An Efficient Clothing Plan Integrity Conventional Neural Network to Visual Character in the Water Colour Image

An Effective Clothing Strategy Integrity is a conventional neural network for visual character recognition in watercolour images, particularly for garment design, is a crucial component of the apparel business. The uneven design of garments, significant deformability, and light sensitivity make the rapid and precise execution of clothing images retrieval a formidable challenge. The effective use of the Transformers in images recognition demonstrates its possible applicability in the visual domain. An enhanced and effective wardrobe strategy based on ResNet-50 is suggested in this article. Initially, the features extraction segment employs the ResNet-50 architecture integrated inside the Transformer modules to enhance the nets features extraction and receptive field capabilities. Secondly, dense jump connection is included into the ResNet-50 up sampling process, optimising the usage of extracted feature information at each step and enhancing the quality of the resulting picture. The net has three stages: the sketching stage, which seeks to forecast the colour distribution of garments and generate watercolour representations devoid of shadows and gradients. The second step is thinning, which transforms the water colour picture into the clothing image with shadow and light effects. The third stage is optimisation, which integrates the outcomes of the prior two processes to enhance the generating quality further. The investigational findings indicate that the enhanced nets IS & first input delay (FID) scores are 4.593 along with 1.507, correspondingly. High-quality clothing pictures may be produced just by providing a line drawing and a limited number of colour points. In comparison to conventional approaches, the picture produced by this network exhibits superior realism and precision. This technique integrates diverse picture feature information, enhances retrieval accuracy, exhibits significant resilience and practicality, and serves as a reference for the everyday activities of fashion designers.

Authors

Institutions

Publication Details

Published
2024-12-06
DOI
https://doi.org/10.1109/smart63812.2024.10882196
Primary Topic
Color Science and Applications
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

An Efficient Clothing Plan Integrity Conventional Neural Network to Visual Character in the Water Colour Image

Vinita Acharya, Lagan Goel, Varun Garg, Punit Goel et al.
Color Science and Applications
article

An Efficient Clothing Plan Integrity Conventional Neural Network to Visual Character in the Water Colour Image

Vinita Acharya, Lagan Goel, Varun Garg, Punit Goel, Sirish Kumar Narra, Swathi Garudasu
article en

Abstract

An Effective Clothing Strategy Integrity is a conventional neural network for visual character recognition in watercolour images, particularly for garment design, is a crucial component of the apparel business. The uneven design of garments, significant deformability, and light sensitivity make the rapid and precise execution of clothing images retrieval a formidable challenge. The effective use of the Transformers in images recognition demonstrates its possible applicability in the visual domain. An enhanced and effective wardrobe strategy based on ResNet-50 is suggested in this article. Initially, the features extraction segment employs the ResNet-50 architecture integrated inside the Transformer modules to enhance the nets features extraction and receptive field capabilities. Secondly, dense jump connection is included into the ResNet-50 up sampling process, optimising the usage of extracted feature information at each step and enhancing the quality of the resulting picture. The net has three stages: the sketching stage, which seeks to forecast the colour distribution of garments and generate watercolour representations devoid of shadows and gradients. The second step is thinning, which transforms the water colour picture into the clothing image with shadow and light effects. The third stage is optimisation, which integrates the outcomes of the prior two processes to enhance the generating quality further. The investigational findings indicate that the enhanced nets IS & first input delay (FID) scores are 4.593 along with 1.507, correspondingly. High-quality clothing pictures may be produced just by providing a line drawing and a limited number of colour points. In comparison to conventional approaches, the picture produced by this network exhibits superior realism and precision. This technique integrates diverse picture feature information, enhances retrieval accuracy, exhibits significant resilience and practicality, and serves as a reference for the everyday activities of fashion designers.

Hemwati Nandan Bahuguna Garhwal University (IN), Symbiosis International University (IN), Osmania University (IN)
Openalex Percentile: Top 76%
Color Science and Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.