Photo Classification
One of the most important processes within RemotePhoto is Photo Classification. It occurs through the work of machine learning algorithms, known affectionately as RemotePhoto Butler (RPB). Photo Classification is the foundation for many of RemotePhoto's functions. Let's dive in and see what it's all about!
Confidence Score
Every photo submitted to RemotePhoto receives a confidence score from RPB. The confidence score represents how certain RPB is that the submitted photo will be approved. A lower score means that he is less certain of photo approval, while a higher score means he is more certain of photo approval.
RemotePhoto Butler has been trained with thousands of photos to identify a quality ID photo. Through training, he's been taught to spot different attributes within photos that would indicate approval or denial. These attributes are derived from standard ID photo requirements, as shown in the screenshot below.

RPB compares the submitted photo to the thousands of photos he has been trained on. Based on how that photo stacks up to the training photos, RemotePhoto Butler gives the photo a Confidence Score.

RemotePhoto Butler has given this photo a 65% confidence score because part of the head has been cropped off. RPB is unsure whether this photo should be approved or denied.
Status Thresholds
RemotePhoto uses Status Thresholds to categorize the submitted photos. Based on the Confidence Score, photos are split into three categories. There are default thresholds—we'll take a look at them now. Also, be aware that these thresholds can be adjusted.
1. Approval threshold - set at 90% or greater confidence score (green status bar).

2. Unsure threshold - set between 20% and 90% confidence score (yellow status bar).

3. Denial threshold - set at 20% confidence score or lower (red status bar).

Customized Status Thresholds
It's surprising how much ID photo standards differ from organization to organization. Some allow for a busy background and others want strictly white. The array of requirements is vast. So how does RemotePhoto accommodate for these differing photo standards?
We allow organizations to tune their status thresholds to fit their needs. For example, if an organization is more lenient with photo standards, we can make adjustments to the thresholds. The changes might look something like this:
- Approval Threshold - 65% or greater confidence score (green status bar).
- Unsure Threshold - between a 35% and 65% confidence score (yellow status bar).
- Denial Threshold - 35% or lower confidence score (red status bar)
Conversely, if an organization is a little more rigid with their photo requirements, we can tune the thresholds accordingly.
Those changes might look something like this:
- Approval Threshold - 97% or greater confidence score (green status bar).
- Unsure Threshold - between a 50% and 95% confidence score (yellow status bar).
- Denial Threshold - 50% or lower confidence score (red status bar)
These thresholds become very important when thinking about Auto Approval for your organization.