Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020097401 - IDENTIFYING IMAGE AESTHETICS USING REGION COMPOSITION GRAPHS

Publication Number WO/2020/097401
Publication Date 14.05.2020
International Application No. PCT/US2019/060365
International Filing Date 07.11.2019
IPC
G06T 7/00 2017.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
CPC
G06K 9/4628
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
4604Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes, intersections
4609by matching or filtering
4619Biologically-inspired filters, e.g. receptive fields
4623with interaction between the responses of different filters
4628Integrating the filters into a hierarchical structure
G06K 9/6256
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
G06K 9/6272
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
6268relating to the classification paradigm, e.g. parametric or non-parametric approaches
627based on distances between the pattern to be recognised and training or reference patterns
6271based on distances to prototypes
6272based on distances to cluster centroïds
G06K 9/66
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
64using simultaneous comparisons or correlations of the image signals with a plurality of references, e.g. resistor matrix
66references adjustable by an adaptive method, e.g. learning
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
Applicants
  • NETFLIX, INC. [US]/[US]
Inventors
  • LIU, Dong
  • KAMATH, Nagendra
  • PURI, Rohit
  • BHATTACHARYA, Subhabrata
Agents
  • LEE, Jonathan R.
Priority Data
16/677,16107.11.2019US
62/757,72608.11.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) IDENTIFYING IMAGE AESTHETICS USING REGION COMPOSITION GRAPHS
(FR) IDENTIFICATION DE L'ESTHÉTIQUE D'UNE IMAGE À L'AIDE DE GRAPHES DE COMPOSITION DE RÉGION
Abstract
(EN)
The disclosed computer-implemented method may include generating a three-dimensional (3D) feature map for a digital image using a fully convolutional network (FCN). The 3D feature map may be configured to identify features of the digital image and identify an image region for each identified feature. The method may also include generating a region composition graph that includes the identified features and image regions. The region composition graph may be configured to model mutual dependencies between features of the 3D feature map. The method may further include performing a graph convolution on the region composition graph to determine a feature aesthetic value for each node according to the weightings in the node's weighted connecting segments, and calculating a weighted average for each node's feature aesthetic value to provide a combined level of aesthetic appeal for the digital image. Various other methods, systems, and computer-readable media are also disclosed.
(FR)
L'invention concerne un procédé mis en œuvre par ordinateur pouvant consister à générer une carte de caractéristiques tridimensionnelles (3D) pour une image numérique à l'aide d'un réseau à convolution complète (FCN). La carte de caractéristiques 3D peut être configurée pour identifier des caractéristiques de l'image numérique et pour identifier une région d'image pour chaque caractéristique identifiée. Le procédé peut également consister à générer un graphe de composition de région qui comprend les caractéristiques identifiées et les régions d'image. Le graphe de composition de région peut être configuré pour modéliser des dépendances mutuelles entre des caractéristiques de la carte de caractéristiques 3D. Le procédé peut en outre consister à réaliser une convolution de graphe sur le graphe de composition de région pour déterminer une valeur esthétique de caractéristique pour chaque nœud en fonction des pondérations dans les segments de connexion pondérés du nœud, et à calculer une moyenne pondérée pour chaque valeur esthétique de caractéristique du nœud pour fournir un niveau combiné d'attrait esthétique pour l'image numérique. L'invention concerne également divers autres procédés, systèmes et supports lisibles par ordinateur.
Also published as
Latest bibliographic data on file with the International Bureau