Helper Bot
CloudCard wants to give cardholders and card offices a fantastic experience. We recognized that card offices waste a lot of time cropping, rotating, and processing photos. We have introduced artificial intelligence to CloudCard in order to solve a lot of these problems. Meet Helper Bot! Helper Bot is a series of machine learning algorithms that have been trained with thousands of photos to identify a quality ID photo. These algorithms help card office directors stop worrying about photos and get back to more pressing projects.
Auto cropping & rotating
There is no longer a need to spend time cropping, re-cropping, and rotating photos. Helper Bot can do all of the time consuming work for you, ensuring the first photo you see has been cropped and rotated already :) Below is a little video showing you exactly what this looks like. Helper Bot is finding the face, rotating, and cropping the photo. This is the view that your cardholders see when they upload a photo.
When the administrators first see the photo, it is already perfectly cropped and rotated without any extra work.
Photo Classification
Every photo that is submitted to CloudCard receives a confidence score from Helper Bot. The confidence score represents how certain Helper Bot 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.
Helper Bot has been trained with thousands of photos to identify a quality ID photo. The training taught him to spot different attributes within photos that would indicate approval or denial. These attributes are derived from standard ID photo requirements like shown in the screenshot below.
Helper Bot compares the photo that is submitted to the thousands of photos that he has been trained on. Based on how that photo stacks up to the other photos in his training, Helper Bot gives the photo a Confidence Score.
Helper Bot has given this photo a 65% confidence score because the card holder submitted a photo that cropped off part of her head. He is unsure as to whether this photo should be approved or denied.
Status Thresholds
CloudCard uses Status Thresholds to categorize the photos that are are submitted. The photos are split into three different default thresholds based on the Confidence Score.
1. Approval Threshold - set at an 90% or greater confidence score (green status bar).
2. Unsure Threshold - set between a 20% and 90% confidence score (yellow status bar).
3. Denial Threshold - set a 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 CloudCard accommodate for the differing photo standards of organizations?
We allow organizations to tune their status thresholds to fit their needs. For example, if a organization is more lenient with photo standards because they see their ID photo as a form of expression, we can make adjustments to the thresholds. The changes might look something like below:
- 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.
Instant Photo Feedback
*This is a deprecated feature*
Once a photo has been classified by Helper Bot, he will automatically contact the cardholder of their photos status. He will let them know whether he thinks their photo will be approved or denied based on the confidence score. In the below screen shot Helper Bot lets the cardholder know that he thinks the photo will be approved. For a deeper look, visit this Instant Photo Feedback article.
The Future of Helper Bot
As we improve the AI, administrators won't need to look at the photos at all. They will simply be approved and denied by Helper Bot without you ever setting eyes on a photo. In fact, this capability is possible today. Check out this article on Auto Approval to learn more!
Helper Bot is even more accurate after he is trained on the photos of your organization. Once you gather enough photos, we can train a customized bot on the photos that you have approved and denied. We are continuing to improve the algorithms so that you can have your own organizational specific Helper Bot and never have to touch a photo again.