# US 2019/0318200 A1 · Object detection device, object detection method, and recording medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0318200 A1 - Document ID: US20190318200A1 - Status: Published application - Kind: A1 - Application number: 16/452,644 - Filed: 2019-06-26 - Published: 2019-10-17 - Earliest claimed: 2015-03-19 - Assignees: NEC Corporation - Applicants: NEC Corporation - Inventors: Tetsuo INOSHITA - Web page: https://patentgrep.com/patent/US20190318200A1 ## CPC - G06V 10/945: {User interactive design; Environments; Toolboxes} - G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting - G06F 18/28: Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries - G06F 18/40: Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor - G06F 3/04842: Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence) - G06F 18/24: Classification techniques - G06N 20/00: Machine learning - G06T 11/26: Drawing of charts or graphs - G06T 2200/24: involving graphical user interfaces [GUIs] - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract Provided is an object detection device for efficiently and simply selecting an image for creating instructor data on the basis of the number of detected objects. The object detection device is provided with: a detection unit for detecting an object from each of a plurality of input images using a dictionary; an acceptance unit for displaying, on a display device, a graph indicating the relationship between the input images and the number of subregions in which the objects are detected, and displaying, on the display device, in order to create instructor data, one input image among the plurality of input images in accordance with a position on the graph accepted by operation of an input device; a generation unit for generating the instructor data from the input image; and a learning unit for learning a dictionary from the instructor data. ## Claims ### Claim 1 A system comprising: a storage that stores a program; and one or more processors that runs the program to perform: detecting objects from each of a plurality of input images by referring to a dictionary; accepting an input of a new partial region and an input of a class for the new partial region; displaying, on a display device, a graph indicating a relation between the input image and a number of partial regions in which the objects are detected; displaying, on the display device, one input image of the plurality of input images in accordance with a location on the graph accepted by an operation of an input device in order to create teacher data; displaying, on the display device, the new partial region accepting by the input, and generating teacher data from the input image. ### Claim 2 (depends on 1) The system according to claim 1, wherein the one or more processors that runs the program to perform: updating acceptance window on the display device after accepting the input of the new partial region. ### Claim 3 (depends on 1) The system according to claim 1, wherein the one or more processors that runs the program to perform: displaying the new partial region emphasized. ### Claim 4 (depends on 1) The system according to claim 1, wherein the one or more processors that runs the program to perform: learning the dictionary based on the teacher data. ### Claim 5 A method comprising: detecting objects from each of a plurality of input images by referring to a dictionary; accepting an input of a new partial region and an input of a class for the new partial region; displaying, on a display device, a graph indicating a relation between the input image and a number of partial regions in which the objects are detected; displaying, on the display device, one input image of the plurality of input images in accordance with a location on the graph accepted by an operation of an input device in order to create teacher data; displaying, on the display device, the new partial region accepting by the input, and generating teacher data from the input image. ### Claim 6 (depends on 5) The method according to claim 5, further comprising: updating acceptance window on the display device after accepting the input of the new partial region. ### Claim 7 (depends on 5) The method according to claim 5, further comprising: displaying the new partial region emphasized. ### Claim 8 (depends on 5) The method according to claim 5, further comprising: learning the dictionary based on the teacher data. ### Claim 9 A non-statutory recording medium storing computer programs, the computer program causing a computer to perform: detecting objects from each of a plurality of input images by referring to a dictionary; accepting an input of a new partial region and an input of a class for the new partial region; displaying, on a display device, a graph indicating a relation between the input image and a number of partial regions in which the objects are detected; displaying, on the display device, one input image of the plurality of input images in accordance with a location on the graph accepted by an operation of an input device in order to create teacher data; displaying, on the display device, the new partial region accepting by the input, and generating teacher data from the input image. ### Claim 10 (depends on 9) The non-statutory recording medium according to claim 9, wherein the computer program further causes the computer to perform: updating acceptance window on the display device after accepting the input of the new partial region. ### Claim 11 (depends on 9) The non-statutory recording medium according to claim 9, wherein the computer program further causes the computer to perform: displaying the new partial region emphasized. ### Claim 12 (depends on 9) The non-statutory recording medium according to claim 9, wherein the computer program further causes the computer to perform: learning the dictionary based on the teacher data.