Detecting Ripeness In Fruit And Vegetables Via Neural Networks

Humans have an innate knack for identifying food that is fit to eat. There’s a reason you instinctively enjoy fresh fruit and vegetables, but find maggot-infested rotting flesh offputting, for example. However, we like to automate as much of the food production process as possible so we can do other things, so it’s necessary to have machines sort the ripe and ready produce from the rest at times. [kutluhan_aktar] has found a way to do just that, using the power of neural networks.

The project’s goal is a straightforward one, aiming to detect ripeness in fruit and vegetables by monitoring pigment changes. Rather than use a camera, the project relies on data from an AS7341 visible light sensor, which is better suited to capturing accurate spectral data. This allows a better read of the actual light reflected by the fruit, as determined by the pigments in the skin which are directly related to ripeness.

Sample readings were taken from a series of fruit and vegetables over a period of several days, which allowed a database to be built up of the produce at various stages of ripeness. This was then used to create a TensorFlow model which can determine the ripeness of fruit held under the sensor with a reasonable degree of certainty.

The build is a great example of the use of advanced sensing in combination with neural networks. We suspect the results are far more accurate than could have reasonably be determined with a cheap webcam, though we’d love to see an in-depth comparison as such.

Believe it or not, it’s not the only fruit spectrometer we’ve featured in these hallowed pages. Video after the break.

Continue reading “Detecting Ripeness In Fruit And Vegetables Via Neural Networks”

Tend Your Garden… Again

In the early 1940s, several countries saw an incredible shift in agriculture. What were called “victory gardens” were being planted en masse by people from all walks of life, encouraged by various national governments around the world. Millions of these small home gardens sprang up to help reduce the price of produce during World War 2, allowing anyone with even the tiniest pot of soil to contribute to the war effort.

It’s estimated that in 1943 alone, victory gardens accounted for around one third of all vegetables produced in the United States. Since then, however, the vast majority of these productive gardens have been abandoned in favor of highly manicured, fertilized, irrigated turfgrass (which produces no food yet costs more to maintain), but thanks to the recent global pandemic there has been a resurgence of people who at least are curious about growing their own food again, if not already actively planting gardens. In the modern age, even though a lot of the folk knowledge has been lost since the ’40s, planting a garden of any size is easier than ever especially with the amount of technology available to help.

As someone who not only puts food on the table as a writer for a world-renowned tech website but also literally and figuratively puts food on the table as a small-scale market farmer, there are a few things that I’ve learned that I hope will help if you’re starting your first garden.

Continue reading “Tend Your Garden… Again”

Less Than Production, More Than One-Offs

We build things we think are cool. Sometimes, other people agree with us and they want a copy of what we’ve built. If you’re lucky enough to have an enviable product but you’re not ready for full-scale manufacturing, you may be looking at a low-volume production run. [Eric Strebel] walks us through one such instance where he makes some custom color swatches for a show. Video after the break.

[Eric Strebel] is an industrial designer so he plays to his strengths by designing the swatch shape, jig, tool, and hangers. He hires out the painting, laser cutting, and CNC machining. This may seem like a simple statement but some of us have a hard time paying other people for things we’re capable of learning. In some cases, we just have to pay the professionals to do it correctly and keep our focus.

The mentality of small runs in this video is perfect for people who sell on Tindie or want to make more than a handful of consistently nice parts. Our own [Lewin Day] recently talked about his experience with a run of 200 mixers called gMix.

Continue reading “Less Than Production, More Than One-Offs”

Red Bull Creation Winners: Maker Twins

This year’s Red Bull Creation theme “Reinvent the Wheel” was pretty¬†broad, but the Maker Twins managed to incorporate it quite closely with their winning project which was completed in under 72 hours. They took the idea of urban farming and figured out one way to make farmer’s markets more feasible by helping to eliminate waste and spruce up the presentation of the produce.

The project amounts to a Ferris wheel. Instead of passenger compartments there are modular crates which are built with one wooden pallet each. The wheel itself is chain-driven and allows the system to track where each crate is in the rotation. This data is leveraged for a couple of different uses. One lets the customer select their produce on a tablet app and the crate will rotate into position so they may pick the individual items they want. The machine will also take care of automated watering to ensure the produce on display doesn’t get dried out. The icing on the cake is a separate station for washing and cutting the purchased veggies.

Thank you to Maker Twins for contributing some demonstration “b-roll” for use in this video.

5 Tones, 1 Arduino

Because the Arduino is in such high demand for producing multiple musical tones at the same time; [Jeremy Blum] has successfully figured out the math and other necessaries that will take your once previously single tone producing MCU and turn it into a 5 tone producing machine. unsurprisingly its really just some creative use of PWM control but it all works out in the end anyway and helps prevent you from purchasing additional sound generating chips. This truly does open up some new doors, as [Jeremy] shows with his still in production thingamakit like project: ReacXion.