The rock-paper-scissors AI detector is a program that recognizes whether a person is indicating rock, paper, or scissors based on the sign made by their hands.
Simply upload a photo to the program, and the AI recognizes the symbol formed by the hand. We downloaded thousands of images and used our skills of Python and machine learning to create the knowledgeable AI utilized in this program.
Our process to successfully create this program couldn't be possible without the guidance and knowledge of AI Camp and its supportive staff. We are a team of 6 young individuals plus an experienced counselor, and we strive to discover the possibilities and opportunities sprouting from the use of coding and AI.
Our inspiration and purpose is to experiment with AI and machine learning to create a program that identifies images. This was a great way to start off a foundation of AI learning and to explore the potential of programming.
We decided what our product would be during our first three days. Everyone came up with different ideas, and we decided to make a rock paper scissors detector because it’s a fun topic which would help us learn about AI and programming without spending lots of time trying to find good data for the model.
After we finalized what our project would be, the next step was to collect the data that would be used to train the AI. We downloaded a set of over 2000 images of hands with rock, paper, or scissor hand gestures, and used labelbox to label the images as rock, paper, or scissors and drew bounding boxes around the hands in the image.
The group split into three teams.
The labeled data was downloaded as a csv file from labelbox. The first group downloaded all of the images from the csv file. The second team used the file to describe the dimensions of the bounding boxes and quantify the data in a text file. The third team used the image and text files created by the first two teams to create three folders for the data called train, test, and valid. These folders were used to train the neural network.
When the data organization was completed, the neural network for our model was set up. The organized data was used to train our neural network.
After training the AI, our group split up into two teams to complete the website. One team designed the website, and the other team made sure that the website would work with the AI.
The backgrounds of our images were all the same, which caused the AI to have a difficult time identifying hands with other backgrounds. This was fixed by changing the backgrounds of the images to different colors for variation. The images were also difficult to label at first in labelbox.
A data labeling and management system used to prepare training data. In Labelbox, we labeled thousands of photos as rock, paper, or scissors and the AI learned to differentiate the three through patterns.
A real time image detector, which we trained to detect rock, paper, and scissors hand gestures
A coding center which was used to format and organize the data and train the neural network. Here we wrote and tested all of our code using Jupyter notebooks and Linux terminals.
I am a student at Poolesville High School. I joined AI camp because it was something I could do with python and it sounded fun. I really enjoyed learning new things about AI and python coding.
Hey, I’m Mason and i’m a student at Upper Arlington High School. I’m interested in everything. And with AI, you can do anything. That’s why I love it so much.
I will be a sophomore at the International Istanbul Community School this upcoming semester. I helped work on organizing the data and designing the website. Having no prior knowledge of AI or python before joining AI Camp, creating an AI was difficult but very rewarding and fun. I hope to continue to work with python later in life and to use the skills I learned here.
I'm a Millis High School student, and I am very interested in the future of AI and computer science. I am doing this AI camp because I love learning new things, and thought that this program would be a great experience.
I am a Walter Payton College Preparatory High School student from Chicago, Illinois. I find the concept of AI and the code behind it extrmely interesting. The possibilities of machine learning and AI never end. In the future, coding and digital expertise will be a necessity to exploring all the amazing oppurtuinites stemming from AI. This program is just the start to my journey and my love for AI.
I am 15 years old and will be a sophomore in highschool this school year. I worked on downloading the data for the model as images to train the neural network and on writing the content of the website. I enjoyed working with the data and learning how to use python to work with different files.
I'm an undergrad student at UTD majoring in software engineering with a domain in artificial intelligence and cognitive modeling. I have a wide range of interests in AI across the board, lending me a vast but shallow knowledge of AI. My hope is that I've imparted some of my interests on everyone I got to work with!