Advanced Computer Vision Technology to Deliver Faster and Higher Quality Web Experiences
SmartVision is a revolutionary new technology that works with Instart Logic’s Image Transcoding feature to deliver brilliant images with fast performance. It uses advanced computer vision algorithms to “look at” the actual content of an image and intelligently determine what the maximum compression level can be without impacting the user experience.
How SmartVision Works
The first time an image is requested by an end user through the service it is also sent to the SmartVision processor in the cloud for advanced image analysis. Instart Logic image scientists have invented advanced image processing algorithms based on the latest computer vision research that can actually gain a unique and detailed understanding of each image.
The SmartVision technology first takes each image through a primary pass analysis, which produces a large number of identification signatures for each image. The system divides the image up into a number of versions, each at a different quality level. The SmartVision processor then analyzes each of these quality levels against the original image to create information on how each version degrades across a number of image signatures.
At this point the system uses an advanced affinity propagation algorithm, together with a large manually-classified image corpus maintained by the service, to identify the characteristics of each image. Examples of this are images which have zoomed-in close-ups of people or products, zoomed-out images of products with few solid colors, medium-zoomed product images with heavy patterns, or even zoomed-out architectural elements like a house or a broad city view.
Based on this information, the system builds a visual quality-of-experience map for each image that can be used to make a decision on the best balance between initial fidelity and performance.
The SmartVision technology then saves this information with the original image fragments, which can now be used by the Image Transcoding feature. This means determining, image by image, the optimal level of compression that can be applied without compromising image quality. This can reduce the size of images on a page up to 70% without any impact on user experience.