Dlib how do I save image

解决c++ - In Dlib how do I save image with overlay?

推荐：how to save a c++ object in java object and use it

http://blog.csdn.net/luoshengyang/article/details/6817933 save: static void android_os_MessageQueue_setNativeMessageQueue(JNIEnv* env, jobject message

2018阿里云全部产品优惠券(新购或升级都可以使用，强烈推荐)
领取地址：https://promotion.aliyun.com/ntms/yunparter/invite.html

I'm trying to modify Dlib's face detection example to save an image with detections to a file since I'm using a server without GUI. So far I have only figured how to save the image but not the overlay. How do I save both to the same file?

//win.add_overlay(dets, rgb_pixel(255,0,0));
save_png(img, "detected.png");

c++ dlib 
  | 
  this question asked Apr 21 '15 at 4:13 Tim Clemans 127 9      How to use draw_rectangle in c++, Please help –  Mavie Apr 18 '16 at 4:44      I have asked about it but It seems not got attention ..can u please tell me how did u saved image with overlay...You can also answer my question. link to question–  Mavie Apr 18 '16 at 4:47

---

---

 | 

2 Answers
2

解决方法

You can call draw_rectangle on the image before saving it.

  | 
  this answer answered Apr 21 '15 at 8:38 Davis King 2,750 14 15      what is the syntax to usedraw_rectangle. –  Mavie Apr 16 '16 at 10:31

---

---

 | 

Try this: dlib::draw_rectangle()

Example: dlib::draw_rectangle(rect_image, rect, dlib::rgb_pixel(255, 0, 0), 1);

  | 
  this answer answered Oct 12 '16 at 8:43 Dmitry 31 5

how to save/crop detected faces in dlib python

Ask Question

up vote7down votefavorite

1

i want to save the detected face in dlib by cropping the rectangle do anyone have any idea how can i crop it. i am using dlib first time and having so many problems. i also want to run the fisherface algorithm on the detected faces but it is giving me type error when i pass the detected rectangle to pridictor. i seriously need help in this issue.

import cv2, sys, numpy, os
import dlib
from skimage import io
import json
import uuid
import random
from datetime import datetime
from random import randint
#predictor_path = sys.argv[1]
fn_haar = 'haarcascade_frontalface_default.xml'
fn_dir = 'att_faces'
size = 4
detector = dlib.get_frontal_face_detector()
#predictor = dlib.shape_predictor(predictor_path)
options=dlib.get_frontal_face_detector()
options.num_threads = 4
options.be_verbose = True

win = dlib.image_window()

# Part 1: Create fisherRecognizer
print('Training...')

# Create a list of images and a list of corresponding names
(images, lables, names, id) = ([], [], {}, 0)

for (subdirs, dirs, files) in os.walk(fn_dir):
    for subdir in dirs:
        names[id] = subdir
        subjectpath = os.path.join(fn_dir, subdir)
        for filename in os.listdir(subjectpath):
            path = subjectpath + '/' + filename
            lable = id
            images.append(cv2.imread(path, 0))
            lables.append(int(lable))
        id += 1

(im_width, im_height) = (112, 92)

# Create a Numpy array from the two lists above
(images, lables) = [numpy.array(lis) for lis in [images, lables]]

# OpenCV trains a model from the images

model = cv2.createFisherFaceRecognizer(0,500)
model.train(images, lables)

haar_cascade = cv2.CascadeClassifier(fn_haar)
webcam = cv2.VideoCapture(0)
webcam.set(5,30)
while True:
    (rval, frame) = webcam.read()
    frame=cv2.flip(frame,1,0)
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    mini = cv2.resize(gray, (gray.shape[1] / size, gray.shape[0] / size))

    dets = detector(gray, 1)

    print "length", len(dets)

    print("Number of faces detected: {}".format(len(dets)))
    for i, d in enumerate(dets):
        print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
            i, d.left(), d.top(), d.right(), d.bottom()))

    cv2.rectangle(gray, (d.left(), d.top()), (d.right(), d.bottom()), (0, 255, 0), 3)


    '''
        #Try to recognize the face
        prediction  = model.predict(dets)
        print "Recognition Prediction" ,prediction'''





    win.clear_overlay()
    win.set_image(gray)
    win.add_overlay(dets)

if (len(sys.argv[1:]) > 0):
    img = io.imread(sys.argv[1])
    dets, scores, idx = detector.run(img, 1, -1)
    for i, d in enumerate(dets):
        print("Detection {}, score: {}, face_type:{}".format(
            d, scores[i], idx[i]))

python opencv face-detection face-recognition dlib

shareimprove this question

asked Oct 12 '16 at 21:39

Irum Zahra Awan

116111

add a comment

4 Answers

activeoldestvotes

up vote5down voteaccepted

Should be like this:

crop_img = img_full[d.top():d.bottom(),d.left():d.right()]

shareimprove this answer

answered Oct 13 '16 at 15:35

Andrey Smorodov

8,46422333

add a comment

up vote3down vote

Please use minimal-working sample code to get answers faster.

After you have detected face - you have a rect. So you can crop image and save with opencv functions:

    img = cv2.imread("test.jpg")
    dets = detector.run(img, 1)
    for i, d in enumerate(dets):
        print("Detection {}, score: {}, face_type:{}".format(
            d, scores[i], idx[i]))
        crop = img[d.top():d.bottom(), d.left():d.right()]
        cv2.imwrite("cropped.jpg", crop)

shareimprove this answer

edited May 28 '17 at 21:03

kjagiello

6,21722243

answered Oct 13 '16 at 11:21

Evgeniy

1,918821

add a comment

up vote2down vote

Answer by Andrey was good but it misses edge cases where original rectangle is partially outside the image window. (Yes that happens with dlib.)

crop_img = img_full[max(0, d.top()): min(d.bottom(), image_height),
                    max(0, d.left()): min(d.right(), image_width)]

shareimprove this answer

edited May 31 '17 at 2:30

Nathan Tuggy

2,18892533

answered May 31 '17 at 1:47

Ankur Jain

39719

add a comment

up vote0down vote

# Select one of the haarcascade files:
#   haarcascade_frontalface_alt.xml  
#   haarcascade_frontalface_alt2.xml
#   haarcascade_frontalface_alt_tree.xml
#   haarcascade_frontalface_default.xml
#   haarcascade_profileface.xml

I remember haarcascade_frontalface_alt.xml is the best one?

shareimprove this answer

In Dlib how do I save image with overlay?

Ask Question

up vote8down votefavorite

1

I'm trying to modify Dlib's face detection example to save an image with detections to a file since I'm using a server without GUI. So far I have only figured how to save the image but not the overlay. How do I save both to the same file?

//win.add_overlay(dets, rgb_pixel(255,0,0));
save_png(img, "detected.png");

c++ dlib

shareimprove this question

asked Apr 21 '15 at 4:13

Tim Clemans

177111

• How to use draw_rectangle in c++, Please help – Mavie Apr 18 '16 at 4:44

• I have asked about it but It seems not got attention ..can u please tell me how did u saved image with overlay...You can also answer my question.link to question – Mavie Apr 18 '16 at 4:47

add a comment

2 Answers

activeoldestvotes

up vote6down voteaccepted

You can call draw_rectangle on the image before saving it.

shareimprove this answer

answered Apr 21 '15 at 8:38

Davis King

3,79511820

• what is the syntax to use draw_rectangle. – Mavie Apr 16 '16 at 10:31

add a comment

up vote2down vote

Try this: dlib::draw_rectangle()

Example:

dlib::draw_rectangle(rect_image, rect, dlib::rgb_pixel(255, 0, 0), 1);