在 tkinter 上需要有关对象检测程序的帮助
Need help on tkinter about object detection program
我正在尝试制作一个 tkinter window 用户按下一个按钮，然后用户输入一个 img 供程序扫描 it.What 我想要的是图像出现在 tkinter 上window 并且程序不会结束而是继续所以用户输入另一个 image.My 输出是这个：
tk window 被破坏，所有显示的是 output.Also 当文件对话框打开并且用户没有输入图像时 tkwindow 也关闭。
代码如下：
import numpy as np
import argparse
import cv2
import tkinter as tk
from tkinter import filedialog
def search_image():
global image1
image1 = filedialog.askopenfilename()
root.destroy()
return image1
root = tk.Tk()
root.geometry('1200x900-100-100')
root.resizable(False, False)
root.title('YOLO')
w = tk.Label(root, text = "IMAGE-DETECTION-YOLO", font = "Arial 36", bg ='lightgray', width = 900)
w.pack()
button = tk.Button(root, text = "CHOOSE", font = "Arial 36", command = search_image)
button.pack()
root.mainloop()
#######after that is code for the detection model############################
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", default=image1,
help="path to input image")
ap.add_argument("-p", "--prototxt", default="MobileNetSSD_deploy.prototxt.txt",
help="path to Caffe 'deploy' prototxt file")
ap.add_argument("-m", "--model", default="MobileNetSSD_deploy.caffemodel",
help="path to Caffe pre-trained model")
ap.add_argument("-c", "--confidence", type=float, default=0.2,
help="minimum probability to filter weak detections")
args = vars(ap.parse_args())
# initialize the list of class labels MobileNet SSD was trained to
# detect, then generate a set of bounding box colors for each class
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
"dog", "horse", "motorbike", "person", "pottedplant", "sheep",
"sofa", "train", "tvmonitor"]
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))
# load our serialized model from disk
print("[INFO] loading model...")
model = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])
# load the input image and construct an input blob for the image
# by resizing to a fixed 300x300 pixels and then normalizing it
# (note: normalization is done via the authors of the MobileNet SSD
# implementation)
image = cv2.imread(args["image"])
(h, w) = image.shape[:2]
blob = cv2.dnn.blobFromImage(cv2.resize(image, (300, 300)), 0.007843, (300, 300), 127.5)
# pass the blob through the network and obtain the detections and
# predictions
print("[INFO] computing object detections...")
model.setInput(blob)
detections = model.forward()
# loop over the detections
for i in np.arange(0, detections.shape[2]):
# extract the confidence (i.e., probability) associated with the
# prediction
confidence = detections[0, 0, i, 2]
# filter out weak detections by ensuring the `confidence` is
# greater than the minimum confidence
if confidence > args["confidence"]:
# extract the index of the class label from the `detections`,
# then compute the (x, y)-coordinates of the bounding box for
# the object
idx = int(detections[0, 0, i, 1])
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
# display the prediction
label = "{}: {:.2f}%".format(CLASSES[idx], confidence * 100)
print("[INFO] {}".format(label))
cv2.rectangle(image, (startX, startY), (endX, endY),
COLORS[idx], 2)
y = startY - 15 if startY - 15 > 15 else startY + 15
cv2.putText(image, label, (startX, y),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)
# show the output image
cv2.imshow("Output", image)
cv2.imwrite('image_detected.jpg',image)
cv2.waitKey(0)
您应该将检测放在一个函数中，并在选择图像文件后调用该函数。同样使用 Pillow 模块转换结果图像并使用 Label.
显示结果图像
import numpy as np
import argparse
import cv2
import tkinter as tk
from tkinter import filedialog
from PIL import Image, ImageTk
def detect_objects(image1):
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", default=image1,
help="path to input image")
ap.add_argument("-p", "--prototxt", default="MobileNetSSD_deploy.prototxt.txt",
help="path to Caffe 'deploy' prototxt file")
ap.add_argument("-m", "--model", default="MobileNetSSD_deploy.caffemodel",
help="path to Caffe pre-trained model")
ap.add_argument("-c", "--confidence", type=float, default=0.2,
help="minimum probability to filter weak detections")
args = vars(ap.parse_args())
# initialize the list of class labels MobileNet SSD was trained to
# detect, then generate a set of bounding box colors for each class
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
"dog", "horse", "motorbike", "person", "pottedplant", "sheep",
"sofa", "train", "tvmonitor"]
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))
# load our serialized model from disk
print("[INFO] loading model...")
model = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])
# load the input image and construct an input blob for the image
# by resizing to a fixed 300x300 pixels and then normalizing it
# (note: normalization is done via the authors of the MobileNet SSD
# implementation)
image = cv2.imread(args["image"])
(h, w) = image.shape[:2]
blob = cv2.dnn.blobFromImage(cv2.resize(image, (300, 300)), 0.007843, (300, 300), 127.5)
# pass the blob through the network and obtain the detections and
# predictions
print("[INFO] computing object detections...")
model.setInput(blob)
detections = model.forward()
# loop over the detections
for i in np.arange(0, detections.shape[2]):
# extract the confidence (i.e., probability) associated with the
# prediction
confidence = detections[0, 0, i, 2]
# filter out weak detections by ensuring the `confidence` is
# greater than the minimum confidence
if confidence > args["confidence"]:
# extract the index of the class label from the `detections`,
# then compute the (x, y)-coordinates of the bounding box for
# the object
idx = int(detections[0, 0, i, 1])
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
# display the prediction
label = "{}: {:.2f}%".format(CLASSES[idx], confidence * 100)
print("[INFO] {}".format(label))
cv2.rectangle(image, (startX, startY), (endX, endY),
COLORS[idx], 2)
y = startY - 15 if startY - 15 > 15 else startY + 15
cv2.putText(image, label, (startX, y),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)
# show the output image
image = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
tkimage = ImageTk.PhotoImage(image)
result.config(image=tkimage)
result.iamge = tkimage
def search_image():
image1 = filedialog.askopenfilename()
if image1:
detect_objects(image1)
root = tk.Tk()
root.geometry('1200x900-100-100')
root.resizable(False, False)
root.title('YOLO')
w = tk.Label(root, text = "IMAGE-DETECTION-YOLO", font = "Arial 36", bg ='lightgray', width = 900)
w.pack()
button = tk.Button(root, text = "CHOOSE", font = "Arial 36", command = search_image)
button.pack()
# label to show the result
result = tk.Label(root)
result.pack()
root.mainloop()
我正在尝试制作一个 tkinter window 用户按下一个按钮，然后用户输入一个 img 供程序扫描 it.What 我想要的是图像出现在 tkinter 上window 并且程序不会结束而是继续所以用户输入另一个 image.My 输出是这个：
tk window 被破坏，所有显示的是 output.Also 当文件对话框打开并且用户没有输入图像时 tkwindow 也关闭。
代码如下：
import numpy as np
import argparse
import cv2
import tkinter as tk
from tkinter import filedialog
def search_image():
global image1
image1 = filedialog.askopenfilename()
root.destroy()
return image1
root = tk.Tk()
root.geometry('1200x900-100-100')
root.resizable(False, False)
root.title('YOLO')
w = tk.Label(root, text = "IMAGE-DETECTION-YOLO", font = "Arial 36", bg ='lightgray', width = 900)
w.pack()
button = tk.Button(root, text = "CHOOSE", font = "Arial 36", command = search_image)
button.pack()
root.mainloop()
#######after that is code for the detection model############################
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", default=image1,
help="path to input image")
ap.add_argument("-p", "--prototxt", default="MobileNetSSD_deploy.prototxt.txt",
help="path to Caffe 'deploy' prototxt file")
ap.add_argument("-m", "--model", default="MobileNetSSD_deploy.caffemodel",
help="path to Caffe pre-trained model")
ap.add_argument("-c", "--confidence", type=float, default=0.2,
help="minimum probability to filter weak detections")
args = vars(ap.parse_args())
# initialize the list of class labels MobileNet SSD was trained to
# detect, then generate a set of bounding box colors for each class
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
"dog", "horse", "motorbike", "person", "pottedplant", "sheep",
"sofa", "train", "tvmonitor"]
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))
# load our serialized model from disk
print("[INFO] loading model...")
model = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])
# load the input image and construct an input blob for the image
# by resizing to a fixed 300x300 pixels and then normalizing it
# (note: normalization is done via the authors of the MobileNet SSD
# implementation)
image = cv2.imread(args["image"])
(h, w) = image.shape[:2]
blob = cv2.dnn.blobFromImage(cv2.resize(image, (300, 300)), 0.007843, (300, 300), 127.5)
# pass the blob through the network and obtain the detections and
# predictions
print("[INFO] computing object detections...")
