Parameter set optimization apparatus, parameter set optimization program, and paper sheet handling system

Patent metadata

Field	Value
Publication number	US-12541987-B2
Application number	US-202318163455-A
Country	US
Kind code	B2
Filing date	Feb 2, 2023
Priority date	Aug 31, 2020
Publication date	Feb 3, 2026
Grant date	Feb 3, 2026

Abstract

A serial number recognition parameter determination apparatus includes: a generation unit, an identification unit, and an evaluation index calculation unit. The generation unit generates a parameter set of a program, the program being used when a paper sheet handing apparatus identifies, from an image of a paper sheet, character present regions in which characters that form a serial number are present. The identification unit identifies, from an image of the paper sheet, the character present regions by using the parameter set that is generated by the generation unit. The evaluation index calculation unit calculates an evaluation index of the parameter set based on the character present regions that are identified by the identification unit.

First claim

What is claimed is:

1 . A parameter set optimization apparatus comprising:
a processor, wherein the processor executes:
a first generation process that generates a parameter set of a program by using a Genetic Algorithm, the program being used when character present regions in which characters that form a serial number are present are identified,
an identification process that identifies, from an image of a paper sheet, the character present regions by using the generated parameter set,
a first calculation process that calculates a first evaluation value related to the number of characters in the identified character present regions, a second evaluation value related to character spacing in the identified character present regions, and a third evaluation value related to a character string width in the identified character present regions,
a second calculation process that calculates a fitness of the parameter set based on the first evaluation value, the second evaluation value and the third evaluation value,
a determination process that determines a parent parameter set of the Genetic Algorithm based on the calculated fitness,
a second generation process that generates a child parameter set of the Genetic Algorithm by performing crossover and mutation to the parent parameter set, and
an optimization process that optimizes the parameter set by repeating the identification process, the first calculation process and the second calculation process until a predetermined termination condition is met when the number of generations of the Genetic Algorithm reaches a predetermined value.

2 . The parameter set optimization apparatus according to claim 1 , wherein the parameter set includes a value that indicates a binarization type used when a serial number region image including the serial number is binarized, a binarization threshold, a value indicating a dilation amount in a dilation process performed on a binarized character present region, a black-to-white ratio threshold that is used when excluding a character present region in which a predetermined percentage or more of black pixels are present from among binarized character present regions, outer edge designation that is used when excluding the character present region that is located within a first predetermined distance from an outer edge of a binarized serial number region image, and a distance threshold that is used when excluding a character present region for which a distance from an adjacent character present region is equal to or larger than a predetermined distance.

3 . A non-transitory computer-readable recording medium having stored therein a parameter set optimization program that causes a computer to execute a processes, the processes comprising:
a first generation process that generates a parameter set of a program by using a Genetic Algorithm, the program being used when character present regions in which characters that form a serial number are present are identified; an identification process that identifies, from an image of a paper sheet, the character present regions by using the generated parameter set; a first calculation process that calculates a first evaluation value related to the number of characters in the identified character present regions, a second evaluation value related to character spacing in the identified character present regions, and a third evaluation value related to a character string width in the identified character present regions; a second calculation process that calculates a fitness of the parameter set based on the first evaluation value, the second evaluation value and the third evaluation value; a determination process that determines a parent parameter set of the Genetic Algorithm based on the calculated fitness; a second generation process that generates a child parameter set of the Genetic Algorithm by performing crossover and mutation to the parent parameter set; and an optimization process that optimizes the parameter set by repeating the identification process, the first calculation process and the second calculation process until a predetermined termination condition is met when the number of generations of the Genetic Algorithm reaches a predetermined value.

4 . A paper sheet handling system comprising:
a paper sheet handling apparatus that, by executing a program, identifies, from an image of a paper sheet, character present regions in which characters that form a serial number are present; and a parameter set optimization apparatus that optimizes a parameter set of the program, wherein the parameter set optimization apparatus includes a processor, wherein the processor executes:
a first generation process that generates the parameter set by using a Genetic Algorithm;
an identification process that identifies, from an image of the paper sheet, the character present regions by using the generated parameter set;
a first calculation process that calculates a first evaluation value related to the number of characters in the identified character present regions, a second evaluation value related to character spacing in the identified character present regions, and a third evaluation value related to a character string width in the identified character present regions,
a second calculation process that calculates a fitness of the parameter set based on the first evaluation value, the second evaluation value and the third evaluation value;
a determination process that determines a parent parameter set of the Genetic Algorithm based on the calculated fitness;
a second generation process that generates a child parameter set of the Genetic Algorithm by performing crossover and mutation to the parent parameter set; and
an optimization process that optimizes the parameter set by repeating the identification process, the first calculation process and the second calculation process until a predetermined termination condition is met when the number of generations of the Genetic Algorithm reaches a predetermined value.

Assignees

• Fujitsu Frontech Ltd
• Fujitsu Frontech Systems Ltd

Inventors

• Yoshimura Kazuhisa
• Kamei Masami

Classifications

• G06V30/19093

  Proximity measures, i.e. similarity or distance measures · CPC title

• G06N3/126

  Evolutionary algorithms, e.g. genetic algorithms or genetic programming · CPC title

• G06V30/1908 Primary

  Region based matching · CPC title

• G06V10/25

  Determination of region of interest [ROI] or a volume of interest [VOI] · CPC title

• G06V30/158

  using character size, text spacings or pitch estimation · CPC title