{"m1":["resume_head","resume_name"],"m2":[],"m3":["resume_base_info","resume_job","resume_edu","resume_skill","resume_work","resume_internship","resume_honor","resume_project","resume_portfolio","resume_school_info","resume_hobby","resume_summary"],"m4":[]}
.resume_main[data_color] .skill_item .skill_slider span::before{background-color:${color};}
.resume_main[data_color] .skill_slider s i{background-color:${relative_skill_color};}
.resume_main[data_color] .skill_style_01.skill_item .skill_slider s {border-color:${relative_skill_color};}
.resume_main[data_color] .skill_style_01.skill_item .skill_slider s i{background-color:${relative_skill_color};}
.resume_main[data_color] .skill_style_04.skill_item .skill_slider[data_level="average"] i,.resume_main[data_color] .skill_style_07.skill_item .skill_slider[data_level="average"] i{box-shadow:24px 0 0 ${relative_skill_color}, 48px 0 0 #ccc, 72px 0 0 #ccc, 96px 0 0 #ccc, 120px 0 0 #ccc;}
.resume_main[data_color] .skill_style_04.skill_item .skill_slider[data_level="good"] i,.resume_main[data_color] .skill_style_07.skill_item .skill_slider[data_level="good"] i{box-shadow:24px 0 0 ${relative_skill_color}, 48px 0 0 ${relative_skill_color}, 72px 0 0 #ccc, 96px 0 0 #ccc, 120px 0 0 #ccc;}
.resume_main[data_color] .skill_style_04.skill_item .skill_slider[data_level="advanced"] i,.resume_main[data_color] .skill_style_07.skill_item .skill_slider[data_level="advanced"] i{box-shadow:24px 0 0 ${relative_skill_color}, 48px 0 0 ${relative_skill_color}, 72px 0 0 ${relative_skill_color}, 96px 0 0 #ccc, 120px 0 0 #ccc;}
.resume_main[data_color] .skill_style_04.skill_item .skill_slider[data_level="expert"] i,.resume_main[data_color] .skill_style_07.skill_item .skill_slider[data_level="expert"] i{box-shadow:24px 0 0 ${relative_skill_color}, 48px 0 0 ${relative_skill_color}, 72px 0 0 ${relative_skill_color}, 96px 0 0 ${relative_skill_color}, 120px 0 0 #ccc;}
.resume_main[data_color] .skill_style_08.skill_item .skill_slider[data_level="average"] i{box-shadow:9px 0 0 ${relative_skill_color}, 18px 0 0 ${relative_skill_color}, 27px 0 0 ${relative_skill_color}, 36px 0 0 ${relative_skill_color}, 45px 0 0 ${relative_skill_color},54px 0 0 #ccc,63px 0 0 #ccc,72px 0 0 #ccc,81px 0 0 #ccc;}
.resume_main[data_color] .skill_style_08.skill_item .skill_slider[data_level="good"] i{box-shadow:9px 0 0 ${relative_skill_color}, 18px 0 0 ${relative_skill_color}, 27px 0 0 ${relative_skill_color}, 36px 0 0 ${relative_skill_color}, 45px 0 0 ${relative_skill_color},54px 0 0 ${relative_skill_color},63px 0 0 #ccc,72px 0 0 #ccc,81px 0 0 #ccc;}
.resume_main[data_color] .skill_style_08.skill_item .skill_slider[data_level="advanced"] i{box-shadow:9px 0 0 ${relative_skill_color}, 18px 0 0 ${relative_skill_color}, 27px 0 0 ${relative_skill_color}, 36px 0 0 ${relative_skill_color}, 45px 0 0 ${relative_skill_color},54px 0 0 ${relative_skill_color},63px 0 0 ${relative_skill_color},72px 0 0 #ccc,81px 0 0 #ccc;}
.resume_main[data_color] .skill_style_08.skill_item .skill_slider[data_level="expert"] i{box-shadow:9px 0 0 ${relative_skill_color}, 18px 0 0 ${relative_skill_color}, 27px 0 0 ${relative_skill_color}, 36px 0 0 ${relative_skill_color}, 45px 0 0 ${relative_skill_color},54px 0 0 ${relative_skill_color},63px 0 0 ${relative_skill_color},72px 0 0 ${relative_skill_color},81px 0 0 #ccc;}
