The invention discloses an image feature descriptor extraction method and device, equipment and a storage medium, and relates to the field of image recognition. The method comprises the steps of obtaining a to-be-processed image; expanding the edge of the to-be-processed image outwards by adopting the pure color pixel points to obtain a filling image; extracting an image feature descriptor of thefilling image; enabling the box type filter to extract the features of the edge pixel points of the image to be processed, extracting the features in the image to be processed fully, and effectivelyavoid the edge effect. For a small-size image, enough features can be accurately extracted from the processed filling image through an SIFT/SURF algorithm.

Image feature descriptor extraction method and device, equipment and storage medium

The invention relates to the technical field of image processing, and provides a method and a device for image coding and logical operation The method comprises the following steps: firstly, extending multiple binary images into multiple square binary images respectively; secondly, according to a node code q and a pixel code r of a node in each square binary image, generating a truncation quadtree code of each square binary image; thirdly, performing logical operation on the truncation quadtree code to obtain a result coded sequence; and finally, performing decoding according to the result coded sequence to obtain an extended binary image of 2N*2N, and capturing a sub-image extended by the extended binary image to obtain a result binary image Therefore, a binary image code of which the space overhead is small enough can be obtained, and meanwhile, the speed is higher when the logical operation of the binary image is carried out

Method and device for image coding and logical operation

The invention relates to the field of image processing technology and provides a binary image reconstruction method and device. According to the method, first, a run of each column in a current maximum circular region corresponding to a current skeleton point is acquired; second, a result binary image is reconstructed directly according to the runs or by performing run merging operation according to the radius of the current maximum circular region and a switching radius threshold value given in advance. According to the method, reconstruction of the binary image can be quickly realized through a regional skeleton in the binary image and the radius of the maximum circular region of each skeleton point, and the speed is remarkably higher than that of a reconstruction method through which pixels are directly set.

Binary image reconstruction method and device

The invention provides a learning method and device for an electricity consumption pattern as well as an intelligent ammeter, and relates to the technical field of intelligent appliances. The method comprises the following steps: obtaining the electricity consumption corresponding to actual situation atmospheric temperature in a preset learning period; according to the electricity consumption and the preset temperature range of the actual situation atmospheric temperature, establishing an electricity consumption sample set of the preset temperature range; according to an inverse function of a normal distribution probability function and the number of samples in the electricity consumption sample set, calculating a first parameter set; and according to the electricity consumption sample set and the first parameter set, establishing an electricity consumption pattern learning model, so as to realize the learning of an electricity consumption pattern of the preset temperature range. Through the adoption of the learning method disclosed by the invention, the electricity consumption habits of a personal user in different preset temperature range are analyzed, so that according to the electricity consumption habits of the personal user, privately-customized precision service can be provided.

Guo Siyu

Papers

Method and device for image coding and logical operation

Binary image reconstruction method and device

Learning method and device for electricity consumption pattern, as well as intelligent ammeter