JP2018160256A5 - - Google Patents

Claims (13)

One or more computers,
A first extraction step of extracting a feature amount from one image;
A second extraction step of extracting the output values of all connected layers after one or more convolutional layers of a convolutional neural network (CNN) based on the feature amount;
A determination step of determining a similar image similar to the one image based on the output value;
A program that runs Causing the one or more computers to execute a conversion step of converting the output value of the entire combined layer into a value range within a predetermined range;
The program according to claim 1. The similar image is stored in an information storage unit.
The program according to claim 1 or claim 2. The convolution neural network (CNN) comprises a plurality of convolution layers,
The program according to any one of claims 1 to 3. The convolutional neural network (CNN) comprises five convolutional layers,
The program according to claim 4. The convolutional neural network (CNN) comprises one all connected layer,
The program according to claim 4 or 5. The transformation step is performed using a sigmoid function
The program according to claim 2. The conversion step is performed such that the value range of the output value is in the range of 0 to 1.
The program according to claim 7. The determining step includes an approximating step of approximating the output value.
The program according to any one of claims 1 to 8. The approximating step approximates the output value by LSH.
The program according to claim 9. The determination step determines a distance scale between Euclidean distance, cosine distance or Hamming distance between the output value and the candidate of the similar image, and determines the similar image by comparing the distance scales.
The program according to any one of claims 1 to 10. A first extraction step of extracting a feature amount from one image;
A second extraction step of extracting the output values of all connected layers after one or more convolutional layers of a convolutional neural network (CNN) based on the feature amount;
A determination step of determining a similar image similar to the one image based on the output value;
An image processing method comprising: A system comprising one or more computers,
The one or more computers are
A first extraction step of extracting a feature amount from one image;
A second extraction step of extracting the output values of all connected layers after one or more convolutional layers of a convolutional neural network (CNN) based on the feature amount;
A determination step of determining a similar image similar to the one image based on the output value;
Run the system.