Text recognition pipeline in Computer Vision - Model Pipeline Trace

Model Pipeline - Text recognition pipeline

This pipeline takes pictures of text and turns them into words you can read on a computer. It first cleans the image, finds the text parts, then reads the letters, and finally gives the text as output.

Data Flow - 8 Stages

1Input Image

1 image x 256 x 256 pixels x 3 color channels→Raw photo input with text→1 image x 256 x 256 pixels x 3 color channels

Photo of a street sign with letters

↓

2Preprocessing

1 image x 256 x 256 x 3→Convert to grayscale and normalize pixel values→1 image x 256 x 256 x 1

Grayscale image with pixel values between 0 and 1

↓

3Text Detection

1 image x 256 x 256 x 1→Find bounding boxes around text areas→1 image x 256 x 256 x 1 + bounding box coordinates

Boxes around words like 'STOP' and 'SPEED'

↓

4Text Cropping

Bounding boxes + image→Crop image regions inside bounding boxes→N cropped images x 32 x 128 x 1 (N = number of text boxes)

Small images each containing one word

↓

5Feature Extraction

N cropped images x 32 x 128 x 1→Extract features using CNN layers→N feature maps x 8 x 32 x 64 channels

Feature maps highlighting edges and shapes of letters

↓

6Sequence Modeling

N feature maps x 8 x 32 x 64→Use RNN layers to understand letter sequences→N sequences x 32 time steps x 256 features

Sequences representing letter order in words

↓

7Prediction

N sequences x 32 x 256→Apply fully connected layer + softmax to predict characters→N sequences x 32 time steps x 37 classes (26 letters + 10 digits + blank)

Probabilities for each character at each time step

↓

8Decoding

N sequences x 32 x 37→Convert probabilities to text using CTC decoding→N text strings

Recognized words like 'STOP' and 'SPEED'

Training Trace - Epoch by Epoch

Loss
2.3 |****
1.8 |***
1.4 |**
1.1 |*
0.9 |*
0.8 |*
     +---------
     Epochs 1-6

Epoch	Loss ↓	Accuracy ↑	Observation
1	2.3	0.25	Model starts learning, loss is high, accuracy low
2	1.8	0.40	Loss decreases, accuracy improves
3	1.4	0.55	Model learns letter shapes better
4	1.1	0.65	Better sequence understanding
5	0.9	0.72	Model converging, good text recognition
6	0.8	0.76	Small improvements, nearing stable performance

Prediction Trace - 7 Layers

Layer 1: Input Image

Layer 2: Text Detection

Layer 3: Text Cropping

Layer 4: Feature Extraction

Layer 5: Sequence Modeling

Layer 6: Prediction

Layer 7: Decoding

Model Quiz - 3 Questions

What is the purpose of the Text Detection stage?

A To predict the letters in the text

B To convert the image to grayscale

C To find where text is located in the image

D To crop the image into smaller pieces

Key Insight

This visualization shows how a text recognition model processes images step-by-step, improving its ability to read text by learning features and sequences, and finally decoding predictions into readable words.