发明名称 |
INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND PROGRAM |
摘要 |
An information processing device, apparatus, method and non-transitory computer-readable storage medium are disclosed. An information processing device may include a memory storing instructions, and at least one processor configured to process the instructions to generate a comparison image by transforming a reference image, associate the comparison image with a class variable representing an object included in the reference image, calculate a degree of difference between an input patch which is an image representing a sub-region of an input image and a comparison patch which is an image representing a sub-region of the comparison image, estimate a displacement vector between the input patch and the comparison patch, calculate a first degree of reliability corresponding to the displacement vector and the class variable on the basis of the displacement vector and the degree of difference, calculate a second degree of reliability for each comparison patch on the basis of the first degree of reliability, and identify the object is represented by the class variable associated with the comparison image including the comparison patch whose second degree of reliability is greater than a predetermined threshold value, as a recognition target. |
申请公布号 |
US2016071285(A1) |
申请公布日期 |
2016.03.10 |
申请号 |
US201514845462 |
申请日期 |
2015.09.04 |
申请人 |
NEC Corporation |
发明人 |
SHIBATA Takashi |
分类号 |
G06T7/20;G06T7/00 |
主分类号 |
G06T7/20 |
代理机构 |
|
代理人 |
|
主权项 |
1. An information processing device comprising:
a memory storing instructions; and at least one processor configured to process the instructions to: generate a comparison image by transforming a reference image, associate the comparison image with a class variable representing an object included in the reference image, calculate a degree of difference between an input patch which is an image representing a sub-region of an input image and a comparison patch which is an image representing a sub-region of the comparison image, estimate a displacement vector between the input patch and the comparison patch, calculate a first degree of reliability corresponding to the displacement vector and the class variable on the basis of the displacement vector and the degree of difference, calculate a second degree of reliability for each comparison patch on the basis of the first degree of reliability, and identify the object is represented by the class variable associated with the comparison image including the comparison patch whose second degree of reliability is greater than a predetermined threshold value, as a recognition target. |
地址 |
Tokyo, JP |