17873994. METHOD AND SYSTEM FOR EXTRACTING SENTIMENTS OR MOOD FROM ART IMAGES simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
METHOD AND SYSTEM FOR EXTRACTING SENTIMENTS OR MOOD FROM ART IMAGES
Organization Name
Inventor(s)
Chandra Prabhaker of Noida (IN)
METHOD AND SYSTEM FOR EXTRACTING SENTIMENTS OR MOOD FROM ART IMAGES - A simplified explanation of the abstract
This abstract first appeared for US patent application 17873994 titled 'METHOD AND SYSTEM FOR EXTRACTING SENTIMENTS OR MOOD FROM ART IMAGES
Simplified Explanation
The patent application describes a method for extracting sentiments or mood from art images using artificial neural networks. The method involves preprocessing the input image, extracting features such as dominant perceptual color and dominant subject, detecting low-level image features, and extracting mood feature information based on description information included in the image. The extracted features are then classified into mood/sentiments classes, and the method predicts the mood or sentiment present in the input image based on the dominant perceptual color and the classified classes.
- Method for extracting sentiments or mood from art images using artificial neural networks
- Preprocessing the input image
- Extracting features such as dominant perceptual color and dominant subject
- Detecting low-level image features
- Extracting mood feature information based on description information included in the image
- Classifying the extracted features into mood/sentiments classes
- Predicting the mood or sentiment present in the input image based on the dominant perceptual color and the classified classes
Potential Applications
- Art analysis and curation
- Emotional analysis of visual content
- Mood-based recommendation systems for art or design
Problems Solved
- Difficulty in understanding the sentiments or mood conveyed by art images
- Lack of automated methods for analyzing emotions in visual content
Benefits
- Provides a method for extracting sentiments or mood from art images
- Enables automated analysis of emotions in visual content
- Can be used for art analysis, curation, and mood-based recommendation systems
Original Abstract Submitted
A method for extracting sentiments or mood from art images includes: receiving at least one of the art images as an input image; preprocessing the input image; extracting features from the preprocessed input image, the extracting including predicting a color label corresponding to a dominant perceptual color detected from the preprocessed input image a dominant subject from the preprocessed input image, detecting low-level image features from the preprocessed input image, and extracting mood feature information based on a description information included in the input image; classifying the extracted features into a plurality of mood/sentiments classes, using an artificial neural network; and predicting at least one of a mood or a sentiment that is present in the input image based on the dominant perceptual color and the plurality of mood/sentiments classes.
