (255, 255, 255), cv2.FILLED) # Draw white box to put label text in
cv2.putText(frame, label, (xmin, label_ymin-7), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 0), 2) # Draw label text
if ((scores[0] < min_conf_threshold)):
cv2.putText(frame,"No Face Detected",(260,260),
cv2.FONT_HERSHEY_SIMPLEX, 0.8, color=(255,0,0))
print("No Face Detected")
image_capture = 0
# Draw framerate in corner of frame
cv2.putText(frame,'FPS: {0:.2f}'.format(frame_rate_calc),(30,50),cv2.FONT_HERSHEY_SIMPLEX,1,(255,255,0),2,cv2.LINE_AA)
# All the results have been drawn on the frame, so it's time to display it.
cv2.imshow('Object detector', frame)
# Calculate framerate
t2 = cv2.getTickCount()
time1 = (t2-t1)/freq
frame_rate_calc= 1/time1
# Press 'q' to quit
if cv2.waitKey(1) == ord('q'):
break
# Clean up
cv2.destroyAllWindows()
videostream.stop()
Any help is appreciated.
Regards,
MD
I'm using freenect2-python to read frames from kinectv2. Following is my code:
from freenect2 import Device, FrameType
import cv2
import numpy as np
def callback(type_, frame):
print(f'{type_}, {frame.format}')
if type_ is FrameType.Color: # FrameFormat.BGRX
rgb = frame.to_array().astype(np.uint8)
cv2.imshow('rgb', rgb[:,:,0:3])
device = Device()
while True:
device.start(callback)
if cv2.waitKey(1) & 0xFF == ord('q'):
device.stop()
break
The color frame format is FrameFormat.BGRX, so I'm taking the first 3 channels to show the image. But it shows a blank black window.
I used PIL but it opens a new window for each frame it receives. Is there a way to show frames in the same window in PIL?
The cv2.imshow couldn't display anything because it was continuously getting updated with a new frame. I added cv2.waitkey(100) after cv2.imshow and it worked.
def callback(type_, frame):
print(f'{type_}, {frame.format}')
if type_ is FrameType.Color: # FrameFormat.BGRX
rgb = frame.to_array().astype(np.uint8)
cv2.imshow('rgb', rgb[:,:,0:3])
# added the following line of code
cv2.imshow(100)
I want to crop and resize multiple images in many sub-directories. The code works if the images are in the same directory, but fails to read from other directories.
I have tried using os.walk() module. It successfully iterate the files from all subdirectories, but the pillow's Image.open() function fails to access the images and thereby displaying error: "image.." not found.
import os
from PIL import Image
for dirpath, dirnames, files in os.walk('.'):
for filename in files:
t = filename.split(".")
ext = t[-1]
if ext in ["jpg"]:
print(filename)
coords = (500, 250, 810,720)
image_obj = Image.open(filename)
cropped_image = image_obj.crop(coords)
resized_image =cropped_image.resize([227,227])
# name = "./data2" + str(i) +".jpg"
resized_image.save("new" + filename)
I expect the code to recursively crop and resize the images in all the sub-directories. The following error occurred.
frame0.jpg
Traceback (most recent call last):
File "........./data2/cropitall.py", line 18, in <module>
image_obj = Image.open(filename) #path of image to be cropped
File "C:\Python36\lib\site-packages\PIL\Image.py", line 2652, in open
fp = builtins.open(filename, "rb")
FileNotFoundError: [Errno 2] No such file or directory: 'frame0.jpg'
Process finished with exit code 1
To open the image you need the entire path to the file, not just file name.
Instead of
image_obj = Image.open(filename)
do
path = os.path.join(dirpath, filename)
image_obj = Image.open(path)
I used a relatively small image (44pixel tall) and scaled it up to have a pixel art look. I tried to change the filtering mode to nearest so the anti-aliasing would disappear but it didn't. It appears with blurry edges. I tried the same with a background getting the same result.
let myNode = SKSpriteNode()
class GameScene: SKScene {
func makeNode() {
myNode.position = CGPoint(x: self.frame.size.width/2, y: self.frame.size.height/2)
myNode.size = CGSize(width: 200, height: 200)
myNode.texture = SKTexture(imageNamed: "image")
myNode.texture!.filteringMode = .Nearest
return self.addChild(myNode)
}
}
override func didMoveToView(view: SKView) {
makeNode()
}
UPDATE:
SKTexture nearest filtering mode is now working in Xcode 7 GM. No need to manually scale images as I've suggested below.
I am experiencing this same problem in Xcode 7 beta 5 with beta iOS 9 ; the Nearest filtering mode is seemingly ignored. In my project, scaling with nearest-neighbor scaling was previously working in Xcode 6 on iOS 8.
In the event that the bug is not resolved before the final release of iOS 9 I am pre-scaling images before I place them in their respective atlases.
To do this I wrote a simple python script to recursively find png files and scale them using imagmagick.
If you don’t have imagemagick installed, you can install it using macports like so:
sudo port install ImageMagick
If you have homebrew it looks like this:
brew install imagemagick
I just place this script (below) in a file called imgscaler.py within the directory above my atlas files (which I want to scale by 400% in my case) and kick it off from the terminal:
python imgscaler.py
The script looks like this:
import subprocess
import os
import sys
import fnmatch
def main():
execution_folder_name = os.getcwd()
file_extension_name = "png"
#
# Collect names of files that will be manipulated
matches = []
for root, dirNames, fileNames in os.walk(execution_folder_name):
for filename in fnmatch.filter(fileNames, '*.' + file_extension_name):
full_name = os.path.join(root, filename)
matches.append(full_name)
scale_percentage = "400"
if not __query_yes_no("This script will scale images by " + scale_percentage + "% recursively from directory " + execution_folder_name + ". Proceed?"):
return
#
# Scale the images
for match in matches:
execution_str = "convert " + match + " -interpolate Nearest -filter point -resize " + scale_percentage + "% " + match + "\n"
sys.stdout.write(execution_str)
__run_command(execution_str)
def __run_command(input_cmd):
"""Runs a command on the terminal, and returns the output in a string array.
"""
process = subprocess.Popen(input_cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, shell=True)
output = []
while True:
line = process.stdout.readline()
if line != '':
output.append(line)
else:
break
return output
def __query_yes_no(question, default="yes"):
"""Asks a yes or no question, returns a true is answered "yes".
"""
valid = {"yes": True, "y": True, "ye": True,
"no": False, "n": False}
if default is None:
prompt = " [y/n] "
elif default == "yes":
prompt = " [Y/n] "
elif default == "no":
prompt = " [y/N] "
else:
raise ValueError("invalid default answer: '%s'" % default)
while True:
sys.stdout.write(question + prompt)
sys.stdout.flush()
choice = raw_input().lower()
if default is not None and choice == '':
sys.stdout.write(default)
sys.stdout.write('\n')
sys.stdout.flush()
return valid[default]
elif choice in valid:
sys.stdout.write(choice)
sys.stdout.write('\n')
sys.stdout.flush()
return valid[choice]
else:
sys.stdout.write("Please respond with 'yes' or 'no' (or 'y' or 'n').\n")
sys.stdout.flush()
main()
Change scale_percentage to whatever percentage you want to scale by.
BTW, I am guessing this scaling issue will eventually get resolved. I’m currently updating my code with this assumption in mind. This is just a bandaid in the event the fix to nearest-neighbor scaling in SpriteKit arrives later than iOS 9.0.
This is a bug in Xcode7 beta / iOS9. It works if you use Xcode 6.