Abstract: An electronic apparatus and a compression method for an artificial neural network are provided. The compression method is adapted for the artificial neural network with a plurality of convolution layers. The compression method includes: setting a first pruning layer for coupling the first pruning layer to Lth convolution layer, where the first pruning layer has a plurality of first weighting values and each of the first weighting values corresponds to each of a plurality of channels of the Lth convolution layer; tuning the first weighting values, selecting a part of the channels of the Lth convolution layer to be at least one first redundancy channel according to the first weighting values, and generating a compressed Lth convolution layer by deleting the at least one first redundancy channel; and removing the first pruning layer, and generating a first compressed artificial neural network.

Abstract: An electronic apparatus and a compression method for an artificial neural network are provided. The compression method is adapted for the artificial neural network with a plurality of convolution layers. The compression method includes: setting a first pruning layer for coupling the first pruning layer to Lth convolution layer, where the first pruning layer has a plurality of first weighting values and each of the first weighting values corresponds to each of a plurality of channels of the Lth convolution layer; tuning the first weighting values, selecting a part of the channels of the Lth convolution layer to be at least one first redundancy channel according to the first weighting values, and generating a compressed Lth convolution layer by deleting the at least one first redundancy channel; and removing the first pruning layer, and generating a first compressed artificial neural network.

Abstract: An image processing method for image alignment, includes sequentially receiving a plurality of images; generating at least one threshold corresponding to each image according to a plurality of intensities of each image of the plurality of images; converting each image according to the thresholds of each image, for generating a plurality of binary images; acquiring a plurality of characteristic pixels of each binary image according to the plurality of binary images; and aligning the plurality of images according to the plurality of characteristic pixels of each binary image.

Abstract: An image processing method for image alignment, includes sequentially receiving a plurality of images; generating at least one threshold corresponding to each image according to a plurality of intensities of each image of the plurality of images; converting each image according to the thresholds of each image, for generating a plurality of binary images; acquiring a plurality of characteristic pixels of each binary image according to the plurality of binary images; and aligning the plurality of images according to the plurality of characteristic pixels of each binary image.