APPARATUS FOR EXTRACTING FACIAL IMAGE CHARACTERISTIC POINTS

摘要

A facial image picture data is processed by an edge extraction part 2, which performs edge-stressing on the inputted image picture. And then the processed data is converted by a binary level conversion part 3 for each preestimated point of facial elements. The binary converted data is stored in a shape data-base part 4. The stored shape data is updated by an updating part 6. An image picture arithmetic processing part 5 performs time-to-time arithmetic computation of correspondence factors between the data of the binary-leveled edged image picture and the data stored in the shape data-base part 4, and issues an output including extracted data of image characteristic points.