.resume_main[data_color] .hobby_item .hobby_item_con .hobby_item_list a.alifont{border-color:${relative_hobby_color};color:${relative_hobby_color}; }
/* ������ */
.resume_main[data_color] .resume_cover .cover_html svg [data-svg="fill"] {fill:${color};}
.resume_main[data_color] .resume_cover .cover_html svg [data-svg="stroke"] {stroke:${color};}
.resume_main[data_color] .resume_letter .letter_html svg [data-svg="fill"] {fill:${color};}
.resume_main[data_color] .resume_letter .letter_html svg [data-svg="stroke"] {stroke:${color};}
.resume_main[data_color] .resume_letter .letter_html svg [data-fill="fill"] {fill:${color};}
.resume_main[data_color] .resume_cover[data-type="07"] .resume_cover_avatar{border-color: ${color};}
.resume_main[data_color] .resume_cover[data-type="07"] .resume_cover_content{background:${color}}
.resume_main[data_color] .resume_cover[data-type="07"] .cover_item_list a.alifont{color: ${color};}
.resume_main[data_color] .resume_cover[data-type="08"] .resume_cover_content::after{background:${color}}
.resume_main[data_color] .resume_cover[data-type="09"] .resume_cover_content{background:${color}}
.resume_main[data_color] .resume_cover[data-type="09"] .cover_item_list a.alifont{color: ${color};}
.resume_main[data_color] .resume_cover[data-type="10"]{background-color:${color}}
.resume_main[data_color] .resume_cover[data-type="11"] .resume_cover_content{background-color:${color}}
.resume_main[data_color] .resume_cover[data-type="14"]{background-color:${color}}
.resume_main[data_color] .resume_cover[data-type="15"]{background-color:${color}}
.resume_main[data_color] .resume_cover[data-type="19"] .resume_cover_word::before{background-color:${color}}
.resume_main[data_color] .resume_cover[data-type="20"]{background-color:${color}}
.resume_main[data_color] .resume_letter[data-type="06"]{background-color:${color}}
.resume_main[data_color] .resume_letter[data-type="12"]{background-color:${color}}
.resume_main[data_color] .resume_m3 .resume_item dt span.resume_item_title_span{color:${color}; border-color:${color};}
["sex","age","nation","education","marriageStatus","politicalStatus","city","jobYear","mobile","email"]
-
基本信息
-
-
姓名
-
锤子简历
梦想每个人都有,但不是每个人都有勇气去坚信,我有!
-
教育背景
-
2014.09 - 2018.06
锤子简历大学
计算机与信息技术
GPA:3.72/4(专业前10%) GRE:324
-
工作经验
-
2019年12月 - 至今
锤子简历信息有限公司
图像识别开发工程师
- 基础的图像卷积模块优化,通用于图像预处理;对比患者的影像图片,进行图像匹配。
- 对于肿瘤图形的对比匹配图像分割的相关算法的研究。
- 定位目标区域的动态轮廓匹配算法研究,对图像清晰度进行研究,工业检测AO,使用halcon检测车载显示屏缺陷。
- 对公司整体模型调参算法开发,用Python编写项目中需要的功能性模块。
- 根据采集到的数据挑选最优的数学模型初步进行拟合操作绘制图像。
- 用Opencv对图像进行数据预处理(如图像裁剪,降噪,数据增强等),运用matplotib绘制分析参数的曲线,优化模型,选择最优参数。
2018年3月 - 2019年12月
锤子简历科技有限公司
图像识别开发工程师
- 在Ubuntu上搭建ROS操作系统,并搭建MOOE导航系统;
- 开发基于激光雷达的SLAM导航、路径规划、运动控制、智能交管系统等算法,并维护及优化;
- 利用图像识别开发机器人底盘自主充电程序、小车识别栈板并运动顶起栈板程序;
- 编写shell脚本对Linux系统及程序进行管理控制;
- 负责图像识别开发工作,参与物体检测神经网络搭建及调测;
-
项目经验
-
2021年3月 - 2021年11月
项目工程
图像识别开发工程师
- 将两张同源的超声图像通过图像特征点进行匹配。
- 使用harrislaplace进行金字塔式寻找角点。
- 使用两个卷积,x和y方向的二维高斯一介导数,即达到降噪和寻找梯度的作用。
- 求局部最大值,即特征点,对相同位置的金字塔中的特征点,使用laplace局部最大值,即特征点所描述的范围。使用SIFT描述子来描述特征点的特征。
- 在harris中求得的方向,在该方向上取laplace描述的范围的矩形窗口。
- 将窗口分为4*4的小窗口,每个窗口分为8个方向求HOG,得到128维的特征向量,使用Hungarian方法进行bipartitematch进行两两匹配,使用RANSAC筛选处于同个仿射变换的匹配。
-
自我评价
-
本人对待工作踏实,认真,并且极富工作和团队精神,因此在工作和生活中结交了许多朋友,具有良好的适应性和熟练的沟通技巧,相信能够协助主管人员出色地完成各项工作。综合素质佳,能够吃苦耐劳,忠诚稳重坚守诚信正直原则,感谢您在百忙之中阅览我的简历,静候佳音!
-
作品展示
-
+(支持jpg/png格式,单张图片不超过2M,最多支持添加8张图片)