A method for emotional semantic recognition of cheongsam images based on fusion features

A technology of semantic recognition and feature fusion, applied in image enhancement, image analysis, image data processing, etc.

Active Publication Date: 2020-08-25
杭州浙泉网络科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, most of the research on clothing images focuses on object recognition, and there are relatively few studies on clothing images from the perspective of emotional semantics.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method for emotional semantic recognition of cheongsam images based on fusion features
  • A method for emotional semantic recognition of cheongsam images based on fusion features
  • A method for emotional semantic recognition of cheongsam images based on fusion features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0125] Step 1. Adjective selection and establishment of emotional space:

[0126] 1.1 From the 30 adjectives for clothing pictures, select a representative group of adjectives (simple and steady, noble and elegant, gentle and romantic, plain and fresh) to describe the cheongsam;

[0127] 1.2 Collected 400 pictures of cheongsam, all with solid color background;

[0128] 1.3 Divide the pictures in step 1.2 into 5 groups at random, with 80 pictures in each group, select 20 subjects to participate, and each 4 subjects evaluate the style of a group of pictures with the adjectives in step 1.1. The pictures are represented by 1, 2, 3, and 4 respectively, where 1 represents "quaint and steady" clothing, 2 represents "noble and elegant" clothing, 3 represents "gentle and romantic" clothing, and 4 represents "plain and fresh" clothing. Select the cheongsam pictures that are evaluated together, and remove the pictures with ambiguous styles. Finally, 350 pictures and corresponding emoti...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a cheongsam image emotion semantic recognition method based on fusion features. This method selects representative adjectives suitable for describing cheongsam images, extracts the color and texture features of cheongsam images, performs feature fusion, and then performs image emotion semantic learning, and uses the trained emotion model to perform emotion recognition on images. The method of the invention combines the fusion features of color and texture, and uses a machine learning method to establish the mapping from the bottom layer features of the cheongsam image to the emotional semantics of the high-level semantics, constructs the emotional semantic classification model of the cheongsam image, and realizes the emotional recognition of the cheongsam image. This method is easy to implement and has high accuracy of emotion recognition.

Description

technical field [0001] The invention relates to an emotion semantic recognition method of a cheongsam image based on fusion features, in particular to an emotion semantic recognition method of a cheongsam image which fuses color and texture features. Background technique [0002] People's perception and understanding of an image is at the semantic level and is subjective. Many studies have shown that different images can evoke different emotions in humans. However, the current image processing and applications mostly ignore the influence and role of emotion. For clothing images, any one or a piece of clothing can bring a certain emotional feeling to people, some clothing makes people feel noble, and some people feel fresh. At present, most of the researches on clothing images focus on object recognition, and there are relatively few studies on clothing images from the perspective of emotional semantics. However, there are very few studies on the emotional semantics of che...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06K9/46G06K9/40G06K9/34G06T5/30
CPCG06T5/30G06T2207/20032G06V10/30G06V10/267G06V10/56G06F18/217G06F18/2411G06F18/253
Inventor 胡更生秦梓轩楼苏迪陈梅
Owner 杭州浙泉网络科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap