Class 10 AI Chapter - Computer Vision Topic - CV Application - Arvindzeclass

Class 10 Artificial Intelligent Code 417 Solutions

Session 2025-26

Artificial Intelligence code 417 syllabus pdf class 10 solutions. Class 10 AI Book. Part - A, Part - B, and Python. This article provides complete solution for class 10 AI (Artificial Intelligence) Code - 417 solution according to new syllabus 2025 – 26. In this article first of all go through the AI Code - 417 syllabus and then follow chapter wise notes. Class 10 AI MCQs Quiz with answers.

Part A - Employability Skills Notes

Chapter 1 - Communication Skills - II

Chapter 2 - Self Management Skills - II

Chapter 3 - ICT Skill - II

Chapter 4 - Entrepreneurial Skills - II

Chapter 5 - Green Skills - II

Part B - Subject Specific Skills Notes

Chapter 1 -AI Project Cycle & Ethics

Chapter 2 - Modelling in AI

Chapter 3 - Evaluating Models

Chapter 4 - Statistical Data

Chapter 5 - Computer Vision

Computer Vision

Chapter 6 - Natural Language Processing

Chapter 7 - Advance Python

Computer Vision

Computer Vision is a branch of Artificial Intelligence (AI) that enables computers to see, understand, and interpret images and videos just like humans understand the world through their eyes and brain.

Definition

Computer Vision is a field of AI that enables machines to perceive and understand visual information (like images or videos) in the same way humans use their eyes and brain to see and interpret the world.

In simple words:

Computer Vision = Teaching computers how to “see” like humans.

Computer Vision Vs Human Vision System

Human Vision

Eyes see an object (for example, a cat).
The optic nerve carries this visual signal to the brain.
The brain processes the information → “This is a cat.”

Computer Vision

A camera captures an image of a cat.
The computer converts the image into numeric values (pixels).
Machine learning / neural network model analyzes these pixels.
It identifies the object → “This is a cat.”

Real-Life Examples

Face unlock in smartphones
Self-driving cars recognizing road signs
CCTV detecting suspicious activities
Google Lens reading text from images

Computer Vision and Artificial Intelligence

Artificial Intelligence is the brain

AI is the broad field focused on making machines think, learn, and make decisions like humans.

Computer Vision & Artificial Intelligence

Computer Vision is the eyes

Computer Vision is a part of AI that gives machines the ability to see and understand visual information.

Without AI, Computer Vision cannot understand what it sees.
Without Computer Vision, AI cannot see the world.

Step-by-step relationship

AI is the main technology
It teaches machines to be intelligent.
Computer Vision is a subfield of AI
It specifically focuses on visual intelligence.
CV works inside AI to provide visual input
It converts raw images or videos into meaningful information.
AI uses that visual information to make decisions
After CV recognizes objects, AI decides what to do with that information.

Computer Vision & Image Processing

Computer Vision (CV)

Definition:

Computer Vision is a branch of Artificial Intelligence (AI) that enables computers or machines to see, interpret, and understand images or videos in the same way humans do.

Key Points:

Focuses on understanding the visual content.
Uses AI, Machine Learning, and Deep Learning to recognize objects, faces, actions, or patterns.
Goal: Enable machines to make decisions based on visual data.

Example Applications:

Face recognition in smartphones
Self-driving cars detecting pedestrians and traffic signs
CCTV security monitoring
Medical diagnosis from X-ray or MRI images

Image Processing (IP)

Definition:

Image Processing is a technique to enhance, manipulate, or transform images using algorithms, often for better visualization or preparation for further analysis.

Key Points:

Focuses on processing the image itself, not necessarily understanding it.
Methods include filtering, noise removal, sharpening, edge detection, resizing, color correction.
Often a pre-step for Computer Vision.

Example Applications:

Removing noise from satellite images
Adjusting brightness/contrast of photos
Scanning and cleaning old documents
Preparing images for facial recognition

Relationship Between CV and IP

Image Processing is a tool for Computer Vision
- CV needs good-quality images to analyze → IP enhances or prepares these images.
Purpose Difference
- IP: Focused on improving the image
- CV: Focused on understanding the content

Quick Definitions

Computer Vision: Ability of machines to perceive, understand, and interpret visual data.
Image Processing: Techniques to manipulate or improve images for analysis or display.

