Geometric shape detection and classification in 2 D images on raspberry pi module - 3 -- 2
₹600-9500 INR
Închis
Data postării: aproape 8 ani în urmă
₹600-9500 INR
Plata la predare
Project is geometric shape detection in 2 dimensional image on raspberry pi module 3.
I have made my progrom in matlab software now I need to convert it into python to make a stand alone application.
Image is captured from camera module interfaced with Raspberry pi and processed.
Reading that image we are for each blob we have to detect what is shape of that region by measuring the distance between shapes centroid and boundary. we decide what is number of vertices like triangle will have three vertices, pentagon will have 5 vertices like wise.
General Overview of My algorithm:
1. Take image using camera interfaced to raspberry pi (Rpi)
2. For a single shape create a centroid to boundary distance profile (Please check the image of centroid to boundary distance profile in attached file)
3. Based on that profile classify these shapes into individual one
4. Also using that profile measure the length of each vertices if shape have vertices between two-to-six and radius and major and minor axis if it is circle or ellipse respectively
5. We need to measure all basic properties of each shape using that profile.
6. So you need to do detection, classification, counting, and measuring properties for each shape
7. Plot detection vs distortion i.e. the accuracy how it behaves against distortion (using synthetic image)
8. Plot time taking for each shape detection
Program steps will be like this:
Different shapes to be classified are:
1-Ellipse
2-equilateral triangle
3-Iso-scale triangle
4-Right triangle
5-Ir-regular triangle
6-Rhombus
7-Irregular rectangle
8-Regular rectangle
9-Square
10-Regular Pentagon
11-Irregular Pentagon
12-Regular Hexagon
13-Irregular Hexagon
14-Circle
…
etc
Hello there...i have good python and opencv skills, i have a sample on my portfolio (people counter). i have seen the algorithm you've proposed, i have other few details i would love to confirm with you
I am an avid programmer with experience in python scikit-image and scikit-learn packages. I also have experience in making shape classification application in matlab. I also have experience in working with Raspberry pi 3 , Arduino mega and Uno. I currently have raspberry pi 3 with me in case the programs need to be run.
I'm currently working on my graduate project and I have some free time. Python is my main Programming language and I have done many projects for my company and university in it.
This project seems very interesting and I'm sure I can complete it with great success rate and in a short time. I'm completly sure how to make your shape analysis. I just need more information on detecting shapes from image and finding it's centroids. Should it be done by simple pixel-by-pixel processing or I can use OpenCV to detect shapes? How fast it needs to work?
Also, I am looking forward to work on any similar data analyse projects you may have in the future.
Please contact me for more informations.
I have to say that I'm new on Freelancer so I haven't passed any of the exams yet. The same applies to my work rating. But this will be updated soon. ;)
Kind regards, Tomislav
Hello.. I have good experience with raspberry and recognition. I build those algorithms from scratch. Lets cooperate here. Cost is $5,000 not negotiable.