基于异构特征聚合的局部视图扭曲型纸币识别

如何识别同一物体的不同结构的表现形式,对于机器而言,是一个比较困难的识别工作.本文以易变形的纸币为例,提出了一种基于异构特征聚合的局部视图扭曲型纸币识别方法.首先利用灰度梯度共生矩阵、Haishoku算法和圆形LBP分别获得纹理风格、色谱风格和纹理,这些特征从不同的角度描述了局部纸币图像,然后通过VGG-16、ResN...

Local View Distorted Banknote Recognition Based on Heterogeneous Feature Aggregation

The same object may has different forms of manifestation for different structures in an unrestricted environment,how to recognize such objects is a relatively difficult recognition task for the machine.The banknote is a kind of object that can be easily distorted,as a result,in this paper,taking the distorted banknotes as an example,a local view distorted banknote recognition method based on heterogeneous feature aggregation was proposed.The texture style,color spectrum style and texture of local view distorted banknotes from multiple views were obtained,and these features describe local view distorted banknote images from different perspectives,so as to capture the semantics of local view distorted banknote images as much as possible.As a result,firstly,the gray gradient co-occurrence matrix was used to obtain texture style by carrying out secondary statistical calculation,the Haishoku algorithm was used to obtain color spectrum style,and the circular LBP was used to obtain texture.Then,considering that the multi-view invariant features describe the distorted banknote image in the local view,the VGG-16,ResNet-18 and DenseNet-121 networks were used for each type of feature respectively in the proposed method,and these three types deep models were fused,that is,these three types models did not recognize separately,but learn the invariant feature to get the output feature,which was normalized and aggregated with the other two output features.The VGG-16 network learned invariant feature of texture style to obtain output feature,the ResNet-18 network learned invariant feature of color spectrum style to obtain output feature,and the DenseNet-121 network learned invariant feature of texture to obtain output feature.These output features were aggregated to obtain aggregated features.After aggregated,aggregated features were input into the recognition layer Softmax to achieve the fusion of three types models,and recognize local view distorted banknote images.We had carried out a lot of experiments to verify the effectiveness of the proposed method through three aspects(i.e.aggregation effect of output features based on invariant features,performance comparison of multiple models fusion,performance comparison with existing methods)and four evaluation indexes(i.e.accuracy,precision,recall and F1).Extensive experiment results showed that the recognition rate of this proposed method was higher and this method could be extended to other visual images,and aggregation of multiple classes features and fusion of different types of models could both capture the semantics of the local view distorted banknote images to the greatest extent,and the proposed method was universal,which could fuse different types of deep networks and apply them.Moreover,multiple classes features aggregation achieved higher recognition than the aggregation based on single and dual features in accuracy,precision,recall and F1,and multiple types models fusion obtained higher recognition than the recognition of the fusion based on single type and two types models in accuracy,precision,recall and F1.In addition,the proposed method had achieved relatively good results compared with the existing state-of-the-art methods under the evaluation criteria of accuracy,time complexity and so on.