Applications of computer vision

Major Applications of Computer Vision

Application	What it does
Facial Recognition	Identifies or verifies a person from their face
Face Filters	Adds virtual effects/masks on a face in real time
Google Search by Image	Finds information using an uploaded picture
Retail	Helps in product recognition, billing, stock monitoring
Self-Driving Cars	Detects surroundings and helps the car drive safely
Medical Imaging	Helps doctors detect diseases from X-rays, MRI, CT scans
Google Translate App	Reads and translates text from image in real time

1. Facial Recognition

The system scans a person's face
Extracts unique features like eyes, nose, jawline, etc.
Compares them with stored database
Confirms identity

Example:
Phone face unlock, airport security, attendance system.

2. Face Filter (AR filters)

Camera detects a person’s face in real-time
Computer Vision tracks landmarks (eyes, nose, mouth)
Augmented Reality (AR) overlays a mask, crown, dog ears, etc., accurately following movement

Example:
Instagram, Snapchat, TikTok face filters.

3. Google Search by Image

You upload a picture
CV analyzes objects, shapes, text, and background
It searches the internet for visually similar items
Returns info, product name, source website, etc.

Example:
Finding a product online just by clicking its photo.

4. Computer Vision in Retail

Identifies products automatically
Helps with smart billing and stock management
Recognizes shoplifting or unusual behavior (smart CCTV)
Enables cashier-less stores

Example:
Amazon Go stores → you pick items and walk out, no checkout counter.

5. Self-Driving Cars

CV acts as the "eyes" of the car
Detects pedestrians, traffic signs, lanes, other vehicles
Sends information to AI for decision-making (stop/slow/turn)

Example:
Tesla Autopilot, Google Waymo.

6. Medical Imaging

Analyzes scans like X-rays, MRIs, CT scans
Detects tumors, fractures, blood vessel blockages, etc.
Helps doctors diagnose faster and accurately

Example:
AI helping radiologists detect early signs of cancer.

7. Google Translate App (Real-time translation)

The camera captures printed text from books, signboards, menus, etc.
CV detects and reads the text (OCR: Optical Character Recognition)
AI translates it into your language instantly
The translated text appears on the screen over the original

Example:
Translating a foreign signboard while traveling.

Summary in One Line

Computer Vision enables machines to see and understand the world, and is used in daily life everywhere — from unlocking phones to medical diagnosis, from translating text to helping cars drive.

Computer Vision Tasks

A. Single Object Tasks

These tasks assume only ONE main object in the image.

1. Image Classification

The model identifies what the object is.

Input: image with a single object
Output: the label (name/object category)

Example:
Image → 🐶
Output → “Dog”

There is no location information, only the category.

2. Classification + Localization

The model identifies what the object is AND where it is located.

It gives two outputs:
1. The category (e.g., “Dog”)
2. The bounding box (the rectangle around the object)

Example:
Image → 🐶 in a garden
Output → “Dog at these coordinates (x,y,w,h)”

This still assumes one main object, but also marks its position.

B. Multiple Object Tasks

In these tasks, the image contains many objects of different types, and the model must identify each one separately.

3. Object Detection

Detects all objects in the image and draws a bounding box around each of them.

Output:
- Object class (what it is)
- Bounding box (where it is)

Example:
Image → road scene
Output → “Car”, “Person”, “Traffic light”, each with its own box.

However, object detection doesn’t understand object shape, only boxes.

4. Instance Segmentation

Detects and outlines each object pixel-by-pixel, not just a box.

It is more detailed than object detection.
Also distinguishes different instances of the same object.

Example:
If there are 3 people:

Instance segmentation gives three separate masks (shape outlines)
Not just three boxes

This is used in self-driving cars, medical imaging, AR, etc.

Summary Table

Category	Task	Purpose	Output
Single Object	Classification	What is it?	Label only
Single Object	Classification + Localization	What & Where?	Label + box
Multiple Objects	Object Detection	What & Where (for ALL)	Labels + boxes
Multiple Objects	Instance Segmentation	Exact shape & position	Labels + pixel-level masks