This study investigates how factors such as light intensity and automatic camera adjustments affect the accuracy of blood flow state estimation using RGB values from facial images. Previous research has estimated blood flow states by analyzing changes in RGB values captured from facial images, demonstrating the potential to assess autonomic nervous system activity through blood flow state changes. Facial images are created by capturing light reflected from the face after being illuminated by a light source, meaning that the shooting conditions, such as the position and intensity of the light source, can significantly impact the estimation process. Additionally, most cameras are equipped with automatic adjustments like ISO sensitivity, exposure, and shutter speed, which affect the brightness and contrast of the images. Cameras built into smartphones and webcams often have these automatic adjustments, which may alter the image’s brightness in response to changes in shooting conditions or body movements. These variations in RGB values could influence the accuracy of blood flow state estimation. However, previous studies have not sufficiently explored how lighting conditions affect RGB values or how automatic camera adjustments impact evaluation accuracy. Therefore, this study aims to systematically examine the effects of different lighting conditions and automatic camera adjustments on blood flow state evaluation. By addressing these factors, we aim to improve the reliability of blood flow estimation and develop more accurate methods for assessing autonomic nervous system activity.