Abstract: The present disclosure discloses a sintered neodymium-iron-boron magnet and a preparation method thereof. The sintered neodymium-iron-boron magnet includes the following raw materials in mass percentage: 1%-40% of an iron powder or a steel powder with a magnetic induction intensity of more than 1.2 T, not more than 10% of a praseodymium-neodymium metal hydride powder, and a remainder of a neodymium-iron-boron fine powder, wherein the mass percentages of the above raw materials add up to 100%. The preparation method includes: weighing the raw materials in mass percentage; mixing the weighed raw materials uniformly, and then subjecting to magnetic-field press molding, isostatic pressing, sintering and tempering to obtain the sintered neodymium-iron-boron magnet.

Abstract: Provided is a method for compensating a displayed picture in a display screen. The display screen includes a plurality of regions, each of the plurality of regions including a plurality of pixels; the method includes: determining transformation matrices corresponding to pixels in the plurality of regions based on texture complexities of pictures to be displayed in the plurality of regions; acquiring compensated grayscales by compensating grayscales of pixel points in the pictures to be displayed in the plurality of regions based on the transformation matrices corresponding to the pixels in the plurality of regions.

Abstract: The present disclosure discloses a sintered neodymium-iron-boron magnet and a preparation method thereof. The sintered neodymium-iron-boron magnet includes the following raw materials in mass percentage: 1%-40% of an iron powder or a steel powder with a magnetic induction intensity of more than 1.2 T, not more than 10% of a praseodymium-neodymium metal hydride powder, and a remainder of a neodymium-iron-boron fine powder, wherein the mass percentages of the above raw materials add up to 100%. The preparation method includes: weighing the raw materials in mass percentage; mixing the weighed raw materials uniformly, and then subjecting to magnetic-field press molding, isostatic pressing, sintering and tempering to obtain the sintered neodymium-iron-boron magnet.

Abstract: The present disclosure relates to a method for training a classifier. The method includes: acquiring an original image; determining a candidate target by segmenting the original image based on at least two segmentation models; determining a universal set of features by extracting features from the candidate target; determining a reference subset of features by selecting features from the universal set of features; and determining a classifier by performing classifier training based on the reference subset of features.

Abstract: The present disclosure relates to a method for training a classifier. The method includes: acquiring an original image; determining a candidate target by segmenting the original image based on at least two segmentation models; determining a universal set of features by extracting features from the candidate target; determining a reference subset of features by selecting features from the universal set of features; and determining a classifier by performing classifier training based on the reference subset of features.

Abstract: The present disclosure relates to a method for training a classifier. The method includes: acquiring an original image; determining a candidate target by segmenting the original image based on at least two segmentation models; determining a universal set of features by extracting features from the candidate target; determining a reference subset of features by selecting features from the universal set of features; and determining a classifier by performing classifier training based on the reference subset of features.

Abstract: The present disclosure relates to a method for training a classifier. The method includes: acquiring an original image; determining a candidate target by segmenting the original image based on at least two segmentation models; determining a universal set of features by extracting features from the candidate target; determining a reference subset of features by selecting features from the universal set of features; and determining a classifier by performing classifier training based on the reference subset of features.