Open up a new file, call it quant.py, and start coding: # import the necessary packagesįrom sklearn.cluster import MiniBatchKMeans Now that we have an understanding of what color quantization is, let’s explore how we can utilize it to create A Scanner Darkly type effect in images.
In fact, the famous QBIC CBIR system (one of the original CBIR systems that demonstrated image search engines were possible) utilized quantized color histograms in the quadratic distance to compute similarity. In practice, you can use this technique to construct more rigid color histograms. This creates a substantially smaller space and (ideally) less noise and variance. And sure, we can build standard color histograms based on these intensity values.īut another approach is to explicitly quantize the image and reduce the number of colors to say, 16 or 64. Take a second to think about color quantization in the context of CBIR, though.Īny given 24-bit RGB image has 256 x 256 x 256 possible colors. If you’re unfamiliar with the term, CBIR is just a fancy academic way of saying “image search engine”. In my own work, I find that color quantization is best used when building Content-Based Image Retrieval (CBIR) systems.
Normally, the intent is to preserve the color appearance of the image as much as possible, while reducing the number of colors, whether for memory limitations or compression. So, what is color quantization?Ĭolor quantization is the process of reducing the number of distinct colors in an image. This example will run on Python 2.7/Python 3.4+ and OpenCV 2.4.X/OpenCV 3.0+.
#Duplicate scanner darkly in opencv code#
Looking for the source code to this post? Jump Right To The Downloads Section
0 kommentar(er)
