Text recognition pipeline in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Key stages in a text recognition pipeline

Which of the following lists the correct main stages of a typical text recognition pipeline in order?

A Text detection → Text segmentation → Text recognition → Post-processing

B Text recognition → Text detection → Text segmentation → Post-processing

C Text segmentation → Text detection → Text recognition → Post-processing

D Post-processing → Text detection → Text segmentation → Text recognition

💡 Hint

Think about first finding where text is, then breaking it down, then reading it.

The pipeline starts by detecting text regions, then segments characters or words, then recognizes the text, and finally applies post-processing to improve accuracy.

❓ Predict Output

intermediate

Output shape of CNN feature extractor in text recognition

Given the following PyTorch CNN feature extractor code for text recognition, what is the shape of the output tensor if the input image batch has shape (8, 1, 32, 128)?

Computer Vision

import torch
import torch.nn as nn

class FeatureExtractor(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(1, 64, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(2, 2),  # halves H and W
            nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(2, 2)   # halves H and W again
        )

    def forward(self, x):
        return self.conv(x)

model = FeatureExtractor()
input_tensor = torch.randn(8, 1, 32, 128)
output = model(input_tensor)
output.shape

A (8, 128, 8, 32)

B (8, 128, 16, 64)

C (8, 64, 8, 32)

D (8, 64, 16, 64)

💡 Hint

Each MaxPool2d halves height and width. Calculate step by step.

Input height 32 → after first pool 16 → after second pool 8. Width 128 → 64 → 32. Final channels 128.

❓ Model Choice

advanced

Best model type for recognizing variable-length text sequences

Which model architecture is best suited for recognizing variable-length text sequences in images, such as handwritten words or license plates?

A K-Nearest Neighbors classifier on raw pixel values

B Simple feedforward neural network with fixed-size input and output

C Convolutional Neural Network (CNN) followed by a Recurrent Neural Network (RNN) with CTC loss

D Support Vector Machine with linear kernel on flattened image

💡 Hint

Think about models that handle sequences and variable lengths.

CNN extracts features, RNN models sequence dependencies, and CTC loss allows variable-length outputs without alignment.

❓ Metrics

advanced

Choosing the best metric for text recognition accuracy

Which metric is most appropriate to evaluate the accuracy of a text recognition model that outputs sequences of characters?

A Mean Squared Error (MSE)

B Precision and Recall on image regions

C Accuracy on individual pixels

D Character Error Rate (CER)

💡 Hint

Consider metrics that compare predicted text sequences to ground truth text.

CER measures the number of character insertions, deletions, and substitutions needed to match the prediction to the true text, making it ideal for text recognition.

🔧 Debug

expert

Identifying the cause of poor text recognition accuracy

A text recognition model trained on clear printed text images performs poorly on handwritten text images. Which is the most likely cause?

A The loss function used is Mean Squared Error instead of Cross-Entropy

B The training data distribution does not match the test data distribution

C The optimizer used is incompatible with text recognition tasks

D The model architecture cannot handle images larger than 64x64 pixels

💡 Hint

Think about differences between training and testing data.

Models trained on one style of text often fail on very different styles due to distribution mismatch, requiring domain adaptation or more diverse training data.