Project

# Title Team Members TA Documents Sponsor
66 Image Recognition Expiration Date Tracker inside of a Refrigerator
Jonathan Jacobson
Kevin Choi
Vaibhav Makar
Bonhyun Ku design_document1.pdf
final_paper1.pdf
other1.png
other2.pdf
photo1.jpg
presentation1.pdf
proposal1.pdf
Jonathan Jacobson, Kevin Choi, Vaibhav Makar

jlj3, gchoi17, vmakar2

_Problem:_ Food is wasted because it expires without the customer knowing. Current food expiration timers require the user to input every food and its expiration date manually, which is a chore few are willing to do. Also, visually impaired people may have trouble reading the expiration date on food, possibly leading to situations where food expires in the fridge or on shelves unnoticed.

_Solution Overview:_ Our project proposes to create an image scanner/speaker combination that can be put inside of a small section of a refrigerator that will scan food using computer vision, estimate the expiration date based on the type of food, and automatically create timers. The product will keep track of the food in the fridge, updating its timers when it recognizes that the food has been removed for an extended period of time (eaten/used). If the food stays in the fridge for an abnormal amount of time (past its estimated expiration), the device will alert the user when the fridge is next opened. There will also be a gas-detecting sensor that will sense certain gases related to food expiration as a failsafe in case food expires past the expected expiration date. The difference between this solution and an app-based solution is that the user does not need to interact with the device at all, it will create and remove timers based on whether the food is in the fridge or not, only alerting the user when food has expired.

_Solution Components:_

**Gas Sensor** Sensors that can detect gaseous ammonia or hydrogen peroxide would work in conjunction with the food expiration estimate to create a robust system to detect spoiled food.

**Camera** A camera connected to the onboard logic that can be used to scan food items and guess what type of food it is (eggs, milk, bread, fruit, meat, etc.) We are planning to use open-source software running on a Raspberry Pi for image recognition.

**Speaker** An external speaker connected to the onboard logic that will be used to transmit information to the consumer. This can be particularly useful to visually impaired people as it would allow for conveying information without a screen.

**Microcontroller** A microcontroller (Microchip PIC) that will be able to sense when the door of the refrigerator has been opened, and will wake up the Raspberry Pi when the door closes again. This microcontroller will also control the gas sensor, sending information to the main computer when either gaseous ammonia or hydrogen peroxide is detected.


**Onboard Computer** A Raspberry Pi that will have the open source image recognition software running on it. This is also where the scripts to start the timers and to play the audible reminders will be located. This computer will remain inactive until it receives the wake-up call from the low-power microcontroller. This also will house the bluetooth transmitter, to transmit the announcement to the user’s smartphone.

**Onboard memory** Onboard memory to store products and expiration dates. This will be stored directly on the Raspberry Pi


**Power circuit** This will power both the low-power microcontroller and the Raspberry Pi, and will be able to route power to the Raspberry Pi when told to by the microcontroller.

**Mobile Application** An app that can pair with the device using Bluetooth and has an interface to modify any incorrect or outdated information.


_Criteria for Success:_

The device should be able to withstand the temperatures in the fridge, determine the types of food and create timers based on their expected expiration dates. This device should be able to alert the user if there is expired food in the fridge and create/delete timers based on the information it receives from the camera. This device will also be outfitted with a gas sensor that can detect gasses commonly emitted by spoiled food (gaseous ammonia and hydrogen peroxide). This ‘smell’ information will supplement the timing information already available to the computer. For an advanced function, we will also create a Bluetooth link from the device to a smartphone, allowing the user's phone to also be alerted when food expires.

S.I.P. (Smart Irrigation Project)

Jackson Lenz, James McMahon

S.I.P. (Smart Irrigation Project)

Featured Project

Jackson Lenz

James McMahon

Our project is to be a reliable, robust, and intelligent irrigation controller for use in areas where reliable weather prediction, water supply, and power supply are not found.

Upon completion of the project, our device will be able to determine the moisture level of the soil, the water level in a water tank, and the temperature, humidity, insolation, and barometric pressure of the environment. It will perform some processing on the observed environmental factors to determine if rain can be expected soon, Comparing this knowledge to the dampness of the soil and the amount of water in reserves will either trigger a command to begin irrigation or maintain a command to not irrigate the fields. This device will allow farmers to make much more efficient use of precious water and also avoid dehydrating crops to death.

In developing nations, power is also of concern because it is not as readily available as power here in the United States. For that reason, our device will incorporate several amp-hours of energy storage in the form of rechargeable, maintenance-free, lead acid batteries. These batteries will charge while power is available from the grid and discharge when power is no longer available. This will allow for uninterrupted control of irrigation. When power is available from the grid, our device will be powered by the grid. At other times, the batteries will supply the required power.

The project is titled S.I.P. because it will reduce water wasted and will be very power efficient (by extremely conservative estimates, able to run for 70 hours without input from the grid), thus sipping on both power and water.

We welcome all questions and comments regarding our project in its current form.

Thank you all very much for you time and consideration!