计算机工程与应用 ›› 2021, Vol. 57 ›› Issue (9): 182-190.DOI: 10.3778/j.issn.1002-8331.1912-0403

• 模式识别与人工智能 • 上一篇    下一篇

目标多种多值属性的端端快速识别网络

周伦钢,孙怡峰,王坤,吴疆,黄维贵,李炳龙   

  1. 1.河南省工业学校,郑州 450002
    2.信息工程大学,郑州 450001
    3.郑州信大先进技术研究院,郑州 450001
  • 出版日期:2021-05-01 发布日期:2021-04-29

End to End Object Recognition Algorithm for Multi-attributes of Multi-values

ZHOU Lungang, SUN Yifeng, WANG Kun, WU Jiang, HUANG Weigui, LI Binglong   

  1. 1.Henan Industrial School, Zhengzhou 450002, China
    2.Information Engineering University, Zhengzhou 450001, China
    3.Zhengzhou Xinda Institute of Advanced Technology, Zhengzhou 450001, China
  • Online:2021-05-01 Published:2021-04-29

摘要:

为提高图像目标多种多值属性的识别速度,提出一种端到端的识别算法。采用修正的YoloV3网络作为主网络,确定目标的boundingbox;依据属性独立特性构造子网络,多个子网络共享由boundingbox确定的主网络深层次特征,进行推断,并采用多值输出满足多值属性的识别。在训练过程中,采用了三阶段分目标训练。实验结果验证了该算法在识别准确度和时间效率上的优良性能。

关键词: 目标检测, 属性识别, 深度学习, 卷积神经网络, 图像识别

Abstract:

In order to improve image object recognition speed for multi-attributes of multi-values, an end-to-end recognition algorithm is proposed. Firstly, the modified YoloV3 network is used as main network in order to detect the object bounding boxes. Sub-networks are constructed according to the independent attributes. Sub-networks share the deep bounding box features of main network and adopt multi-outputs to recognize the attributes multi-values. There are three stages with different objective functions in the training process. Experimental results show that the proposed algorithm has good performance.

Key words: object detection, attribute recognition, deep learning, convolutional neural network, image recognition