Fine granularity classification recognition method and object part location and feature extraction method thereof

Abstract

The invention provides a fine granularity classification recognition method and an object part location and feature extraction method thereof. The fine granularity classification recognition method and the object part location and feature extraction method thereof well achieve object part location and feature expression in fine granularity classification recognition. For object part location, a series of part detectors trained by supervised learning are utilized, the methods just detect the part with small deformation in consideration of the posture change and deformation influence of targets to be located, different detectors are trained for the same object part by adopting the posture clustering method, and therefore the posture change of objects is taken into account. For feature expression of the objects or parts, features are extracted at multiple dimensions and multiple positions according to the methods and then fused to be used for final object expression, and therefore the features have certain dimension and translation invariance. According to the methods, object part location and feature expression have certain complementarity at the same time, and therefore the accuracy of fine granularity classification recognition can be effectively improved.

Description

technical field [0001] The present invention relates to a method in the technical field of image processing, in particular to a fine-grained category recognition method, and a partial location and feature extraction method for objects involved in the recognition problem. Background technique [0002] The goal of fine-grained classification problems is to distinguish hundreds of multiple subcategories under the same category, such as distinguishing different categories of flowers, birds, dogs, etc. It is very difficult for non-professionals to identify these subcategories, and the fine-grained classification problem is proposed to solve the problem of non-professionals identifying these similar subcategories. The user only needs to give the target object, and through the fine category recognition method, the category of the target object can be returned, and a series of characteristics of the subcategory can be obtained. Unlike general class recognition problems (such as dis...

AI Technical Summary

Problems solved by technology

When the detected part of the object has a large deviation from the real position, this feature cannot overcome this translation change very well

Images