model.setInput(blob)
detections = model.forward()
# loop over the detections
for i in np.arange(0, detections.shape[2]):
# extract the confidence (i.e., probability) associated with the
# prediction
confidence = detections[0, 0, i, 2]
# filter out weak detections by ensuring the `confidence` is
# greater than the minimum confidence
if confidence > args["confidence"]:
# extract the index of the class label from the `detections`,
# then compute the (x, y)-coordinates of the bounding box for
# the object
idx = int(detections[0, 0, i, 1])
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
# display the prediction
label = "{}: {:.2f}%".format(CLASSES[idx], confidence * 100)
print("[INFO] {}".format(label))
cv2.rectangle(image, (startX, startY), (endX, endY),
COLORS[idx], 2)
y = startY - 15 if startY - 15 > 15 else startY + 15
cv2.putText(image, label, (startX, y),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)
# show the output image
cv2.imshow("Output", image)
cv2.imwrite('image_detected.jpg',image)
cv2.waitKey(0)
您应该将检测放在一个函数中，并在选择图像文件后调用该函数。同样使用 Pillow 模块转换结果图像并使用 Label.
import numpy as np
import argparse
import cv2
import tkinter as tk
from tkinter import filedialog
from PIL import Image, ImageTk
def detect_objects(image1):
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", default=image1,
help="path to input image")
ap.add_argument("-p", "--prototxt", default="MobileNetSSD_deploy.prototxt.txt",
help="path to Caffe 'deploy' prototxt file")
ap.add_argument("-m", "--model", default="MobileNetSSD_deploy.caffemodel",
help="path to Caffe pre-trained model")
ap.add_argument("-c", "--confidence", type=float, default=0.2,
help="minimum probability to filter weak detections")
args = vars(ap.parse_args())
# initialize the list of class labels MobileNet SSD was trained to
# detect, then generate a set of bounding box colors for each class
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
"dog", "horse", "motorbike", "person", "pottedplant", "sheep",
"sofa", "train", "tvmonitor"]
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))
# load our serialized model from disk
print("[INFO] loading model...")
model = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])
# load the input image and construct an input blob for the image
# by resizing to a fixed 300x300 pixels and then normalizing it
# (note: normalization is done via the authors of the MobileNet SSD
# implementation)
image = cv2.imread(args["image"])
(h, w) = image.shape[:2]
blob = cv2.dnn.blobFromImage(cv2.resize(image, (300, 300)), 0.007843, (300, 300), 127.5)
# pass the blob through the network and obtain the detections and
# predictions
print("[INFO] computing object detections...")
model.setInput(blob)
detections = model.forward()
# loop over the detections
for i in np.arange(0, detections.shape[2]):
# extract the confidence (i.e., probability) associated with the
# prediction
confidence = detections[0, 0, i, 2]
# filter out weak detections by ensuring the `confidence` is
# greater than the minimum confidence
if confidence > args["confidence"]:
# extract the index of the class label from the `detections`,
# then compute the (x, y)-coordinates of the bounding box for
# the object
idx = int(detections[0, 0, i, 1])
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
# display the prediction
label = "{}: {:.2f}%".format(CLASSES[idx], confidence * 100)
print("[INFO] {}".format(label))
cv2.rectangle(image, (startX, startY), (endX, endY),
COLORS[idx], 2)
y = startY - 15 if startY - 15 > 15 else startY + 15
cv2.putText(image, label, (startX, y),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)
# show the output image
image = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
tkimage = ImageTk.PhotoImage(image)
result.config(image=tkimage)
result.iamge = tkimage
def search_image():
image1 = filedialog.askopenfilename()
if image1:
detect_objects(image1)
root = tk.Tk()
root.geometry('1200x900-100-100')
root.resizable(False, False)
root.title('YOLO')
w = tk.Label(root, text = "IMAGE-DETECTION-YOLO", font = "Arial 36", bg ='lightgray', width = 900)
w.pack()
button = tk.Button(root, text = "CHOOSE", font = "Arial 36", command = search_image)
button.pack()
# label to show the result
result = tk.Label(root)
result.pack()
root.mainloop()