Image classification using images with separate grayscale and color channels

摘要

Image classification techniques using images with separate grayscale and color channels are described. In one or more implementations, an image classification network includes grayscale filters and color filters which are separate from the grayscale filters. The grayscale filters are configured to extract grayscale features from a grayscale channel of an image, and the color filters are configured to extract color features from a color channel of the image. The extracted grayscale features and color features are used to identify an object in the image, and the image is classified based on the identified object.

主权项

1. A system comprising:
one or more processors; and a memory comprising instructions stored thereon that, responsive to execution by the one or more processors implement an image classification network, the image classification network comprising:
an image separator configured to separate an image into a grayscale channel of the image and a color channel of the image, the image comprising a color image;a first column of grayscale filters configured to receive the grayscale channel of the image and extract grayscale features from the grayscale channel of the image;a second column of color filters configured to receive the color channel of the image and extract color features from the color channel of the image, wherein the image classification network has a greater number of grayscale filters than color filters;an image classifier configured to identify an object in the image based on the extracted grayscale features and the extracted color features, and classify the image based on the identified object.