Abstract: A method for context-aware text recognition employing two neuromorphic computing models, auto-associative neural network and cogent confabulation. The neural network model performs the character recognition from input image and produces one or more candidates for each character in the text image input. The confabulation models perform the context-aware text extraction and completion, based on the character recognition outputs and the word and sentence knowledge bases.

Abstract: A metal piece having an organic coating with improved corrosion resistance and adhesion is described which comprises a zinc or zinc alloy plated metal piece having on its surface, a chromate film deposited from an aqueous acidic chromium solution comprising trivalent chromium as substantially the only chromium ion present, and a cathodic electrocoated siccative organic coating on the chromate film. In one embodiment, the zinc alloy includes a substantial gamma crystallographic phase. A process for obtaining such coated metal pieces also is described.

Abstract: A metal piece having an organic coating with improved corrosion resistance and adhesion is described which comprises a zinc or zinc alloy plated metal piece having on its surface, a chromate film deposited from an aqueous acidic chromium solution comprising trivalent chromium as substantially the only chromium ion present, and a cathodic electrocoated siccative organic coating on the chromate film. A process for obtaining such coated metal pieces also is described.

Abstract: A metal piece having an organic coating with improved corrosion resistance and adhesion is described which comprises a zinc or zinc alloy plated metal piece having on its surface, a chromate film deposited from an aqueous acidic chromium solution comprising trivalent chromium as substantially the only chromium ion present, and a cathodic electrocoated siccative organic coating on the chromate film. A process for obtaining such coated metal pieces also is described.