For face detection I have used the haarcascade_frontalface_alt.xml.
The problem is that the this this algorithm gives me a roi a little bit larger so the rectangle catches some hair and some of the background. Is there a solution to change the dimension of this rectangle?
This what the haarcascade_frontalface_alt.xml detects:
And this what I want to detect:
You cannot reply on OpenCV to do this because its model is trained based on face images just like the first one. That is to say, it is supposed to give face detections like the first one.
Instead, consider to crop the detected rectangles a little bit, whatever size you want it be.
To be more accurate, you can crop the faces based on the facial features, as discussed in this thread.
Related
Here I say that I have tried many tutorials to implement face recognition in OpenCV 3.2 by using the FaceRecognizer class in face module. But I did not get the accepted result as I wish.
Here I want to ask and I want to know, that what is the best way or what are the conditions to be care off during training and recognizing?
What I have done to improve the accuracy:
Create (at least) 10 faces for training each person in the best quality, size, and angle.
Try to fit the face in the image.
Equalize the HIST of the images
And then I have tried all the three face recognizer (EigenFaceRecognizer, FisherFaceRecognizer, LBPHFaceRecognizer), the result all was the same, but the recognition rate was really very low, I have trained only for three persons, but also cannot recognize very well (the fist person was recognized as the second and so on problems).
Questions:
Do the training and the recognition images must be from the same
camera?
Do the training images cropped manually (photoshop -> read images then train) or this task
must be done programmatically (detect-> crop-> resize then train)?
And what are the best parameters for the each face recognizer (int num_components, double threshold)
And how to set training Algorithm to return -1 when it is an unknown
person.
Expanding on my comment, Chapter 8 in Mastering OpenCV provides really helpful tips for pre-processing faces to make aid the recognition process, such as:
taking a sample only when both eyes are detected (via haar cascade)
Geometrical transformation and cropping: This process would include scaling, rotating, and translating the images so that the eyes are aligned, followed by the removal of the forehead, chin, ears, and background from the face image.
Separate histogram equalization for left and right sides: This process standardizes the brightness and contrast on both the left- and right-hand sides of the face independently.
Smoothing: This process reduces the image noise using a bilateral filter.
Elliptical mask: The elliptical mask removes some remaining hair and background from the face image.
I've added a hacky load/save to my fork of the example code, feel free to try it/tweak it as you need it. Currently it's very limited, but it's a start.
Additionally, you should also check OpenFace and it's DNN face recognizer.
I haven't played with that yet so can't provide details, but it looks really cool.
I am trying to detect a ball in an filtered image.
In this image I've already removed the stuff that can't be part of the object.
Of course I tried the HoughCircle function, but I did not get the expected output.
Either it didn't find the ball or there were too many circles detected.
The problem is that the ball isn't completly round.
Screenshots:
I had the idea that it could work, if I identify single objects, calculate their center and check whether the radius is about the same in different directions.
But it would be nice if it detect the ball also if he isn't completely visible.
And with that method I can't detect semi-circles or something like that.
EDIT: These images are from a video stream (real time).
What other method could I try?
Looks like you've used difference imaging or something similar to obtain the images you have..? Instead of looking for circles, look for a more generic loop. Suggestions:
Separate all connected components.
For every connected component -
Walk around the contour and collect all contour pixels in a list
Suggestion 1: Use least squares to fit an ellipse to the contour points
Suggestion 2: Study the curvature of every contour pixel and check if it fits a circle or ellipse. This check may be done by computing a histogram of edge orientations for the contour pixels, or by checking the gradients of orienations from contour pixel to contour pixel. In the second case, for a circle or ellipse, the gradients should be almost uniform (ask me if this isn't very clear).
Apply constraints on perimeter, area, lengths of major and minor axes, etc. of the ellipse or loop. Collect these properties as features.
You can either use hard-coded heuristics/thresholds to classify a set of features as ball/non-ball, or use a machine learning algorithm. I would first keep it simple and simply use thresholds obtained after studying some images.
Hope this helps.
I've working on this some time now, and can't find a decent solution for this.
I use OpenCV for image processing and my workflow is something like this:
Took a picture of a tv.
Split image in to R, G, B planes - I'm starting to test using H, S, V too and seems a bit promising.
For each plane, threshold image for a range values in 0 to 255
Reduce noise, detect edges with canny, find the contours and approximate it.
Select contours that contains the center of the image (I can assume that the center of the image is inside the tv screen)
Use convexHull and HougLines to filter and refine invalid contours.
Select contours with certain area (area between 10%-90% of the image).
Keep only contours that have only 4 points.
But this is too slow (loop on each channel (RGB), then loop for the threshold, etc...) and is not good enought as it not detects many tv's.
My base code is the squares.cpp example of the OpenCV framework.
The main problems of TV Screen detection, are:
Images that are half dark and half bright or have many dark/bright items on screen.
Elements on the screen that have the same color of the tv frame.
Blurry tv edges (in some cases).
I also have searched many SO questions/answers on Rectangle detection, but all are about detecting a white page on a dark background or a fixed color object on a contrast background.
