| 目标多种多值属性的端端快速识别网络 |
| |
| 引用本文： | 周伦钢,孙怡峰,王坤,吴疆,黄维贵,李炳龙.目标多种多值属性的端端快速识别网络[J].计算机工程与应用,2021,57(9):182-190. |
| |
| 作者姓名： | 周伦钢 孙怡峰 王坤 吴疆 黄维贵 李炳龙 |
| |
| 作者单位： | 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 |
| |
| 基金项目： | 工信部2018年大数据产业发展试点示范项目;郑州市重大科技创新专项项目 |
| |
| 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 |
End to End Object Recognition Algorithm for Multi-attributes of Multi-values |
| |
| ZHOU Lungang,SUN Yifeng,WANG Kun,WU Jiang,HUANG Weigui,LI Binglong.End to End Object Recognition Algorithm for Multi-attributes of Multi-values[J].Computer Engineering and Applications,2021,57(9):182-190. |
| |
| Authors: | ZHOU Lungang SUN Yifeng WANG Kun WU Jiang HUANG Weigui LI Binglong |
| |
| Affiliation: | 1.Henan Industrial School, Zhengzhou 450002, China
2.Information Engineering University, Zhengzhou 450001, China
3.Zhengzhou Xinda Institute of Advanced Technology, Zhengzhou 450001, China |
| |
| 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. |
| |
| Keywords: | object detection attribute recognition deep learning convolutional neural network image recognition |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载全文 |
