Is there a Contrast Invariant object recognition technique

I am working on object recognition and understand the technique. I’ve work with the MNIST dataset and understand how CNNs work. Now it is time for me to apply what I have learned to a real-world problem and right off the bat I encounter a major issue. The object I need to locate is a dark colored object on a white background. Building a filter on a dark object doesn’t make sense to me. Should I color invert the image before training? It is clear to me that would work. Are there processing techniques that are contrast invariant? That is to say, the technique works on a dark object on light background or light object on a dark background.