My final goal is to implement this on Android/iOS for near-real time tv screen detection. My code takes up to 4 seconds on a Galaxy Nexus.
Hope anyone could help . Thanks in advance!
Update 1: Just using canny and houghlines, does not work, because there can be many many lines, and selecting the correct ones can be very difficult. I think that some sort of "cleaning" on the image should be done first.
Update 2: This question is one of the most close to the problem, but for the tv screen, it didn't work.
Hopefully these points provide some insight:
1)
If you can properly segment the image via foreground and background, then you can easily set a bounding box around the foreground. Graph cuts are very powerful methods of segmenting images. It appears that OpenCV provides easy to use implementations for it. So, for example, you provide some brush strokes which cover "foreground" and "background" pixels, and your image is converted into a digraph which is sliced optimally to split the two. Here is a fun example:
http://docs.opencv.org/trunk/doc/py_tutorials/py_imgproc/py_grabcut/py_grabcut.html
This is a quick something I put together to illustrate its effectiveness:
2)
If you decide to continue down the edge detection route, then consider using Mathematical Morphology to "clean up" the lines you detect before trying to fit a bounding box or contour around the object.
http://en.wikipedia.org/wiki/Mathematical_morphology
3)
You could train across a dataset containing TVs and use the viola jones algorithm for object detection. Traditionally it is used for face detection but you can adapt it for TVs given enough data. For example you could script downloading images of living rooms with TVs as your positive class and living rooms without TVs as your negative class.
http://en.wikipedia.org/wiki/Viola%E2%80%93Jones_object_detection_framework
http://docs.opencv.org/trunk/doc/py_tutorials/py_objdetect/py_face_detection/py_face_detection.html
4)
You could perform image registration using cross correlation, like this nice MATLAB example demonstrates:
http://www.mathworks.com/help/images/examples/registering-an-image-using-normalized-cross-correlation.html
As for your template TV image which would be slid across the search image, you could obtain a bunch of pictures of TVs and create "Eigenscreens" similar to how Eigenfaces are used for facial recognition and generate an average TV image:
http://jeremykun.com/2011/07/27/eigenfaces/
5)
It appears OpenCV has plenty of fun tools for describing shape and structure features, which appears to be mainly what you're interested in. Worth a look if you haven't seen this already:
http://docs.opencv.org/modules/imgproc/doc/structural_analysis_and_shape_descriptors.html
Best of luck.
I am attempting to detect coloured tennis balls on a similar coloured background. I am using OpenCV and C++
This is the test image I am working with:
http://i.stack.imgur.com/yXmO4.jpg
I have tried using multiple edge detectors; sobel, laplace and canny. All three detect the white line, but when the threshold is at a value where it can detect the edge of the tennis ball, there is too much noise in the output.
I have also tried the Hough Circle transform but as it is based on canny, it isn't effective.
I cannot use background subtraction because the background can move. I also cannot modify the threshold values as lighting conditions may create gradients within the tennis ball.
I feel my only option is too template match or detect the white line, however I would like to avoid this if possible.
Do you have any suggestions ?
I had to tilt my screen to spot the tennisball myself. It's a hard image.
That said, the default OpenCV implementation of the Hough transform uses the Canny edge detector, but it's not the only possible implementation. For these harder cases, you might need to reimplement it yourself.
You can certainly run the Hough algorithm repeatedly with different settings for the edge detection, to generate multiple candidates. Besides comparing candidates directly, you can also check that each candidate has a dominant texture (after local shading corrections) and possibly a stripe. But that might be very tricky if those tennisballs are actually captured in flight, i.e. moving.
What are you doing to the color image BEFORE the edge detection? Simply converting it to gray?
In my experience colorful balls pop out best when you use the HSV color space. Then you would have to decide which channel gives the best results.
Perhaps transform the image to a different feature space might be better then relying on color. Maybe try LBP which responds to texture. Then do PCA on the result to reduce the feature space to 1 single channel image and try Hough Transform on that.
I have a video sequence of which one frame is shown below as shown below.
I was trying to use corner detection to find the edges of the rectangle on the sheet of paper.
I am using the Shi-Tomasi corner detector for the same. However it detects a number of other things that I don't need from the background of the image. How can I narrow down my ROI to only the sheet of paper.
Second Question:
In the video sequence upon detecting The corners I need to play another video inside the rectangle. I was trying to do this using a single thread but it lead to a lot of lag and jerks. What can I possibly do to improve my processing speed. Do I need to use multiple threads for each video. One video is from the webcam while the other is from the hard-drive.
Here is what I did for one of previous projects.
Find all contours in your picture and approximate each with 4 corner shape
Find right rectangle with your own condition such as rectangle with area > 1000000
(optional) you will notice that your rectangle is not real rectangle because of 3D world. You might want to do perspective transformation to get correct rectangle
Paint green or whatever texture on the found rectangle since you already have 4 corners from above
As for jerky playing, you might want to use not only multithreading with GPU but also encryption to improve speed.