1293 results about "Artificial neural network" patented technology

A method, system, and computer program product for modifying an appearance of an anatomical structure in a medical image, e.g., rib suppression in a chest radiograph. The method includes: acquiring, using a first imaging modality, a first medical image that includes the anatomical structure; applying the first medical image to a trained image processing device to obtain a second medical image, corresponding to the first medical image, in which the appearance of the anatomical structure is modified; and outputting the second medical image. Further, the image processing device is trained using plural teacher images obtained from a second imaging modality that is different from the first imaging modality. In one embodiment, the method also includes processing the first medical image to obtain plural processed images, wherein each of the plural processed images has a corresponding image resolution; applying the plural processed images to respective multi-training artificial neural networks (MTANNs) to obtain plural output images, wherein each MTANN is trained to detect the anatomical structure at one of the corresponding image resolutions; and combining the plural output images to obtain a second medical image in which the appearance of the anatomical structure is enhanced.

A signal processing method and system combining smooth level wavelet pre-processing together with artificial neural networks all in the wavelet domain for signal denoising and extraction. Upon receiving a signal corrupted with noise, an n-level decomposition of the signal is performed using a discrete wavelet transform to produce a smooth component and a rough component for each decomposition level. The nth level smooth component is then inputted into a corresponding neural network pre-trained to filter out noise in that component by pattern recognition in the wavelet domain. Additional rough components, beginning at the highest level, may also be retained and inputted into corresponding neural networks pre-trained to filter out noise in those components also by pattern recognition in the wavelet domain. In any case, an inverse discrete wavelet transform is performed on the combined output from all the neural networks to recover a clean signal back in the time domain.

An “Animation Synthesizer” uses trainable probabilistic models, such as Hidden Markov Models (HMM), Artificial Neural Networks (ANN), etc., to provide speech and text driven body animation synthesis. Probabilistic models are trained using synchronized motion and speech inputs (e.g., live or recorded audio / video feeds) at various speech levels, such as sentences, phrases, words, phonemes, sub-phonemes, etc., depending upon the available data, and the motion type or body part being modeled. The Animation Synthesizer then uses the trainable probabilistic model for selecting animation trajectories for one or more different body parts (e.g., face, head, hands, arms, etc.) based on an arbitrary text and / or speech input. These animation trajectories are then used to synthesize a sequence of animations for digital avatars, cartoon characters, computer generated anthropomorphic persons or creatures, actual motions for physical robots, etc., that are synchronized with a speech output corresponding to the text and / or speech input.

A method of processing information is provided. The method involves receiving a message; processing the message with a trained artificial neural network based processor, having at least one set of outputs which represent information in a non-arbitrary organization of actions based on an architecture of the artificial neural network based processor and the training; representing as a noise vector at least one data pattern in the message which is incompletely represented in the non-arbitrary organization of actions; analyzing the noise vector distinctly from the trained artificial neural network; searching at least one database; and generating an output in dependence on said analyzing and said searching.

A method for coding pixels or voxels of a digital or digitalized two dimensional or three dimensional image, comprises the steps of: providing a digital image consisting in a two dimensional array of pixels or in a three dimensional array of voxels, each pixel or voxel being defined by at least one variable as its intensity in a grey scale image or the HSV (Hue, Saturation and Value) or the RGB values in a colour image; each pixel or voxel of the image being considered as a target pixel or voxel and for each target pixel or voxel a neighborhood being formed by a pixel or voxel windows comprising the said target pixel or voxel and a certain number of surrounding pixels or voxels for each target pixel or voxel generating a vector univocally associated to the said target pixel or voxel, the components of the said vectors being generated as a function of the values of the said target pixel or voxel and of each of the pixels or voxels of the said pixel or voxel window. The function of the values of the said target pixel or voxel and of each of the pixels or voxels of the said pixel or voxel window correspond to the characteristic parameters of the numerical matrix representing the pixels or voxels of the said window or of a transformation of the said numerical matrix. The invention relates also to an image processing method in which image data coded according to the above method are processed by means of a predictive algorithm as for example an artificial neural network.