Visual Intelligence

Details

Image processing technologies focus on the development of data extraction techniques applied toward the statistical classification of visual imagery in order to get an enhanced image or to extract some useful information from it. Artificial Intelligence techniques are used in the image processing industry to solve a wide range of previously intractable problems. Working on a variety of projects with different levels of complexity, we have had accurate results on Computer Vision (Deep Learning based) projects in visual intelligence.

Image processing made simple with Artificial Intelligence and Machine Learning technology. Our highly accurate results on Computer Vision (Deep Learning based) projects in visual intelligence led to:

Portrait segmentation – identifying the contour of every person in a given photo.
Face identification using 3D camera – identifying a person from a database based on a photo taken with a 3D camera.
Depth Estimation – approximating the distance between the objects in a given scene./estimating depth maps from 2d images (information relating to the distance of the surfaces of scene objects from the camera viewpoint)
Overexposure detection/White discrimination for improving HDR image generation – identifying the overexposed/underexposed and the white objects in a photo.

The purpose of this project is to automatically generate exhaustive data.

Data augmentation using Generative Adversarial Networks (GANs) for improving Face recognition systems robustness - producing images of real humans (portraits) with transformed face-attributes (i.e added/removed beard, sunglasses, etc.), without any sense of heterogeneity in the results (realistic samples).
Domain transform using GANs - transform image representation from RGB domain to NIR (Near-infrared) domain (Face recognition in low-light imaging).