郑州大学学报（理学版）2019，Vol.51Issue(3)：55-60,6.DOI:10.13705/j.issn.1671-6841.2018157
多尺度区域特征的细粒度分类算法研究
Multi-scale Region Features Algorithm for Fine-grained Classification
摘要
Abstract
Intending to reduce the influence of complex background on fine-grained classification, as well as to study the global information and local information of the target objects extracted from the convolu-tional neural network for fine-grained tasks, a fine-grained classification method based on multi-scale re-gion feature was proposed. The method FASTER-RCNN framework was to train three convolution models to locate multi-scale object regions. Then the bounding box constraint and Helen constraint were applied to improve the location accuracy of the detected object. Finally, the extracted multi-scaled region features were combined to train a SVM classifier for fine-grained classification. The proposed method was tested in Caltech-UCSD bird datasets and CompCars vehicle datasets. The results showed that the accuracy of clas-sification in Caltech-UCSD bird datasets was 82.8%. It increased by 7.5 % than the method without multi-scale region features. Compared with part-based RCNN, it increased by 8.9 %. The results showed that the accuracy of classification in CompCars was 93.5%. It increased by 8.3 % than the method with-out multi-scale region features. Compared with GoogleNet, it increased by 2.3 %.关键词
精细识别/神经网络微调/包围盒约束/海伦约束算法Key words
fine-grained recognition/neural network fine-tuning/box constraint/Helen constraint algo-rithm分类
信息技术与安全科学引用本文复制引用
熊昌镇,蒋杰..多尺度区域特征的细粒度分类算法研究[J].郑州大学学报（理学版）,2019,51(3):55-60,6.基金项目
国家重点研发计划项目(2017YFC0821102). （2017YFC0821102）
