Image segmentation basics in TensorFlow

Introduction

Image segmentation helps computers understand pictures by dividing them into meaningful parts. It tells which pixels belong to which object.

To separate a cat from the background in a photo.

To find roads and buildings in satellite images.

To detect tumors in medical scans.

To count fruits on a tree in an orchard photo.

To help self-driving cars recognize lanes and obstacles.

Syntax

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.InputLayer(input_shape=(height, width, channels)),
    tf.keras.layers.Conv2D(filters, kernel_size, activation='relu', padding='same'),
    tf.keras.layers.Conv2D(num_classes, 1, activation='softmax')
])

This is a simple example of a segmentation model using convolution layers.

The last layer uses softmax to predict class for each pixel.

Examples

Model for 128x128 RGB images with 2 classes (e.g., object and background).

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.InputLayer(input_shape=(128, 128, 3)),
    tf.keras.layers.Conv2D(32, 3, activation='relu', padding='same'),
    tf.keras.layers.Conv2D(2, 1, activation='softmax')
])

Model for 256x256 grayscale images with 3 classes.

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.InputLayer(input_shape=(256, 256, 1)),
    tf.keras.layers.Conv2D(64, 5, activation='relu', padding='same'),
    tf.keras.layers.Conv2D(3, 1, activation='softmax')
])

Sample Model

This code builds a simple image segmentation model, trains it on random data, and shows prediction results.

TensorFlow

import tensorflow as tf
import numpy as np

# Create a simple segmentation model
model = tf.keras.Sequential([
    tf.keras.layers.InputLayer(input_shape=(64, 64, 3)),
    tf.keras.layers.Conv2D(16, 3, activation='relu', padding='same'),
    tf.keras.layers.Conv2D(2, 1, activation='softmax')
])

# Compile the model
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

# Create dummy data: 10 images of 64x64 with 3 channels
x_train = np.random.random((10, 64, 64, 3)).astype(np.float32)
# Create dummy labels: 10 images with 64x64 pixels, each pixel labeled 0 or 1
y_train = np.random.randint(0, 2, (10, 64, 64)).astype(np.int32)

# Train the model for 1 epoch
history = model.fit(x_train, y_train, epochs=1, batch_size=2)

# Predict on one image
pred = model.predict(x_train[:1])

# Show shape of prediction and first pixel class probabilities
print('Prediction shape:', pred.shape)
print('First pixel class probabilities:', pred[0, 0, 0])

Important Notes

Image segmentation models predict a class for every pixel, unlike classification models that predict one label per image.

Softmax activation is used in the last layer to get probabilities for each class per pixel.

Training requires images and matching pixel-wise labels (masks).

Summary

Image segmentation divides images into parts by labeling each pixel.

Simple models use convolution layers and softmax to predict pixel classes.

Training needs images and pixel-level labels (masks).

Practice

1. What is the main goal of image segmentation in TensorFlow?

easy

A. To compress images without losing quality

B. To label each pixel in an image with a class

C. To generate random noise images

D. To classify the entire image into one category

Solution

1. Step 1: Understand image segmentation purpose

   Image segmentation assigns a class label to every pixel, dividing the image into meaningful parts.

2. Step 2: Compare with other tasks

   Unlike classification, which labels the whole image, segmentation works at pixel level.

3. Final Answer:

   To label each pixel in an image with a class -> Option B

4. Quick Check:

   Image segmentation = pixel-wise labeling [OK]

Hint: Segmentation means labeling pixels, not whole images [OK]

Common Mistakes:

• Confusing segmentation with image classification
• Thinking segmentation compresses images
• Believing segmentation creates random images

2. Which TensorFlow layer is commonly used to extract features for image segmentation?

easy

A. Convolutional layer

B. Dense layer

C. Dropout layer

D. Flatten layer

Solution

1. Step 1: Identify feature extraction layers

   Convolutional layers scan images to find patterns and features useful for segmentation.

2. Step 2: Understand other layers' roles

   Dense layers are for classification, dropout prevents overfitting, flatten reshapes data but doesn't extract features.

3. Final Answer:

   Convolutional layer -> Option A

4. Quick Check:

   Feature extraction = convolutional layers [OK]

Hint: Convolutional layers find image features [OK]

Common Mistakes:

• Choosing dense layers for feature extraction
• Confusing flatten with convolution
• Ignoring convolution's role in images

3. What will be the shape of the output tensor after applying a softmax activation on a segmentation model predicting 3 classes for a 128x128 image?

medium

A. (128, 128, 3)

B. (3, 128, 128)

C. (128, 3, 128)

D. (128, 128)

Solution

1. Step 1: Understand output shape for segmentation

   Each pixel has a probability for each class, so output shape is height x width x classes.

2. Step 2: Apply to given image and classes

   Image size is 128x128, classes are 3, so output shape is (128, 128, 3).

3. Final Answer:

   (128, 128, 3) -> Option A

4. Quick Check:

   Output shape = (height, width, classes) [OK]

Hint: Output shape = image size + number of classes [OK]

Common Mistakes:

• Mixing class dimension position
• Forgetting classes dimension
• Using 2D shape instead of 3D

4. Given this TensorFlow code snippet for segmentation, what is the error?

model = tf.keras.Sequential([
  tf.keras.layers.Conv2D(16, 3, activation='relu', input_shape=(64, 64, 3)),
  tf.keras.layers.Dense(3, activation='softmax')
])

medium

A. Conv2D kernel size must be 1

B. Input shape is incorrect for images

C. Activation 'relu' is invalid

D. Dense layer cannot follow Conv2D without flattening

Solution

1. Step 1: Check layer sequence

   Conv2D outputs 4D tensor, Dense expects 2D input, so flattening is needed before Dense.

2. Step 2: Validate other options

   Input shape is valid for images, 'relu' is a valid activation, kernel size 3 is allowed.

3. Final Answer:

   Dense layer cannot follow Conv2D without flattening -> Option D

4. Quick Check:

   Dense after Conv2D needs flattening [OK]

Hint: Dense layers need flat input, add Flatten after Conv2D [OK]

Common Mistakes:

• Ignoring tensor shape mismatch
• Thinking kernel size must be 1
• Misunderstanding activation functions

5. You want to train a simple segmentation model in TensorFlow. Which data do you need to provide during training?

hard

A. Only images without labels

B. Images and image-level class labels

C. Images and their pixel-level masks

D. Random noise images

Solution

1. Step 1: Identify training data for segmentation

   Segmentation requires images and masks labeling each pixel's class to learn pixel-wise predictions.

2. Step 2: Compare with other data types

   Image-level labels are for classification, no labels means no supervision, noise images are irrelevant.

3. Final Answer:

   Images and their pixel-level masks -> Option C

4. Quick Check:

   Training segmentation = images + pixel masks [OK]

Hint: Segmentation training needs pixel masks, not just labels [OK]

Common Mistakes:

• Using only image-level labels
• Training without masks
• Confusing segmentation with classification data