Cloning Image Features from Software Environment to a Hardware Media for Machine Vision Applications

The paper outlines a methodology for crafting an embedded processor system to replicate image features computed within a mat lab software environment onto a hardware-based processor system. The proposed approach depends on computing the features of the hand gesture images using Histograms of Oriented Gradients algorithm in the software media to be cloned to a hardware environment represented by an embedded processor system. Embedded Design Techniques were used to construct the processor system to be configured on Spartan 3E slice with DDR-SDRAM and EEPROM external memories connected to the processor via multiport memory controller embracing the processor local bus. The system saves the cloned features in the EEPROM for hardware image recognition applications. The designed configuration allows to be tailored with a robot camera circuitry for machine vision systems.