SYSTEM FOR GENERATION OF USER-CUSTOMIZED IMAGE IDENTIFICATION DEEP LEARNING MODEL THROUGH OBJECT LABELING AND OPERATION METHOD THEREOF

A deep learning system may simply establish steps for deep learning model generation, and provide an intuitive, natural, and easy interaction when performing feedback operations relating to image input, a manual labeling operation, and an automatic labeling operation required for the deep learning m...

Full description

Saved in:
Bibliographic Details
Main Authors YANG, Kyung Ok, CHUNG, Dae Su, LEE, Woo Yung
Format Patent
LanguageEnglish
French
Korean
Published 23.12.2021
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:A deep learning system may simply establish steps for deep learning model generation, and provide an intuitive, natural, and easy interaction when performing feedback operations relating to image input, a manual labeling operation, and an automatic labeling operation required for the deep learning model generation steps. Therefore, the deep learning system can provide an opportunity for a user who does not have specialized knowledge of deep learning to directly generate and utilize a user-customized image identification deep learning model for identification of an object desired to be identified. Système d'apprentissage profond pouvant simplement établir des étapes de génération de modèle d'apprentissage profond, et fournir une interaction intuitive, naturelle et commode lors de la réalisation d'opérations de retour d'information concernant une entrée d'image, une opération de marquage manuel et une opération de marquage automatique requises pour les étapes de génération de modèle d'apprentissage profond. Par conséquent, le système d'apprentissage profond peut fournir l'opportunité à un utilisateur, qui n'a pas de connaissances spécialisées en matière d'apprentissage profond, de générer et d'utiliser directement un modèle d'apprentissage profond d'identification d'image personnalisé par l'utilisateur pour l'identification d'un objet que ce dernier souhaite identifier. 딥러닝 시스템은, 딥러닝 모델의 생성 단계를 간단하게 정립하고, 상기 단계들에 필요한 이미지 입력, 수동 레이블링 작업 및 자동 레이블링 작업에 대한 피드백 작업을 수행하는데 있어 직관적이며, 자연스럽고 쉬운 인터랙션을 제공함으로써, 딥러닝에 대한 전문적인 지식이 없는 사용자에게 식별을 원하는 객체 식별을 위한 사용자맞춤 이미지식별 딥러닝 모델을 직접 생성하며 활용할 수 있는 기회를 제공할 수 있다.
Bibliography:Application Number: WO2020KR08631