Image recognition device, image recognition method, and integrated circuit

摘要

An image recognition device that improves the accuracy of generic object recognition compared with conventional technologies by reducing the influence of the position, size, background clutter and the like of an object that is targeted to be recognized in the input image by the generic object recognition. The image recognition device performs a generic object recognition and includes: a segmenting unit configured to segment an input image into a plurality of regions in accordance with meanings extracted from content of the input image; a generating unit configured to compute feature data for each of the plurality of regions and generate feature data of the input image reflecting the computed feature data; and a checking unit configured to check whether or not a recognition-target object is present in the input image in accordance with the feature data of the input image.

主权项

1. An image recognition device for performing a generic object recognition using spatial pyramid matching, comprising:
a non-transitory memory storing a program; and a hardware processor configured to execute the program and to cause the image recognition device to operate as the following units stored in the non-transitory memory: a segmenting unit configured to segment an input image by pyramid matching into a plurality of increasingly fine regions in accordance with information extracted from content of the input image; a generating unit configured to compute feature data for each of the plurality of regions and generate feature data of the input image reflecting the computed feature data; and a checking unit configured to check whether or not a recognition-target object is present in the input image in accordance with the feature data of the input image: wherein the segmenting unit generates a score map by mapping, for each of a plurality of pixels constituting the input image, a probability of being a pixel pertaining to the recognition-target object, generates a semantic map by segmenting the score map into a plurality of levels by using a plurality of thresholds, and uses the semantic map as information representing the information extracted from the content of the input image.