January 11, 2011 – As technology goes, visual recognition continues to be one of the most talked about areas. So it was no surprise when Cortexica came on the scene and started using algorithms that emulate the visual cortex and the techniques the brain uses to identify and categorize objects.
We found this interesting article in the Wall Street Journal titled, “Teaching Computers To See Like Humans.” Taking conventional visual recognition that is based around filters and has no adaptive ability, Cortexica’s system is built like the brain works. Looking for key points in the image to analyze them and ultimately understand the images.
This very semantic-like technology creates visual words that work like building blocks to assemble more and more complicated images. Cortexica’s system works in specific verticals—such as wine labels, art, cars and watches. That way, the “dictionary” of visual words can be specific to that vertical, making recognition both faster and more accurate.
They continue to advance and evolve the technology. It will be interesting to see what boundaries they break.
Melody K. Smith
Sponsored by Access Innovations, the world leader in taxonomies, metadata, and semantic enrichment to make your content findable.