I am working on a face recognition project where a I can first enroll myself and then start a recognize script which will start my webcam and it will recognize myself. I am following this article and its working perfectly fine.
What I have noticed is that if I show my photo to the camera instead myself in front of the camera, it still detects and recognize my face. There is no anti-spoofing involved in it. I want to include anti-spoofing method in the code so that it can detect weather the face detected/recognized is real of fake. For this I thought of following below approaches:
1. Eye blink detection: Initially I thought I would implement an eye blink detection algorithm, but it also has its disadvantage. What if a real face person didnt blinked his eyes for sometime, in that case our code will tag that face as fake. Also the eyes was also not getting detected at a distance of 1-1.5meter from the camera.
2. Using temperature sensor: I also interfaced omron thermal sensor so that I can get the temperature of the face. In normal human face, temperature is always above a threshold. In case of face in photo, it will always be below that threshold. I implemented this and it was working fine. But later realized that if someone showed photo in phone, in that case due to phone's high screen temperature, its always more than the threshold and thus it is tagged in as real photo.
Above mentioned methods didn't worked for me. I am looking for a simple solution which can work in all the scenarios. I am doing this project on raspberry pi, so looking for a solution which is compatible with raspberry pi. Please help. Thanks
Sorry for any mistake because I am not from raspberry pi's background but as a decent guy helping people I think that you should try resolution check (if it is possible) because phone's screen would always have less resolution than the real face. And then you can use it with the eye blink method to catch hold of a phone as photos do not blink eyes. Average human blinks 12 times in a minute so 1 time every 5 seconds . This will help you to catch hold of the printed photos. Hope this would help.
You should use an object detector on top of the face detector. It can definitely detect a phone.
You could retrain it to detect a photo being held up as well.
Have the object detector run first, save the bounding box coordinates of the phone, then see if the face bounding box coordinates reside inside of the phone.
I'm working on a face recognition system right now as my thesis project. Have you tried this article? Adrian says that it is usable in Raspberry Pi, but it means we have to install TensorFlow & Keras to do it. I think this could help.
Related
I'm working on a machine learning application for reading data from fuel pumps, so far I've gone ahead and created a pretty robust YOLOv5 Object Detection Model that can detect the regions that I want fairly accurately. But there is a problem, at certain times of the day there are reflections on the digital screen and I'm unable to use OpenCV pre-process it so that I can extract the numbers from the display.
Check this Video to Understand (YOLOv5 Detection)
https://www.youtube.com/watch?v=3XjZ6Nw70j8
Minimum Reproduceable Example
Cars come and go and their reflection makes it really difficult to differentiate between the reigons for digital-7 font that is used in these displays, you can check out the following repository to understand what I want as s result https://github.com/arturaugusto/display_ocr
Other Solutions I'm Open to:
Since, this application is going to run 24/7 how should I deal with different times,
perhaps create a database of HSV ranges to extract at different times.
Use a polarizing lens would it help in removing the reflections (any user's who have had previous experiences in deploying them).
Edit: I added the correct video ...
I'm a senior in high school and this year I have to do a project for my electronic class, I was hoping to get some advice from people with some experience.
My idea is kind of complicated and has a lot of different sensors but not too crazy, the problem begins with possible image processing. I have a camera who need to check for flashing light and send the video to a screen without the frames of the flashing (like just skipping the frame, so the video is always a frame in delay but the person won't notice it).
The fashing light is supposed to be like in a party or in a video game you get a warning on. The idea is to notice the extreme changing of lighting and to not show it on the screen.
My teacher is afraid that doing image processing might be too complicated and video processing as well... I don't have any knowledge in it, and I have a little background in Python and other languages, do you think it is possible? Can anyone give me an advice or a good video/tutorial to learn from?
Thank you in advance:)
your probleme if quite diificult, cause it envolved unknown environnement in a dynamic time range.
if you admit as an axiom that your camera has for exemple a frame rate of 20 FPS, the chances that your difference between Frame f' and next frame f+1 are quite low.
