Image recognition apparatus and image recognition method
An image recognition apparatus includes a reception part that receives an image that has been read; a determination part that determines a registered object to correspond to an object included in the received image that has been read from among previously registered plural objects; a reflecting part that reflects colors of the image that has been read in previously stored plural similar objects each similar to the registered object determined by the determination part; and a printing control part that causes a printing apparatus to print the plural similar objects in which the colors have been reflected by the reflecting part.
1. An image recognition apparatus comprising:
a reception part that receives an image that has been read;
a determination part that determines a registered object to correspond to an object included in the received image that has been read from among previously registered plural objects;
a reflecting part that reflects colors of the image that has been read in previously stored plural similar objects each being similar to the registered object determined by the determination part; and
a printing control part that causes a printing apparatus to print the plural similar objects in which the colors have been reflected by the reflecting part.
2. The image recognition apparatus as claimed in claim 1 , further comprising:
an inscribed circle extraction part that extracts an inscribed circle inscribed in the object included in the image that has been read;
a circumscribed circle setting part that sets a circumscribed circle circumscribing the object and having a center point the same as a center point of the inscribed circle;
a data generation part that generates a waveform corresponding to the object based on a relative position of an outer shape of the object with respect to the circumscribed circle; and
an extraction part that extracts at least one template candidate corresponding to the generated waveform of the object from among waveforms of plural templates stored in a database corresponding to the previously registered plural objects, wherein
the determination part determines the registered object to correspond to the object included in the image that has been read based on the at least one template candidate extracted by the extraction part.
3. The image recognition apparatus as claimed in claim 2 , wherein
the data generation part generates the waveform corresponding to the outer shape of the object based on the relative position of the outer shape of the object calculated based on intersections of lines extending from the center point of the circumscribed circle in radial directions of the circumscribed circle and the outer shape of the object and intersections of the lines and the circumscribed circle.
4. The image recognition apparatus as claimed in claim 3 , further comprising
An object dividing part that divides the object included in the image that has been read into plural objects, wherein
the data generation part generates the respective waveforms corresponding to the plural objects obtained by the object dividing part, and
the extraction part extracts the at least one template candidate corresponding to the waveform of at least any one of the plural objects obtained by the object dividing part.
5. The image recognition apparatus as claimed in claim 4 , wherein
the determination part narrows down the at least one template candidate corresponding to the object included in the image that has been read based on positional relationship between the respective circumscribed circles of the plural objects obtained by the object dividing part.
6. The image recognition apparatus as claimed in claim 2 , wherein
the extraction part compares the generated waveform of the object with the respective waveforms of the plural templates stored in the database, using any point of the generated waveform of the object as a starting point.
7. The image recognition apparatus as claimed in claim 2 , wherein
the extraction part carries out frequency analysis of the waveforms of the plural templates stored in the database and the generated waveform of the object, and extracts the at least one template candidate corresponding to the object based on the analysis result.
8. The image recognition apparatus as claimed in claim 2 , wherein
the object included in the image that has been read is a three-dimensional object, and respective objects obtained from plural view points corresponding to the three-dimensional object are obtained,
the data generation part generates the respective waveforms of the objects of the plural view points, and
the extraction part extracts the at least one template candidate for each of the respective objects of the plural view points from three-dimensional templates stored in the database.
9. The image recognition apparatus as claimed in claim 2 , wherein
the image that has been read is a two-dimensional or three-dimensional moving image.
10. The image recognition apparatus as claimed in claim 8 , wherein
the data generation part generates the waveforms of the three-dimensional object from a three-dimensional image in a real-time manner.
11. An image recognition method comprising:
receiving an image that has been read;
determining, by a processor, a registered object to correspond to an object included in the received image that has been read from among previously registered plural objects;
reflecting, by the processor, colors of the image that has been read in previously stored plural similar objects each being similar to the registered object determined by the determining; and
causing a printing apparatus to print the plural similar objects in which the colors have been reflected by the reflecting.
12. The image recognition method as claimed in claim 11 , further comprising:
extracting, by the processor, an inscribed circle inscribed in the object included in the image that has been read;
setting, by the processor, a circumscribed circle circumscribing the object and having a center point the same as a center point of the inscribed circle;
generating, by the processor, a waveform corresponding to the object based on a relative position of an outer shape of the object with respect to the circumscribed circle; and
extracting, by the processor, at least one template candidate corresponding to the generated waveform of the object from among waveforms of plural templates stored in a database corresponding to the previously registered plural objects, wherein
the determining determines the registered object to correspond to the object included in the image that has been read based on the at least one template candidate extracted by the extracting.
13. The image recognition method as claimed in claim 12 , wherein
the generating generates the waveform corresponding to the outer shape of the object based on the relative position of the outer shape of the object calculated based on intersections of lines extending from the center point of the circumscribed circle in radial directions of the circumscribed circle and the outer shape of the object and intersections of the lines and the circumscribed circle.
14. The image recognition method as claimed in claim 13 , further comprising
dividing the object included in the image that has been read into plural objects, wherein
the generating generates respective waveforms corresponding to the plural objects obtained from the dividing, and
the extracting extracts the at least one template candidate corresponding to the waveform of at least any one of the plural objects obtained from the dividing.
15. The image recognition method as claimed in claim 14 , wherein
the determining narrows down the at least one template candidate corresponding to the object included in the image that has been read based on positional relationship between the respective circumscribed circles of the plural objects obtained by the dividing.
16. The image recognition method as claimed in claim 12 , wherein
the extracting compares the generated waveform of the object with the waveforms of the plural templates stored in the database, using any point of the generated waveform of the object as a starting point.
17. The image recognition method as claimed in claim 12 , wherein
the extracting carries out frequency analysis of the waveforms of the plural templates stored in the database and the generated waveform of the object, and extracts the at least one template candidate corresponding to the object based on the analysis result.
18. The image recognition method as claimed in claim 12 , wherein
the object included in the image that has been read is a three-dimensional object, and respective objects obtained from plural view points corresponding to the three-dimensional object are obtained,
the generating generates the respective waveforms of the objects of the plural view points, and
the extracting extracts the at least one template candidate for each of the respective objects of the plural view points from three-dimensional templates stored in the database.
19. The image recognition method as claimed in claim 18 , wherein
the generating generates the waveforms of the three-dimensional object from a three-dimensional image in a real-time manner.
20. The image recognition method as claimed in claim 12 , wherein
the image that has been read is a two-dimensional or three-dimensional moving image.