METHOD FOR IDENTIFYING, ORDERING, AND PRESENTING IMAGES ACCORDING TO EXPRESSIONS
Embodiments are directed to digital image processing, storage, retrieval, and presentation systems and methods for ordering and ranking visually perceivable facial expressions identified within the selected set of digital images. In addition, arranging for presentation the ordered and ranked set of digital images in response to a user-selection of an emotional expression or range of emotional expressions and presenting the selected arranged set of digital images on a display device.
1 . A digital image processing method for analyzing facial expressions in digital images, comprising:
identifying facial feature points from one or more digital images;
comparing the identified facial feature points to a reference facial recognition facial feature point look-up table (LUT) to identify a subject face in the one or more digital images;
using the reference facial recognition facial feature point LUT to determine an emotional expression score for the one or more digital images across one or more emotional vectors;
categorizing the one or more digital images based on the emotional expression score;
determining an emotional expression or range of emotional expressions of the one or more digital images for at least one of: emotional expression-based capture, tagging, utilization, searching, storage, presentation, or display.
2 . The digital image processing method of claim 1 , wherein the one or more emotional vectors comprise at least one of: active-passive, pleasant-unpleasant, positive-negative, or conscious-unconscious.
3 . The digital image processing method of claim 1 , wherein the facial feature points are measured and converted into the emotional expressions or range of emotional expressions using models of incremental feature point variations.
4 . The digital image processing method of claim 1 , wherein the facial feature points are measured and converted into the emotional expressions or range of emotional expressions using comparison models trained by human observers.
5 . The digital image processing method of claim 1 , wherein the facial feature points are measured and converted into the emotional expressions or range of emotional expressions using relative positions of facial feature points to a determined neutral facial expression.
6 . The digital image processing method of claim 1 , further comprising:
verifying the determination with human observers having remote access to the one or more digital images.
7 . A digital image processing system for analyzing facial expressions in digital images, comprising:
a facial feature point analyzer configured to identify facial feature points from one or more images stored in an image collection;
a facial expression emotional vector sequencer configured to compare the facial feature points to a reference facial recognition facial feature point LUT to identify a subject face and to determine an emotional expression score for each of the one or more images across emotional vectors;
a data storage system including image metadata and the image collection.
8 . The digital image processing system of claim 4 , wherein the emotional vectors comprise at least one of: active-passive, pleasant-unpleasant, positive-negative, or conscious-unconscious.
9 . The digital image processing system of claim 4 , further comprising a facial feature point alignment calculator.
10 . A computer-readable storage medium, comprising:
instructions stored on the computer-readable storage medium, wherein the instructions comprise the digital image processing method of claim 1 ; and
a processor, wherein the processor executes the instructions.