Abstract: A method for generating an order includes acquiring by one or more processors, an initial image and a first detection result of a target container before being subjected to a pick-up operation, where the first detection result includes a first detection image with a number of first commodity frames obtained by processing the initial image, and first identification information corresponding to a commodity in each of the first commodity frames, acquiring by one or more processors, a result image of the target container after performing the pick-up operation, generating by one or more processors, an RGB difference image between before-shopping and after-shopping, based on the result image and the initial image, where the RGB difference image is obtained by calculating an absolute value of differences of individual pixels of the initial image and the result image before and after shopping in three RGB channels.

Abstract: A text recognition method, a text recognition apparatus, an electronic device, and a storage medium are provided. The method includes: extracting character prediction regions of a text line image using a constructed text recognition model, to obtain a character region set; calculating horizon-distance IOUs between the character prediction regions in the character region set according to a position of each character prediction region in the character region set; removing overlapped character prediction regions from the character region set, according to the horizon-distance IOUs between the character prediction regions in the character region set, to obtain a character position set; and sorting and outputting character categories corresponding to the character prediction regions in the character position set according to positions of the character prediction regions in the character position set.

Abstract: The present disclosure provides a method, a device, an electronic apparatus, and a storage medium for generating an order, with the method for generating an order including the following steps of: acquiring an initial image and a first detection result of a target container before the occurrence of a pick-up operation, wherein the first detection result includes a first detection image with a plurality of first commodity frames obtained by processing the initial image, and first identification information corresponding to the commodity in each of the first commodity frames; acquiring a result image of the target container after the finish of the pick-up operation; generating an RGB difference image between before-shopping and after-shopping based on the result image and the initial image; and generating a commodity order corresponding to the removed commodity based on the RGB difference image and the first detection result.

Abstract: A text recognition method, a text recognition apparatus, an electronic device, and a storage medium are provided. The method includes: extracting character prediction regions of a text line image using a constructed text recognition model, to obtain a character region set; calculating horizon-distance IOUs between the character prediction regions in the character region set according to a position of each character prediction region in the character region set; removing overlapped character prediction regions from the character region set, according to the horizon-distance IOUs between the character prediction regions in the character region set, to obtain a character position set; and sorting and outputting character categories corresponding to the character prediction regions in the character position set according to positions of the character prediction regions in the character position set.