Handwriting recognition basics in Computer Vision - Model Metrics & Evaluation

Metrics & Evaluation - Handwriting recognition basics

Which metric matters for handwriting recognition and WHY

For handwriting recognition, accuracy is important because it shows how many characters or words the model gets right. But accuracy alone can be misleading if some characters appear much more often than others. So, we also look at precision and recall to understand how well the model finds the correct characters without mistakes or misses. For example, recall tells us if the model misses some letters, and precision tells us if the model wrongly guesses letters. The F1 score balances both precision and recall, giving a clear picture of overall performance.

Confusion matrix example for handwriting recognition

      Confusion Matrix (for 3 characters: A, B, C)

          Predicted
          A   B   C
    A   50   2   3
    B    4  45   1
    C    2   3  48

    Explanation:
    - True Positives (TP) for 'A' = 50 (correctly recognized A)
    - False Positives (FP) for 'A' = 4 + 2 = 6 (B and C wrongly predicted as A)
    - False Negatives (FN) for 'A' = 2 + 3 = 5 (A wrongly predicted as B or C)
    - True Negatives (TN) = total samples - TP - FP - FN
    

Precision vs Recall tradeoff with examples

Imagine the model is recognizing handwritten letters:

• High Precision: The model rarely mistakes one letter for another. For example, when it says a letter is 'A', it is almost always correct. This is good if you want to avoid wrong letters in official documents.
• High Recall: The model finds almost all the 'A's in the text, even if it sometimes mistakes other letters for 'A'. This is important if missing a letter is worse than a few mistakes, like reading a handwritten note where every letter matters.

Balancing precision and recall depends on what is more important: avoiding mistakes or not missing letters.

What good vs bad metric values look like for handwriting recognition

• Good: Accuracy above 90%, precision and recall both above 85%, and F1 score close to 0.9. This means the model correctly recognizes most letters and rarely makes mistakes or misses letters.
• Bad: Accuracy below 70%, precision or recall below 50%. This means the model often mistakes letters or misses many letters, making the recognition unreliable.

Common pitfalls in handwriting recognition metrics

• Accuracy paradox: If some letters appear very often, a model guessing only those letters can have high accuracy but poor real performance.
• Data leakage: If the model sees the same handwriting style in training and testing, it may look better than it really is.
• Overfitting: The model performs very well on training data but poorly on new handwriting styles.
• Ignoring class imbalance: Some letters appear less often, so metrics should consider this to avoid misleading results.

Self-check question

Your handwriting recognition model has 98% accuracy but only 12% recall on the letter 'A'. Is it good for production? Why or why not?

Answer: No, it is not good. Even though accuracy is high, the model misses most 'A's (low recall). This means many 'A's are not recognized, which can cause serious errors in reading handwriting.

Key Result

For handwriting recognition, balanced precision and recall with high accuracy ensure the model correctly identifies letters without missing or wrongly predicting them.