Shape-biased image classification using deep convolutional networks

A method of analyzing images, comprising:

• receiving an image;
• applying, by an analysis device, the received image to a machine learning network and classifying one or more features in the received image, the machine learning network configured to propagate image data through a plurality of convolutional layers, each convolutional layer of the plurality of convolutional layers including a plurality of filter channels, the plurality of filter channels configured to apply a plurality of filters to the image data and output a feature map for each filter, the machine learning network including a bottleneck layer configured to recognize an image feature based on a shape of an image component, the bottleneck layer configured to prevent encoding of texture and configured to apply a single filter related to the shape of the image component to each feature map;
• and
• outputting characterization data that includes a classification of the one or more features.

A vehicle system comprising:

• a memory having computer readable instructions;
• and
• a processor for executing the computer readable instructions, the computer readable instructions controlling the processor to perform:
• receiving an image;
• applying, by an analysis device, the received image to a machine learning network and classifying one or more features in the received image, the machine learning network configured to propagate image data through a plurality of convolutional layers, each convolutional layer of the plurality of convolutional layers including a plurality of filter channels, the plurality of filter channels configured to apply a plurality of filters to the image data and output a feature map for each filter, the machine learning network including a bottleneck layer configured to recognize an image feature based on a shape of an image component, the bottleneck layer configured to prevent encoding of texture and configured to apply a single filter related to the shape of the image component to each feature map;
• and
• outputting characterization data that includes a classification of the one or more features.