UNLESS you have a huge color change du to ligth flash,
So you can process with an image similarity such as ssim or psim
https://www.pyimagesearch.com/2017/06/19/image-difference-with-opencv-and-python/
if your image is over a certain treshold that you have to define ( can use also a kalmann filter to dynamically reajust the difference treshold)
so it will probably mean that your flash light is on.
Although it's a visual coding program (per se), Bonsai is a great open source software for doing what's in your description; as well, Bonsai supports applications that require combinations of different hardware (e.g. microcontrollers, cameras) and software components (e.g. Python).
To provide a similar application as an example, I have setup a workflow where Bonsai captures images sent from a Basler camera, it processes the input video frame-by-frame, and when it detects, within the cropped frame (that I cropped around an red LED), a threshold change in pixel intensity (i.e. the red LED turns ON or OFF), it sends an output signal (i.e. 5 volts) to an Arduino microcontroller while saving the image frame as a png file as well as a avi video file along with a vector of True/False (corresponding to the ON or OFF red LED frames) and corresponding timestamps that are saved as csv files, etc. Although this isn't identical to what you've described, I'm sure you can setup a similar Bonsai workflow to accomplish your goal.
Citation: https://www.frontiersin.org/articles/10.3389/fninf.2015.00007/full
Edit: I'm very familiar with Bonsai so if you need help with setting up a Bonsai workflow I'd be happy to help; I don't think there is direct message on StackOverFlow, but given that StackOverFlow doesn't list Bonsai as a programming language (because it's a visual programming language; or because it's not well known enough to include on StackOverFlow) feel free to reach out if you have any questions regarding Bonsai specifically (again, it's also an open source software).
This is my first post here, so hello everyone.
I am working on a project that involves writing a program in c++ or python that will detect obstacles and will be used for AR.Drone 2.0. However, I don't know which approach should I take.
Initially, I was adviced to use opencv and optocal flow. I've found some videos and papers about it and one way is that: divide every frame from AR.Drone's camera on 2 (left/right side) or 4 (additionally up and bottom) and calculate optical flow for each part. Then, fly in the direction where the optical flow is less.
However I have some doubts about it:
1)Which method of optical flow calculation should I use? I know that in opencv there are provided methods for calculating both dense or sparse optical flow. Which one should I choose in this application? Won't dense optical flow be too slow to meet real-time requirements?
2)I guess that in time when UAV moves left-right or up-down I'll get some "fake" vectors caused by the movement of a drone and not because of the looming obstacle. How to prevent this?
Another solution I was told about a method shown here (link for paper in description) and someone who implemented it github link however the author admitted that he "never get obstacle detection working properly on the drone".
Another option I was told about is attaching a realsense camera to a drone and extract an information about the obstacle somehow using it.
So, my question is - which path should I take? Or is there some other method to do this that will work for application I described and is relatively easy to implement?
Thanks in advance for every reply.
I'm not sure the scope of your project, whether or not this is academic or professional, but my recommendation would be to use object detection of a control image with the camera facing directly forward on the drone. if the object is detected, you can estimate it's distance from your drone based on it's size. Since it is a control image it should have a constant size and you should record how many pixels across that is at various distances from your camera. This way you can build up a model. Once you know how far away the object is you can determine if it is an obstacle or not.
Once the detection becomes large enough, determine if it is in the flight path. Then you move the drone such that the coordinates of the detection box are no longer in your flight path.
For the detection, you can either use Google's detection api which comes with a number of solid detectors/classifiers, or if you are looking to add a layer of depth to the project you can train your own. PyImageSearch is a great place to start. And if you are feeling extra scientific you can dive right into Tensorflow.
Best of luck!
Try the open source project https://github.com/generalized-intelligence/GAAS
It uses stereo camera and SLAM to detect obstacles.
