A computer-implemented method, computer program product and computer system (100) for determining the impact of herbicides on crop plants (11) in an agricultural field (10). The system includes an interface (110) to receive an image (20) with at least one crop plant representing a real world situation in the agricultural field (10) after herbicide application. An image pre-processing module (120) rescales the received image (20) to a rescaled image (20a) matching the size of an input layer of a first fully convolutional neural network (CNN1) referred to as the first CNN. The first CNN is trained to segment the rescaled image (20a) into crop (11) and non-crop (12, 13) portions, and provides a first segmented output (20s1) indicating the crop portions (20c) of the rescaled image with pixels belonging to representations of crop. A second fully convolutional neural network (CNN2), referred to as the second CNN, is trained to segment said crop portions into a second segmented output (20s2) with one or more sub-portions (20n, 20l) with each sub-portion including pixels associated with damaged parts of the crop plant showing a respective damage type (11-1, 11-2). A damage measurement module (130) determines a damage measure (131) for the at least one crop plant for each damage type (11-1, 11-2) based on the respective sub-portions of the second segmented output (20s2) in relation to the crop portion of the first segmented output (20s1).

Embodiments of the present invention provides a system and method of learning and classifying features to identify objects in images using a temporally coded deep spiking neural network, a classifying method by using a reconfigurable spiking neural network device or software comprising configuration logic, a plurality of reconfigurable spiking neurons and a second plurality of synapses. The spiking neural network device or software further comprises a plurality of user-selectable convolution and pooling engines. Each fully connected and convolution engine is capable of learning features, thus producing a plurality of feature map layers corresponding to a plurality of regions respectively, each of the convolution engines being used for obtaining a response of a neuron in the corresponding region. The neurons are modeled as Integrate and Fire neurons with a non-linear time constant, forming individual integrating threshold units with a spike output, eliminating the need for multiplication and addition of floating-point numbers.

Texture extraction is disclosed.

Apparatuses, systems, and techniques to indicate an extent, to which text corresponds to one or more images. In at least one embodiment, an extent to which text corresponds to one or more images is indicated using one or more neural networks and used to train the one or more neural networks.

Methods and systems for high-resolution image manipulation are disclosed. An original high-resolution image to be manipulated is obtained, as well as a driving signal indicating a manipulation result. The original high-resolution image is down-sampled to obtain a low-resolution image to be manipulated. Using a trained manipulation generator, a low-resolution manipulated image and a motion field are generated from the low-resolution image. The motion field represent pixel displacements of the low-resolution image to obtain the manipulation indicated by the driving signal. A high-frequency residual image is computed from the original high-resolution image. A high-frequency manipulated residual image is generated using the motion field. A high-resolution manipulated image is outputted by combining the high-frequency manipulated residual image and a low-frequency manipulated image generated from the low-resolution manipulated image by up-sampling.

Methods, apparatus and systems for recognizing sign language movements using multiple input and output modalities. One example method includes capturing a movement associated with the sign language using a set of visual sensing devices, the set of visual sensing devices comprising multiple apertures oriented with respect to the subject to receive optical signals corresponding to the movement from multiple angles, generating digital information corresponding to the movement based on the optical signals from the multiple angles, collecting depth information corresponding to the movement in one or more planes perpendicular to an image plane captured by the set of visual sensing devices, producing a reduced set of digital information by removing at least some of the digital information based on the depth information, generating a composite digital representation by aligning at least a portion of the reduced set of digital information, and recognizing the movement based on the composite digital representation.

A neural network feature decoding method and apparatus according to the present disclosure receives a bitstream including an encoded feature, decodes a feature from a bitstream, and reconstructs features corresponding to a plurality of layers of a neural network based on a decoded feature.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a synthesized signal. In some implementations, a computer-implemented system obtains generator input data including at least an input signal having one or more first characteristics, processes the generator input data to generate output data including a synthesized signal having one or more second characteristics using a generator neural network, and outputs the synthesized signal to a device. The generator neural network is trained, based on a plurality of training examples, with a discriminator neural network. The discriminator neural network is configured to process discriminator input data that combines a discriminator input signal having the one or more second characteristics with at least a portion of generator input data to generate a prediction of whether the discriminator input signal is a real signal provided in one of the plurality of training examples or a synthesized signal outputted by the generator neural network.

Disclosed are an image processing method and device using a line-wise operation. The image processing device, according to one embodiment, comprises: a receiver for receiving an image; a first convolution operator for generating a feature map by performing a convolution operation on the basis of the image; and a compressor for compressing the feature map into units of at least one line; and a decompressor for reconstructing the feature map compressed into units of lines.

Embodiments of this application provide an image reconstruction method and device. The method includes: inputting a first image into a newly constructed super-resolution model to obtain a reconstructed second image, where a resolution of the second image is higher than that of the first image. The newly constructed super-resolution model is obtained by training an initial super-resolution model by using an error loss. The error loss includes a pixel mean square error and an image feature mean square error. The image feature in the image feature mean square error includes at least one of a texture feature, a shape feature, a spatial relationship feature, and an image high-level semantic feature. According to the embodiments of this application, the quality of a reconstructed image can be improved.