Computer architecture for artificial image generation using auto-encoder

A non-transitory machine-readable medium for image processing, the machine-readable medium storing instructions which, when executed by processing circuitry of one or more machines, cause the processing circuitry to:

• receive a voxel model of a first set of objects different from a target object, wherein the target object is to be recognized using an image recognizer;
• generate, based on the voxel model, a set of TSB (target shadow background-mask) images of the first set of objects;
• receive, at an auto-encoder, a set of real images of the first set of objects;
• generate, using the auto-encoder, one or more artificial images of the target object based on the set of TSB images, wherein the auto encoder encodes, using a sub-encoder, the set of TSB images into a latent vector and decodes, using a sub-decoder, the latent vector to generate the one or more artificial images, wherein the auto-encoder learns differences between the target object and the first set of objects, wherein the sub-encoder comprises a plurality of convolution pools, each convolution pool being followed by a batch normalization, and each batch normalization being followed by a ReLU (rectified linear unit), wherein a kernel size of each convolution pool is larger than a kernel size of a previous convolution pool;
• and
• provide, as output, the generated one or more artificial images of the target object.

An image processing method comprising:

• receiving a voxel model of a first set of objects different from a target object, wherein the target object is to be recognized using an image recognizer,
• generating, based on the voxel model, a set of TSB (target shadow background-mask) images of the first set of objects;
• receiving, at an auto-encoder, a set of real images of the first set of objects;
• generate, using the auto-encoder, one or more artificial images of the target object based on the set of TSB images, wherein the auto encoder encodes, using a sub-encoder, the TSB model into a latent vector and decodes, using a sub-decoder, the latent vector to generate the one or more artificial images, wherein the auto-encoder learns differences between the target object and the first set of objects, wherein the sub-encoder comprises a plurality of convolution pools, each convolution pool being followed by a batch normalization, and each batch normalization being followed by a ReLU (rectified linear unit), wherein a kernel size of each convolution pool is larger than a kernel size of a previous convolution pool;
• and
• providing, as output, the generated one or more artificial images of the target object.