I am looking into image processing using an SJ4000 camera, linked up via USB to a Raspberry Pi (running Raspbian Jessie) for image processing with OpenCV in Python. I have achieved quite a bit using my webcam but now need to port it into the SJ4000's environment, however I am stuck at this hurdle.
The code I've used is identical to the answer to this question: rotated face detection.
On my laptop's webcam, I get a reasonably good framerate. When the SJ4000 is connected to my laptop via USB as well, I get a good framerate. However, on the Raspberry Pi, when I execute the same code, the image is just frozen for some reason. I then need to force quit the video viewer window which shows up as it's simply frozen.
EDIT 1: After closing the Spyder IDE and loading it up again a few times, and executing the same code, I can see a feed, but the framerate is very low (2-3 seconds per frame) and it will just freeze after some time.
EDIT 2: I've done further testing and find that when I include the face detection code, it takes a long time for the feed to be displayed as there is a TEN second delay. When I forward the feed live without any processing, it's very responsive.
How should I get around this? Is the only way getting a more powerful processor?
Thanks for any help!
Like others said, face detection is very computationally expensive using HOG/Haar descriptors. You won't be able to do real time face detection on the Raspberry Pi. On my Raspberry Pi 3, I can do human body detection on a 300x300 image at around 5 fps.
What I recommend is: Do motion detection. When motion is detected, start face detection.
Further optimization can be done by running face detection in its own thread, and have motion detection feed a FIFO of frames to be analyzed by face detector if motion is detected in a frame. That way, your face detector can operate asynchronously, and not hold up the main thread capturing the video frames, and doing motion detection.
I am working on a project where I need to program a Raspberry Pi to grab an image from a webcam, search that image for a box and identify what box it is by it's size ratio. The boxes will be a unique color to the rest of the environment. It would also be good to identify the distance from the box and angle to the box.
Everything I've seen seems to indicate that this should be possible, but after several days of searching I have yet to find anything that really helps me to do this. This project is my first experience using Python, so I'm pretty newbish. Any help even with how to do little portions of this would be greatly appreciated.
Here's my working code so far. It's not much, all it does is grab an image from a webcam :/
import imgproc
from img imgproc *
camera = Camera(160, 120)
viewer = Viewer(160, 120)
n = 1
while (n > 0):
img = camera.grabImage()
viewer.displayImage(img)
This is not a complete solution, but some good ideas on how to get started :)
First off, there are Python bindings for OpenCV, an open source free computer vision library originally written in C: http://opencv.willowgarage.com/documentation/python/index.html
The first thing you have to do when solving a computer vision problem is pre-process. In particular, knowing that the box is a different colour helps a LOT - it means we can threshold by colour and create an image that is black where the box is not, and white where the box is, using a technique such as in http://aishack.in/tutorials/thresholding/ .
Then, you'd follow a process similar to the Sudoku grabber/solver described in this blog - you do blob extraction ( http://en.wikipedia.org/wiki/Blob_extraction ) then do a hough transform to get lines, and then you can compare the lines' distances to each other to determine the box's ratio. http://aishack.in/tutorials/sudoku-grabber-with-opencv-plot/
Pretty much just read about people's OpenCV Sudoku solvers until you get the gist of how it's done, because there are a lot of good tutorials and it's a simple illustration of how computer vision projects go: https://www.google.com.au/search?q=sudoku+opencv&aq=f&oq=sudoku+opencv&aqs=chrome.0.57j60l3j0l2.1506&sourceid=chrome&ie=UTF-8
You may want to try installing SimpleCV from the github repo. Using SimpleCV you should be able to get the blob's color using the Image.hueDistance command. If you use the findBlobs command to find your boxes each blob should have its aspect ratio as a parameter. We just posted our full PyCon tutorial about SimpleCV here. You can view just the slides here. We've heard that there are some issues installing PyGame (a SimpleCV dependency) on the RaspberryPi. This walk through might address those issues.