Machine Learning Week 11 Application Example and Thank you Andrew Ng

1 Photo OCR

1.1 Program description and pipeline

1.2 Sliding windows

1. take pedestrian detection as an example
   
   using different rectangles to scan the image, step by step-size or stride, say 4 pixels
2. Text detection
   
   got the result like this
   

1.3 Character segmentation

1.4 Character classification

2 Getting lots of data: Artificial data synthesis

2.1 Artificial data examples

1. use lots of fonts to make synthetic data
   
2. synthesizing data by introducing distortions

1. Distortion should be representatioin of the type of noise/distrotions in the test set, eg: background noise, bad cellphone connection sounds
2. Usually does not help to add purely random/meaningless noise.

2.2 Discussion on getting more data

1. Make sure you have a low bias classifier before getting more data.(Plotting learning curves)
2. Always ask “How much work would it be to get 10times as much data as we currently have?”
   1)Artificial data synthesis
   2)Collect/label it by yourself
   3)“Crowd source”(eg: Amazon Mechanical Turk)

3 Thank you, Andrew Ng!