AI image recognizing agent through a scalable neural network

• Published in: 2013 International Conference on Human Computer Interactions (ICHCI) pp. 1 - 6
• Main Authors: Ebenezer, R. H. P., Manoj, P., Joseph, H. R., Visumathi, J.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.08.2013
• Subjects: Artificial Intelligence; Artificial Neural Networks; Biological neural networks; Digital Search Tree; Image color analysis; Image Processing; Image recognition; Image segmentation; Knowledge based systems; Neurons; Reinforced learning; Vegetation
• DOI: 10.1109/ICHCI-IEEE.2013.6887773

As of now, unbounded solutions for efficient image recognition and retrieval have been proposed within various fields of computer science. Such solutions include both primitive and complex approaches to minimize the input required from the whole of the image to form the most accurate idea of the big picture. The proposed image recognizing agent accomplishes its task though the application of a scalable neural network. Each neuron of the network focuses on a subset of the image taken as a segment. The neuron finds the closest match of the obtained subject with respect to the dynamic knowledge base. The network of neurons ensembles their decisions and provide the recognized image statement. The feedback provided to the network develops the synaptic strengths to further develop the image recognizing ability in terms of performance and accuracy. The system uses the concept of both assisted supervised learning and reinforced learning, and exploits the asynchronous and parallel computing ability of artificial neural networks.