Image as numerical data (pixels, channels) in Computer Vision - Model Pipeline Trace

Model Pipeline - Image as numerical data (pixels, channels)

This pipeline shows how an image is turned into numbers that a computer can understand. It breaks down the image into pixels and color channels, then uses these numbers to train a model that learns to recognize patterns.

Data Flow - 4 Stages

1Input Image

1 image of 28x28 pixels with 3 color channels→Raw image loaded as height x width x channels→28 rows x 28 columns x 3 channels

A photo of a red apple represented as a 28x28 grid with RGB values

↓

2Normalization

28 rows x 28 columns x 3 channels→Scale pixel values from 0-255 to 0-1→28 rows x 28 columns x 3 channels

Pixel value 255 becomes 1.0, pixel value 0 stays 0.0

↓

3Flattening

28 rows x 28 columns x 3 channels→Convert 3D image data into 1D array for model input→2352 features (28*28*3)

The 3D pixel grid becomes a long list of 2352 numbers

↓

4Model Training

2352 features→Train a simple neural network to classify images→Output probabilities for each class

Model predicts 0.8 probability for 'apple', 0.2 for 'banana'

Training Trace - Epoch by Epoch

Epoch 1: ************ (loss=1.2)
Epoch 2: *********    (loss=0.9)
Epoch 3: *******      (loss=0.7)
Epoch 4: *****        (loss=0.5)
Epoch 5: ****         (loss=0.4)

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.45	Model starts learning, accuracy is low
2	0.9	0.6	Loss decreases, accuracy improves
3	0.7	0.72	Model is learning important features
4	0.5	0.82	Good improvement, model is converging
5	0.4	0.88	Loss low, accuracy high, training successful

Prediction Trace - 4 Layers

Layer 1: Input Image

Layer 2: Normalization

Layer 3: Flattening

Layer 4: Neural Network Prediction

Model Quiz - 3 Questions

What does normalization do to the image pixel values?

A Changes image size from 28x28 to 14x14

B Scales pixel values from 0-255 to 0-1

C Converts color image to black and white

D Flattens the image into a 1D array

Key Insight

Images are made of pixels arranged in height, width, and color channels. Turning these pixels into numbers lets a model learn patterns. Normalizing and flattening prepare the data so the model can understand it and make predictions.

Practice

1. What does each pixel in a color image usually represent?

easy

A. A single number representing brightness only

B. A sound wave frequency

C. A text label describing the image

D. A set of numbers for red, green, and blue colors

Solution

1. Step 1: Understand pixel representation in color images

   Each pixel stores values for red, green, and blue channels to show color.

2. Step 2: Compare options to pixel data

   Only A set of numbers for red, green, and blue colors correctly describes pixels as sets of RGB numbers.

3. Final Answer:

   A set of numbers for red, green, and blue colors -> Option D

4. Quick Check:

   Pixel = RGB values [OK]

Hint: Pixels hold RGB numbers, not text or sound [OK]

Common Mistakes:

• Thinking pixels store text labels
• Confusing pixel with brightness only
• Assuming pixels represent sound

2. Which Python code correctly creates a 3x3 image with 3 color channels filled with zeros?

easy

A. image = np.zeros((3, 3, 3))

B. image = np.zeros(3, 3, 3)

C. image = np.zeros[3, 3, 3]

D. image = zeros((3, 3, 3))

Solution

1. Step 1: Recall numpy zeros syntax

   np.zeros requires a single tuple argument for shape, like (3, 3, 3).

2. Step 2: Check each option's syntax

   image = np.zeros((3, 3, 3)) uses correct tuple and function call syntax. Others have syntax errors or missing np.

3. Final Answer:

   image = np.zeros((3, 3, 3)) -> Option A

4. Quick Check:

   np.zeros((3,3,3)) creates 3x3 RGB image [OK]

Hint: Use np.zeros with shape tuple inside parentheses [OK]

Common Mistakes:

• Passing multiple arguments instead of a tuple
• Using square brackets instead of parentheses
• Forgetting np. prefix

3. Given this code:

import numpy as np
image = np.array([[[255, 0, 0], [0, 255, 0]],
                  [[0, 0, 255], [255, 255, 0]]])
print(image.shape)

What is the output?

medium

A. (2, 3, 2)

B. (3, 2, 2)

C. (2, 2, 3)

D. (3, 3, 3)

Solution

1. Step 1: Analyze the array structure

   The array has 2 rows, each with 2 pixels, each pixel has 3 color values (RGB).

2. Step 2: Determine shape order

   Shape is (height=2, width=2, channels=3), so (2, 2, 3).

3. Final Answer:

   (2, 2, 3) -> Option C

4. Quick Check:

   Shape = (rows, cols, channels) = (2, 2, 3) [OK]

Hint: Shape is (height, width, channels) in that order [OK]

Common Mistakes:

• Mixing up dimensions order
• Counting channels as first dimension
• Assuming square shape without checking

4. What is wrong with this code snippet for accessing the green channel of an image?

green_channel = image[:, :, 1:2]

medium

A. It returns a 3D array instead of 2D

B. It causes an index error

C. It accesses the red channel instead

D. It modifies the original image

Solution

1. Step 1: Understand slicing with 1:2

   Slicing with 1:2 keeps the channel dimension, returning shape (height, width, 1).

2. Step 2: Compare with expected 2D array

   To get a 2D array, use index 1 without slice, like image[:, :, 1].

3. Final Answer:

   It returns a 3D array instead of 2D -> Option A

4. Quick Check:

   Slicing with 1:2 keeps channel dim [OK]

Hint: Use single index, not slice, for 2D channel array [OK]

Common Mistakes:

• Using slice returns extra dimension
• Confusing channel indices
• Assuming it changes original image

5. You have a grayscale image stored as a 2D array with shape (100, 100). You want to convert it to a 3-channel RGB image by repeating the grayscale values across all channels. Which code correctly does this?

hard

A. rgb_image = np.repeat(gray_image, 3)

B. rgb_image = np.stack([gray_image]*3, axis=2)

C. rgb_image = gray_image.reshape(100, 100, 3)

D. rgb_image = np.concatenate(gray_image, 3)

Solution

1. Step 1: Understand the goal

   We want to create a 3D array where each pixel's grayscale value repeats in 3 channels.

2. Step 2: Check each method

   rgb_image = np.stack([gray_image]*3, axis=2) stacks the grayscale image 3 times along new channel axis correctly. rgb_image = np.repeat(gray_image, 3) repeats flattening data, wrong shape. rgb_image = gray_image.reshape(100, 100, 3) reshapes without adding channels, causing error. rgb_image = np.concatenate(gray_image, 3) has wrong syntax.

3. Final Answer:

   rgb_image = np.stack([gray_image]*3, axis=2) -> Option B

4. Quick Check:

   Stack repeats grayscale across channels [OK]

Hint: Use np.stack with axis=2 to add channels [OK]

Common Mistakes:

• Using np.repeat without axis
• Reshaping without adding channel dimension
• Wrong function syntax for concatenation