Apparatus and method for food search service
First Claim
Patent Images
1. An apparatus for food search service, comprising:
- a processor; and
one or more units comprising executable code configured and executed by the processor using algorithm associated with a non-transitory storage device,wherein the one or more units comprise;
a food region using the processor to detect regions in an image where food is present and extract a plurality of candidate regions;
a candidate region using the processor to cluster the candidate regions into groups according to a ratio of overlap between the candidate regions; and
a search result using the processor to determine a position of a food region and a food item from the grouped candidate regions based on convolutional neural network trained with deep learning.
1 Assignment
0 Petitions
Accused Products
Abstract
An apparatus for food search service includes a food region extractor configured to perform detection in regions in an image where food is present and extract a plurality of candidate regions; a candidate region refiner configured to cluster the candidate regions into groups according to a ratio of overlap between the candidate regions; and a search result generator configured to determine a position of a food region and a food item from the grouped candidate regions.
6 Citations
14 Claims
-
1. An apparatus for food search service, comprising:
-
a processor; and one or more units comprising executable code configured and executed by the processor using algorithm associated with a non-transitory storage device, wherein the one or more units comprise; a food region using the processor to detect regions in an image where food is present and extract a plurality of candidate regions; a candidate region using the processor to cluster the candidate regions into groups according to a ratio of overlap between the candidate regions; and a search result using the processor to determine a position of a food region and a food item from the grouped candidate regions based on convolutional neural network trained with deep learning. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A method for food search service, the method being implemented by a processor executing instructions stored in a non-transitory computer-readable medium and comprising:
-
detecting, by a food region using the processor, regions in an image where food is present and extracting a plurality of candidate regions; clustering, by a candidate region using the processor, the candidate regions into groups according to a ratio of overlap between the candidate regions; and determining, by a search result using the processor, a position of a food region and a food item from the grouped candidate regions based on convolutional neural network trained with deep learning. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
Specification