The thing to do is tie the whole thing together with unsupervised NN. Templet matching did not do good for detection because it is two pattern laid over each other. A NN detect both because it generals to the middle ground between the two.
Templet match has the confusion of pattern "A" being 44 percent of pattern "B", the ground truth anchor. Or is pattern "B" forty-four percent of pattern"A". NN generates one output or a symbol. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T9a211170d976967d-Mf27acbe42bf5aac09b40973b Delivery options: https://agi.topicbox.com/groups/agi/subscription
