DELHI PUBLIC SCHOOL

NACHARAM

Class: X

Topic: Computer Vision (CV)

1. Explain the term resolution with an example.

Ans:

● Resolution refers to the number of pixels that make up an image or screen, determining how much detail it can
present.
● "pixel" means a picture [Link] the smallest unit of information that make up a picture

● Higher resolution means more pixels, giving a clearer and sharper image.

● Resolution is written as width × height in pixels.

Example: A screen with a resolution of 1280 × 1024 has:
● 1280 pixels across (width)

● 1024 pixels from top to bottom (height)

More pixels = better image quality.
2. What is a "byte image" format in the context of digital images?

Ans:A byte image is a common pixel format used in digital images. In this format, each pixel is stored as an
8-bit integer (1 byte), which can represent values from 0 to 255.

● 0 represents black (no color or brightness).

● 255 represents white (full color or brightness).

● Values between 0 and 255 represent different shades of gray or color intensity.
We have a maximum value of 255 because:
● Each pixel uses 8 bits (1 byte).
● Each bit can be either 0 or 1, giving 2 possible values.

● Therefore, the total number of possible values is 2⁸ = 256, which means the values range from 0 to 255.

3. Differentiate Computer vision and Image processing

Ans
 Computer Vision Image Processing

Deals with extracting meaningful information from images Focuses on processing raw images to
or videos and interpreting them to understand or predict the enhance them or prepare them for
visual input. further tasks.

It is a superset of Image Processing. It is a subset of Computer Vision.

Examples: Object detection, Handwriting recognition, etc. Examples: Rescaling images, correcting
brightness, Changing tones, etc.

4. Explain Computer Vision with three applications

Ans:The Computer Vision domain of Artificial Intelligence, enables machines to see through images or
visual data, process and analyse them on the basis of algorithms and methods to analyse actual
phenomena with images.

Applications:

1. Face Recognition – Recognizes and verifies people by analyzing their facial features.
2. Object Detection – Detects and identifies objects like cars, people, or animals in images or videos.
3. Medical Imaging – Helps doctors detect diseases by analyzing X-rays, MRI, or CT scan images.

5. Briefly explain computer vision tasks with examples

Ans:The tasks used in a computer vision application are:

1. Single Objects
a. Image Classification
● Assigns an entire image one label from a predefined set of categories.
● Used to Identify what is in the image.
● Ex:Medical images classified as healthy vs. diseased (e.g., chest X-ray: pneumonia vs. normal).
b. Classification+ Localisation
● This is the task that involves both processes of identifying what object is present in the image and
at the same time identifying at what location that object is present in that image.
● It is used only for single objects.
● Ex:A smart camera that identifies a person and draws a box around them.
2. Multiple Objects
a. ObjectDetection
 ● Object detection is the process of finding instances of real-world objects such as faces, bicycles,
and buildings in images or videos.
● Object detection algorithms typically use extracted features and learning algorithms to recognize
instances of an object category.
● Ex:It is commonly used in applications such as image retrieval and automated vehicle parking
systems. Self-driving cars detecting vehicles, pedestrians, traffic lights, etc.
b. Instance Segmentation
● Instance Segmentation is the process of detecting instances of the objects, giving them a
category, and then giving each pixel a label based on that.
● A segmentation algorithm takes an image as input and outputs a collection of regions (or
segments).
● Ex:Medical imaging: outlining exact tumor regions on MRI/CT scans.
Photo editing apps like Photoshop selecting objects with pixel accuracy (e.g., selecting a person
to blur the background).
6. Differentiate between Gray scale images and RGB images

Ans: Grayscale Images

● Grayscale images contain only shades of gray and have no apparent color.

● The darkest shade is black, which represents a pixel value of 0 (no color).

● The lightest shade is white, which represents a pixel value of 255 (full intensity).

● Intermediate shades of gray are formed by equal brightness levels of the three primary colors.

● A grayscale image has only one channel, and each pixel is stored in 1 byte.

● Therefore, a grayscale image can be stored as a 2D array of pixels.

● Image size = Height × Width.

2. RGB Images

● All images we commonly see around us are colored images.

● Color images are created using three primary colors: Red, Green, and Blue.

● Any visible color is produced by combining different intensities of red, green, and blue.

● Every RGB image is stored using three separate channels:R (Red) channel,G (Green) channel,B (Blue)
channel.
● Each channel is a 2D layer containing pixel values from 0 to 255, which represent the intensity of that
color component.

● When these three layers are combined, they produce the final color image.

● Thus, each pixel in an RGB image contains three values (R, G, B), one from each channel.

● If we split an RGB image into R, G, and B channels, each channel looks like a grayscale image because:
The pixel values again range from 0 to 255
0 = black, 255 = white