Abstract: A method for classifying at least one input image representing a target particle in a sample, involves implementing, by data processing of a client, steps of: (b) extracting the characteristic map of the target particle by a convolutional neural network pre-trained on a base of public images; (c) classifying the input image according to the extracted characteristic map.

Abstract: A digital holographic imaging technique, includes iterative steps of: a) through back-propagation to the object coordinate of a hologram field comprising a spatial distribution of amplitude corresponding to the spatial distribution of intensity of the hologram and a spatial distribution of phase, determining an object field involving a spatial distribution of absorption and of phase shift of the imaged object, b) thresholding the values of the spatial distribution of absorption and of phase shift by decreasing the values to below a respective threshold, the thresholds decreasing in each iteration, c) through repropagation of the object field to the hologram coordinate, determining a modified hologram field comprising a modified spatial distribution of amplitude and a modified spatial distribution of phase, d) replacing the spatial distribution of phase of the hologram field with the modified spatial distribution of phase, the spatial distribution of phase shift and of absorption of the imaged object being tho

Abstract: A method for classifying a sequence of input images representing a target particle in a sample over time, includes the following steps performed by the data processing of a client, namely: (b) concatenation of the input images in the sequence as a three-dimensional stack; (c) direct classification of the three-dimensional stack using a convolutional neural network, CNN

Abstract: A method for classifying at least one input image representing a target particle in a sample involves implementing, by data processing a client, steps of: (B) extracting a characteristic map of the target particle from the input image; (c) reducing the number of variables in the extracted characteristic map, using the t-SNE algorithm; (d) classifying, unsupervised, the input image based on the characteristic map having a reduced number of variables.

Abstract: A method for classifying at least one input image containing a target particle in a sample, involves implementing, via data-processing of a client, steps of: (b) extracting a vector of characteristics of the target particle, the characteristics being numerical coefficients each associated with one elementary image of a set of elementary images each representing a reference particle, such that a linear combination of the elementary images weighted by the coefficients approximates the representation of the target particle in the input image; (c) classifying the input image depending on the extracted vector of characteristics.