Please help me for my android project Fruit Ripeness Recogntion of Banana and Mango (ripe, midripe, unripe and over ripe)

Question

1.00/5 (2 votes)

See more:

Good Day to Everyone :)

can someone help me to form a source code for that kind of project.
Using a camera of smartphone it will recognized whether the banana or mango is unripe, midripe, ripe and over ripe.

Posted 10-Jan-14 14:19pm

Member 10215246

Updated 10-Jan-14 14:49pm

v3

Add a Solution

Comments

Matt T Heffron 10-Jan-14 20:23pm

How can we help if you haven't asked a specific question about a problem you're having.

Member 10215246 10-Jan-14 20:43pm

can someone help me to form a source code for that kind of project.
Using a camera of smartphone it will recognized whether the banana or mango is unripe, midripe, ripe and over ripe

2 solutions

Add a Solution

Add your solution here

Treat my content as plain text, not as HTML

Preview 0

…

Existing Members

Sign in to your account

...or Join us

Download, Vote, Comment, Publish.

Your Email
Password
Forgot your password?

Your Email
This email is in use. Do you need your password?
Optional Password

I have read and agree to the Terms of Service and Privacy Policy
Please subscribe me to the CodeProject newsletters

When answering a question please:

Read the question carefully.
Understand that English isn't everyone's first language so be lenient of bad spelling and grammar.
If a question is poorly phrased then either ask for clarification, ignore it, or edit the question and fix the problem. Insults are not welcome.
Don't tell someone to read the manual. Chances are they have and don't get it. Provide an answer or move on to the next question.

Let's work to help developers, not make them feel stupid.

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

Dave Kreskowiak · Accepted Answer · 2014-01-10T16:15:00

Solution 2

If by "help me to form a source code" you mean that you want something is already written, you're not going to find it and nobody is going to write it for you.

What you're talking about is called "computer vision" or "machine vision". Your project is actually an extremely large problem to solve. How are you going to recognize the fruit in question? How are you going to determine how ripe the fruit is? How are you going to recognize the ripeness for each fruit?

This project is going to take something like the AForge library to help with the "vision" part and you're going to need to come up with a neural network that learns what level of ripeness is for each fruit.

There are fruits that you're not going to be able to determine the ripeness of simply because you can't see it on the outside.

Posted 10-Jan-14 16:15pm

Dave Kreskowiak

Comments

Member 10215246 10-Jan-14 22:57pm

thanks for your comment
my instructor suggested me to use MATLAB because this kind of project is pure image processing
To know if the fruit is ripe, the skin color of the fruit like banana or mango will be captured.

Dave Kreskowiak 11-Jan-14 0:17am

MATLAB on a smartphone? Good luck with that!

Also, color isn't exactly easy to determine in a webcam image. You still need calibration and an adapting algorithm because not all cameras are created equal and will vary with things like color temperature, exposure, brightness and contrast and IR filtering quality to name a few.

Also, how to do you define a color like "green"? What is green in any arbitrary collection of pixels in a camera image is actually many different shades of green, even for pixels that are right next to each other, and will vary according to light levels and everything else I just mentioned.

Unless you've already got some vision, image processing, and neural network experience, this will be a really tough project.

Good luck!

BillWoodruff · Accepted Answer · 2014-01-10T16:31:00

For fruit recognition there are no low-hanging fruit !

I suggest you take on a project with much more limited goals. Consider how necessary the haptic sense (touch), and the olfactory sense (smell), are in recognizing the "ripeness state" of many fruits, in addition to the visual !

You could do some visual screening based on the appearance of "blotches," or variations from a standard range of colors, but remember a lot of fruit (in upscale American groceries, anyway) is "doctored" to look good.

For certain specific fruit (bananas), you might be able to use color alone to estimate ripeness.

See: [^], [^].

And, think about the problem of just scanning for blotches: you'd need multiple scans to cover the whole fruit, depending on shape.