LIGHTING CONDITION CREATION SUPPORT DEVICE, CAPTURED IMAGE ESTIMATION METHOD, AND LIGHTING CONDITION CREATION METHOD
To provide a lighting condition creation support device, a captured image estimation method, and a lighting condition creation method that can acquire in a short time captured images of a component under a plurality of lighting conditions.SOLUTION: A captured image estimation method includes: a firs...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Patent |
Sprache: | eng ; jpn |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | To provide a lighting condition creation support device, a captured image estimation method, and a lighting condition creation method that can acquire in a short time captured images of a component under a plurality of lighting conditions.SOLUTION: A captured image estimation method includes: a first imaging step of capturing images of a component lit by lighting means under a plurality of lighting conditions with imaging means; a learning step (ST1) of generating a learning model 41 on the basis of the plurality of captured images obtained in the first imaging step and the lighting conditions (captured image data 40) at the time of imaging; a second imaging step of imaging one component D99 lit by the lighting means under one lighting condition 1 with the imaging means; and an image estimation step (ST2) of estimating other captured images (estimated image data 42) obtained when the imaging means images the one component D99 lit by the lighting means under other lighting conditions 6 and 7 from the captured image (captured image data 40) of the component D99 obtained in the second imaging step using the generated learning model 41.SELECTED DRAWING: Figure 5
【課題】複数の照明条件による部品の撮像画像を短時間に取得することができる照明条件作成支援装置および撮像画像推定方法ならびに照明条件作成方法を提供する。【解決手段】撮像画像推定方法は、照明手段が複数の照明条件で照明した部品を撮像手段で撮像する第1撮像工程と、第1撮像工程により得られた複数の撮像画像と撮像時の照明条件(撮像画像データ40)とに基づき、学習モデル41を生成する学習工程(ST1)と、照明手段が一の照明条件1で照明した一の部品D99を撮像手段で撮像する第2撮像工程と、生成された学習モデル41を用いて、第2撮像工程により得られた部品D99の撮像画像(撮像画像データ40)から、照明手段が他の照明条件6、7で照明した一の部品D99を撮像手段が撮像した場合に得られる他の撮像画像(推定画像データ42)を推定する画像推定工程(ST2)と、を含む。【選択図】図5 |
---|