What kind of sensor I can use to identify which fruit it is (like mango or apple). Moreover, is there any sensor to identify different varieties of apples or mangoes.

  • 3
    $\begingroup$ Have you tried answering your own question? What sensors did you find in your research? Why were they not adequate for your purpose? $\endgroup$ – Shahbaz Feb 13 '16 at 16:57
  • $\begingroup$ That can be done with pattern matching. How much RAM or other space do you have available for that comparison? How many different fruits do you want to identfy? $\endgroup$ – ott-- Feb 13 '16 at 21:11
  • $\begingroup$ I voted to close this question because, "Unbounded Design Questions are off-topic because there are many ways to solve any given design problem, so questions that ask for a list of approaches or a subjective recommendation on a method (for how to build something, how to accomplish something, what something is capable of, etc.) are off-topic." $\endgroup$ – Chuck Feb 14 '16 at 18:46
  • $\begingroup$ You could use a color sensor and color match, or any of a host of 3D sensors (stereo vision, LIDAR, radar, etc.) to shape match, or an electronic noise to match by smell, or take a sample and match by chemistry or spectral analysis, or remove the seeds and do shape matching on seeds, or check skin thickness, or or or. As a designer, it's up to you to evaluate all the options. This site exists to help you with specific questions based on problems you actually face. It is not a brainstorming site. $\endgroup$ – Chuck Feb 14 '16 at 18:51
  • $\begingroup$ Welcome to robotics Subhajit Biswas, but I'm afraid it's not clear what you are asking. We prefer practical, answerable questions based on actual problems that you face, so it is a good idea to include details of what what you would like to achieve, what you have tried, what you expected to see & what you actually saw. Take a look at How to Ask & tour for more information on how stack exchange works. Please use the Robotics question checklist to make your question clearer. $\endgroup$ – Mark Booth Feb 15 '16 at 12:18

To answer your question I can think of at least: RGB camera, NIR camera, laser scanner.

What you do with the sensors is much more difficult, for example, you have an RGB image of a mango fruit on a tree, how do you find which pixels are mango and which are not (e.g. tree, sky, ground). This is an ongoing research topic in computer vision and agricultural robotics. Some papers show results under controlled conditions (in a lab) or semi-controlled (using assumptions, shading and controlled lighting).

It really depends on the assumptions you can make, then you can match by colour, size and visual texture, amongst other properties.


Not the answer you're looking for? Browse other questions tagged or ask your own question.