1. 毕业设计（论文）的内容和要求

本课题为基于深度学习的特定目标识别，在摄像装置采集的图像中，针对指定目标进行检测与识别。

主要包括三个组成部分，分别为：图像预处理、目标特征训练、特定目标检测与识别。

本设计从已知的图像中提取出特定的目标特征，再从其它图像中高效找出同一目标并进行标记。

2. 参考文献

[1] ElAlami M E. A novel image retrieval model based on the most relevant features[J]. Knowledge-Based Systems, 2011, 24(1): 23-32. [2]Jhanwar N, Chaudhuri S, Seetharaman G, et al. Content based image retrieval using motif cooccurrence matrix[J]. Image and Vision Computing, 2004, 22(14): 1211-1220. [3]Iqbal K, Odetayo M O, James A. Content-based image retrieval approach for biometric security using colour, texture and shape features controlled by fuzzy heuristics[J]. Journal of Computer and System Sciences, 2012, 78(4): 1258-1277. [4]Rashedi E, Nezamabadi-Pour H, Saryazdi S. A simultaneous feature adaptation and feature selection method for content-based image retrieval systems[J]. Knowledge-Based Systems, 2013, 39: 85-94. [5]ElAlami M E. A new matching strategy for content based image retrieval system[J]. Applied Soft Computing, 2014, 14: 407-418. [6]Di Lecce V, Guerriero A. An evaluation of the effectiveness of image features for image retrieval[J]. Journal of Visual Communication and Image Representation, 1999, 10(4): 351-362. [7]Zeng S, Huang R, Wang H, et al. Image retrieval using spatiograms of colors quantized by Gaussian Mixture Models[J]. Neurocomputing, 2016, 171: 673-684. [8]Yildizer E, Balci A M, Jarada T N, et al. Integrating wavelets with clustering and indexing for effective content-based image retrieval[J]. Knowledge-Based Systems, 2012, 31: 55-66. [9]万维. 基于深度学习的目标检测算法研究及应用[D]. [10]梁鑫, 徐慧. 基于深度学习神经网络的SAR图像目标识别算法[J]. 江汉大学学报(自然科学版), 2016, 44(2):131-136. [11]文孟飞, 胡超, 刘伟荣. 一种基于深度学习的异构多模态目标识别方法[J]. 中南大学学报(自然科学版), 2016, 47(5):1580-1587.

3. 毕业设计（论文）进程安排

2018-12-21~2019-1-10 查阅大量资料，理解系统基本原理，完成开题报告 2019-1-11~2019-2-10 对系统流程进行设计，掌握模块要求 2019-2-11~2019-3-31 进行系统软件设计，编写程序 2019-4-1~2019-4-30 系统软、硬件调试，各模块联调 2019-5-1~2019-5-31 论文撰写 2019-6-1~2019-6-10 查漏补缺 准备答辩PPT，准备答辩