image analysis/openCV object detection

I'm attempting to experiment and get started with image analysis and OpenCV

My aim is to detect certain objects in random pictures, which are easy to detect, for example: symbols and brand logos. I'd also like to be able to detect more variable features like facial fea开发者_运维百科tures, porn features. usecase: autotagging, autofiltering

My questions:

1. Where should I start learning applied image-analysis in the context of my aims?
2. What are important existing concepts/approches that I should introduce myself to?
3. What are good existing solutions/components of OpenCV which i can feed with training-datasets of example pictures showing the objects of interest and then make a human manually outline the shapes of interest in order to make it learn to detect the features.