Machine LEARNING-XVIII. Application Example Photo OCR application Example-photographic OCR (WEEK10)

http://blog.csdn.net/pipisorry/article/details/44999703

Machine learning machines Learning-andrew NG Courses Study notes

Application Example Photo OCR application Example Photos

OCR (Optical Character recognition) Optical text identification

Problem Description and pipeline problem description and piping

three reasons to centered around an application called Photo OCR: First to show you a example of how a complex MA Chine learning system can be put together. Second, once told the concepts of a machine learning a pipeline and how to allocate resources when you ' re trying to decide What does next. Finally, the Photo OCR problem also tell-a couple more interesting ideas for machine learning. Learning to Computer vision, and second are the idea of the artificial data synthesis.

Photo OCR Pipeline

Note: Some photo OCR systems do more complex things,likespelling correction at the end. For example character segmentation and character classification system tells the IT sees Word C 1 e a n i n G. Then,spelling correction system might tell "this is probably the word ' cleaning ', and your character classificatio n algorithm had just mistaken the L for a 1.

Note:

1. A system like this is called a machine learning pipeline. In particular, here's a picture showing the photo OCR pipeline.
2. Pipelines is common, where you can has multiple modules, each of the which may is machine learning component,or s Ometimes It may isn't a machine learning component but to has a set of modules that act one after another on some piece of data in order to produce the output of want.

3. Designing a machine learning system one of the most important decisions would often be what exactly is thepipeline that's want to put together. In other words, given the photo OCR problem, How does you break this problem to a sequence of different modules. And each of the performance of all of the modules in your Pipeline.will often has a big impact on the final performance of Your algorithm.


Sliding Windows sliding window

Getting Lots of data and Artificial data for large volumes

Ceiling analysis:what part of the Pipeline to working on next upper limit analysis-next to what parts of the pipeline work

from:http://blog.csdn.net/pipisorry/article/details/44999703

Machine LEARNING-XVIII. Application Example Photo OCR application Example-photographic OCR (WEEK10)