Building a Computer Vision Model

A simplified, straightforward tutoral on a computer vision model.   This is the place you can get something impressive out of neural nets,  and an intro to the general AI method along them way.       Of most use too, pointers to existing databases to get started with.  We used ImageNet and WordNet tags, for example.

From KDNuggets:

How can we build a computer vision model using CNNs? What are existing datasets? And what are approaches to train the model? This article provides an answer to these essential questions when trying to understand the most important concepts of computer vision.  

By Javier Couto, Tryolabs.

Computer vision is one of the hottest subfields of machine learning, given its wide variety of applications and tremendous potential. Its goal: to replicate the powerful capacities of human vision. But how is this achieved with algorithms?

Let's have a loot at the most important datasets and approaches.

Existing datasets
Computer vision algorithms are no magic. They need data to work, and they can only be as good as the data you feed in. These are different sources to collect the right data, depending on the task:

One of the most voluminous and well known dataset is ImageNet, a readily-available dataset of 14 million images manually annotated using WordNet concepts. Within the global dataset, 1 million images contain bounding box annotations.  .... "

More on WordNet

A short piece on the origins of the semantic ontology called Wordnet.  Remarkable and free resource to pull help you pull apart aspects of natural language.  We used it as a knowledge base for a tag analysis application.

Semantic Parsing for Human Reason and Understanding

Today's CSIG talk:

Lenhart Schubert from the University of Rochester, presented "From Semantic Parsing to Reasoning."   ...   Slides here. 

This presentation is quite technical, but also gives an excellent non technical introduction to the current state of the art and continued deep challenges in knowledge based text understanding.    Points  to some excellent examples of work underway and tools like KNext and WordNet.  We used these for some consumer engagement applications, without attempting to solve the very deep underlying problem.

    ... sign up for making a presentation by sending a note to (fodell@us.ibm.com).   The format for these calls is 20-25 minutes by the presenter on work he/she is doing in Cognitive Computing or Cognitive Systems, followed by 5-10 minutes of questions and answers.   A link to slides (if used) and a recording of each call will be available on the CSIG website (http://cognitive-science.info/community/weekly-update/).