Image properties (shape, dtype, size) in Computer Vision - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does the shape property of an image represent?

The shape property shows the dimensions of the image, usually as (height, width, channels). It tells how tall, wide, and how many color channels the image has.

beginner

What is dtype in the context of an image?

dtype means the data type of the image pixels, like uint8 for values 0-255 or float32 for decimal values. It affects how pixel values are stored and processed.

beginner

How do you find the total number of pixels in an image?

Multiply the height by the width of the image. For example, an image with shape (100, 200) has 100 × 200 = 20,000 pixels.

intermediate

What does the size property of an image tell you?

size gives the total number of elements (pixels × channels) in the image array. For example, a 100×200 RGB image has size 100 × 200 × 3 = 60,000.

intermediate

Why is knowing the dtype important when working with images?

Because it affects memory use and how pixel values are interpreted. For example, uint8 stores integers 0-255, while float32 can store decimals, which is important for some image processing tasks.

What does the shape (64, 64, 3) of an image mean?

A 64 pixels total with 3 channels

B Width 64, height 64, 3 color channels

C 3 images of size 64x64

D Height 64, width 64, 3 color channels

The shape is (height, width, channels), so 64 height, 64 width, and 3 color channels (like RGB).

If an image has dtype uint8, what is the range of pixel values?

A -128 to 127

B 0 to 1

C 0 to 255

D Any decimal number

uint8 means unsigned 8-bit integers, so pixel values range from 0 to 255.

How do you calculate the total number of pixels in an image?

A Multiply height by width

B Add height and width

C Multiply channels by width

D Divide height by width

Total pixels = height × width.

What does the size property of an image array represent?

A Number of color channels

B Total number of elements (pixels × channels)

C Width of the image

D Height of the image

Size is the total number of elements in the array, including all pixels and channels.

Why might you convert an image's dtype from uint8 to float32?

A To allow decimal pixel values for precise calculations

B To reduce memory usage

C To increase pixel value range to 0-65535

D To make the image grayscale

float32 allows decimal values, useful for some image processing and neural network inputs.

Explain what the shape, dtype, and size properties of an image tell you.

Think about how these properties describe the image's structure and data.

Describe why understanding image properties is important before processing images in machine learning.

Consider how these properties affect model training and predictions.

Practice

1. What does the shape property of an image represent?

easy

A. The file size of the image in bytes

B. The data type of the pixel values

C. The dimensions and number of color channels of the image

D. The compression level of the image

Solution

1. Step 1: Understand what shape means in images

   The shape of an image is a tuple that shows its height, width, and number of color channels.

2. Step 2: Differentiate shape from other properties

   File size and data type are different properties; shape specifically refers to dimensions and channels.

3. Final Answer:

   The dimensions and number of color channels of the image -> Option C

4. Quick Check:

   Shape = dimensions + channels [OK]

Hint: Shape always shows height, width, and channels [OK]

Common Mistakes:

• Confusing shape with file size
• Mixing up data type with shape
• Thinking shape shows compression

2. Which of the following is the correct way to get the data type of an image stored in a NumPy array named img?

easy

A. img.dtype

B. img.type()

C. img.data_type

D. img.get_dtype()

Solution

1. Step 1: Recall NumPy syntax for data type

   In NumPy, the data type of an array is accessed using the dtype attribute.

2. Step 2: Check each option

   Only img.dtype is valid syntax; others are incorrect or do not exist.

3. Final Answer:

   img.dtype -> Option A

4. Quick Check:

   Use .dtype to get data type [OK]

Hint: Use .dtype attribute for NumPy array data type [OK]

Common Mistakes:

• Using parentheses like a function
• Trying non-existent attributes
• Confusing dtype with type() function

3. Given the following code:

import numpy as np
img = np.zeros((100, 200, 3), dtype=np.uint8)
print(img.size)

What will be the output?

medium

A. 3

B. 60000

C. 200

D. 100

Solution

1. Step 1: Understand the shape and size

   The image shape is (100, 200, 3). Size is total number of elements = 100 * 200 * 3 = 60000.

2. Step 2: Confirm what .size returns

   The size attribute returns total pixels including all channels.

3. Final Answer:

   60000 -> Option B

4. Quick Check:

   Size = height * width * channels = 60000 [OK]

Hint: Multiply all shape dimensions for size [OK]

Common Mistakes:

• Using only height or width as size
• Ignoring color channels in size
• Confusing size with shape

4. Consider this code snippet:

import numpy as np
img = np.array([[255, 128], [64, 0]])
print(img.shape)
print(img.dtype)

What is the error in this code if the goal is to represent a color image?

medium

A. The array values are out of range for images

B. The dtype should be float instead of int

C. The shape attribute is called incorrectly

D. The array shape lacks a color channel dimension

Solution

1. Step 1: Check the array shape

   The array shape is (2, 2), meaning 2 rows and 2 columns, no color channels.

2. Step 2: Understand color image requirements

   A color image needs 3 dimensions: height, width, and channels (usually 3 for RGB).

3. Final Answer:

   The array shape lacks a color channel dimension -> Option D

4. Quick Check:

   Color images need 3D shape [OK]

Hint: Color images need 3D shape (height, width, channels) [OK]

Common Mistakes:

• Thinking dtype must be float for images
• Assuming shape attribute is wrong
• Believing pixel values are out of range

5. You have a grayscale image loaded as a NumPy array with shape (256, 256) and dtype float32. You want to convert it to an 8-bit unsigned integer image suitable for display. Which code snippet correctly does this?

hard

A. img_uint8 = (img * 255).astype(np.uint8)

B. img_uint8 = img.astype(np.uint8)

C. img_uint8 = img / 255

D. img_uint8 = img.astype(np.float64)

Solution

1. Step 1: Understand dtype conversion needs

   Converting from float32 (0 to 1 range) to uint8 (0 to 255) requires scaling by 255.

2. Step 2: Check each option

   img_uint8 = (img * 255).astype(np.uint8) scales and converts correctly. img_uint8 = img.astype(np.uint8) converts without scaling, causing wrong values. Options A, B, and D do not convert to uint8 properly.

3. Final Answer:

   img_uint8 = (img * 255).astype(np.uint8) -> Option A

4. Quick Check:

   Scale float to 255 then convert to uint8 [OK]

Hint: Multiply floats by 255 before uint8 conversion [OK]

Common Mistakes:

• Skipping scaling before type conversion
• Using wrong dtype conversion
• Dividing instead of multiplying