Scribd
Upload
5 views6 pages

Ai Exp 1

The document outlines an AI project using PictoBlox to create a Logo Quiz game, where users identify logos with AI assistance. It details the steps for setting up the project, including enabling AI extensions, training models, and implementing game logic. The project aims to enhance technical skills in AI and programming while providing an engaging learning experience.

Uploaded by

amishav2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
5 views6 pages

Ai Exp 1

The document outlines an AI project using PictoBlox to create a Logo Quiz game, where users identify logos with AI assistance. It details the steps for setting up the project, including enabling AI extensions, training models, and implementing game logic. The project aims to enhance technical skills in AI and programming while providing an engaging learning experience.

Uploaded by

amishav2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 6

Experiment – 1

Activity Based – Implement any one project from - STEMpedia Projects


Learning To get an insight into AI projects
Objective:
Learning Student will be able get hands on with AI projects
Outcome:
Course CSL604.3
Outcome:
Program (P Design/ development of solutions: Breadth and uniqueness of engineering
Outcome: problems i.e. the extent to which problems are original and to which solutions have
previously been identified or codified
(PO 12) Life Long Learning

Bloom's Analysis,Create
Taxonomy
Level:
What is PictoBlox?
Theory: PictoBlox is a visual programming software based on Scratch that supports AI and
machine learning extensions. It enables users to create interactive projects with
features like AI, speech recognition, and more.

Theory for Making a Logo Quiz


Objective:
The objective of the quiz is to display a logo to the player and have the AI
recognize it. The player will input their guess, and the program will evaluate the
answer.

Steps to Create the Logo Quiz


1. Define the Goal:
 Build a game where users can identify logos and test their knowledge.
 Integrate AI to recognize logos from the user's camera or image uploads.

2. Requirements:
 PictoBlox software with AI extension enabled.
 Images of logos for the quiz.
 Internet connection for AI features.

3. Steps in PictoBlox:
Step 1: Enable the AI Extension
1. Open PictoBlox.
2. Go to the "Extensions" tab.
3. Add the "Artificial Intelligence" extension.

Step 2: Load Logo Images


 Import logo images into your project as backdrops or sprites.

Step 3: Train the AI Model


1. Use the "Train Machine Learning Model" feature in the AI extension.
2. Create a new project for logo recognition.
3. Add images of logos in separate categories (e.g., "Nike," "Apple,"
"McDonald's").
4. Train the model with a sufficient dataset for each category.

Step 4: Set Up the Game Logic


1. Create a start screen that introduces the quiz and provides instructions.
2. Display a logo from your dataset.
3. Use AI to analyze the user's guess:
o Use text input blocks to allow the user to type their guess.
o Match the user's input with the AI’s recognition output.

Step 5: Provide Feedback


 If the user guesses correctly, display a "Correct!" message and move to the
next logo.
 If incorrect, display a "Try Again" message.

Step 6: Add Scoring and Levels


 Award points for correct answers.
 Create levels with increasing difficulty by showing more challenging logos.

Step 7: Test the Game


 Test the project thoroughly to ensure the AI correctly identifies logos and
handles user input effectively.

Algorithm : 1. Image Recognition Algorithm


The core algorithm for logo recognition involves Convolutional Neural
Networks (CNNs). CNNs are widely used for image-related tasks because
they can:
 Extract meaningful features from images.
 Identify patterns such as shapes, colors, and edges.

2. Steps in the Algorithm


Step 1: Preprocessing
 Convert the input logo image into a standardized format (e.g., resize,
normalize pixel values).
 Enhance the image if needed (e.g., remove noise).
Step 2: Feature Extraction
 Use CNN layers to scan the image and extract features like edges, corners,
and textures.
 Features are organized hierarchically:
o Early layers detect simple features (e.g., lines, corners).
o Deeper layers detect complex patterns (e.g., logo shapes, text).
Step 3: Classification
 The extracted features are passed through a fully connected layer of the
neural network.
 The network predicts a probability distribution over possible logo
categories.
Step 4: Output Prediction
 The category with the highest probability is selected as the recognized
logo.
 Compare the prediction with user input to determine correctness.

3. Algorithm Flow
1. Input: An image of the logo (from a file or webcam feed).
2. Preprocessing:
o Resize the image to match the input size required by the model.
o Normalize pixel values.
3. Feature Extraction:
o Pass the image through CNN layers.
4. Classification:
o Predict the logo category using the trained machine learning model.
5. Output: Provide feedback to the user:
o Correct if the user's guess matches the predicted category.
o Incorrect otherwise.

Data Set : FlickrLogos-32

Outcome :
Conclusion : The Logo Quiz Project in PictoBlox showcases the practical use of AI for image
recognition in a fun, interactive game. It enhances technical skills in dataset
preparation, AI model training, and logical programming. The project is an
engaging way to learn AI concepts with potential for advanced features and
broader applications.
References: https://ai.thestempedia.com/project/make-logo-quiz-using-the-artificial-
intelligence-extension-in-pictoblox/

https://thestempedia.com/blog/simple-ai-and-machine-learning-projects-for-
students-and-beginners/

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy