CN108596250B - 图像特征编码方法、终端设备及计算机可读存储介质 - Google Patents

图像特征编码方法、终端设备及计算机可读存储介质 Download PDF

Info

Publication number
CN108596250B
CN108596250B CN201810375628.8A CN201810375628A CN108596250B CN 108596250 B CN108596250 B CN 108596250B CN 201810375628 A CN201810375628 A CN 201810375628A CN 108596250 B CN108596250 B CN 108596250B
Authority
CN
China
Prior art keywords
image
pixel
gabor
histogram
response
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810375628.8A
Other languages
English (en)
Other versions
CN108596250A (zh
Inventor
沈琳琳
李绵
解为成
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen University
Original Assignee
Shenzhen University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen University filed Critical Shenzhen University
Priority to CN201810375628.8A priority Critical patent/CN108596250B/zh
Publication of CN108596250A publication Critical patent/CN108596250A/zh
Application granted granted Critical
Publication of CN108596250B publication Critical patent/CN108596250B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • G06F18/241Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/50Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
    • G06V10/507Summing image-intensity values; Histogram projection analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/513Sparse representations

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Multimedia (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)

Abstract

本发明公开了一种图像特征编码方法、终端设备及计算机可读存储介质,其中图像特征编码方法:获取待处理图像,采用Gabor滤波器和待处理图像进行卷积,得到Gabor响应图像并提取像素点的像素值;根据Gabor滤波器的方向对响应图像的每个像素点确定多个与该像素点相邻的像素点,像素点之间形成多边形邻域;根据像素点的像素值的大小关系进行排序,并进行编码,得到编码图像。根据多边形邻域有效地提取Gabor响应的纹理信息,进而对Gabor响应上的像素值的大小关系进行自适应方向上的排序编码,图像进行Gabor变换后充分利用不同方向的纹理信息,利用编码的特征向量进行图像识别,实现图像识别准确度高、鲁棒性好。

Description

图像特征编码方法、终端设备及计算机可读存储介质
技术领域
本发明涉及图像处理技术领域,尤其涉及一种图像特征编码方法、终端设备及计算机可读存储介质。
背景技术
当今社会已经进入信息时代,传统的以密码为特征的生物特征识别技术,如口令码、PIN码等越来越难以满足当下的信息安全需求。生物特征识别作为一种颇具应用价值和前景的技术手段能够提高身份认证的安全性,并能以更加便捷的方式满足日常生活中的加解密需求。在对稳定性、识别精度、用户接受度、便捷程度以及低硬件成本等方面综合考量下,发现掌纹识别与传统生物特征识别相比具有天然优势。这些固有的诸多优点也使得掌纹识别技术作为一种新兴的生物特征识别技术逐步进入大众视野,掌纹识别技术已在近年来成为生物特征识别应用领域的热点之一。
Gabor滤波器已经广泛应用于掌纹识别和人脸识别上。Gabor滤波器能够良好地体现二维纹理特征和二维空间位置的变化,在纹理特征提取的生物识别技术中得到了广泛的应用。然而,大多数现有方法在图像进行Gabor变换后并没有充分利用到所有方向的纹理信息,对于不同方向的响应信息利用不足,对于不同方向的响应都做了同一个处理,而且对于掌纹获取时噪声和偏移造成的影响,大部分采取屏蔽噪声的方法,预处理过程繁琐,方法鲁棒形差。
发明内容
本发明的主要目的在于提供一种图像特征编码方法、终端设备及计算机可读存储介质,旨在解决现有技术中图像进行Gabor变换后对不同方向的纹理信息利用不足,图像识别准确度低以及图像特征提取方法鲁棒性差的问题。
为实现上述目的,本发明提供一种图像特征编码方法,包括:
获取待处理图像,采用多个Gabor滤波器和待处理图像进行卷积操作或者傅立叶变换,得到与Gabor滤波器个数相同的Gabor响应图像,提取Gabor响应图像中每个像素点的像素值;
根据Gabor滤波器的方向对所述响应图像的每个像素点确定至少两个与所述像素点相邻的像素点,像素点之间形成多边形邻域;
根据所述像素点的的像素值大小关系进行排序,通过预设的排序编码表,对所述像素点的的像素值大小关系进行编码,得到编码图像。
可选地,所述采用多个Gabor滤波器和待处理图像进行卷积操作或者傅立叶变换,得到与Gabor滤波器个数相同的Gabor响应图像,提取Gabor响应图像中每个像素点的像素值的步骤包括:
采用5个尺度和8个方向的Gabor滤波器对待处理图像进行卷积;
或者将待处理图像与5个尺度和8个方向的Gabor滤波器分别进行快速傅立叶变换,将变换得到的待处理图像和Gabor滤波器进行乘积操作,再将所述乘积进行快速反傅立叶变换;
得到40幅Gabor虚部或者实部响应图像,提取所述Gabor虚部或者实部响应图像中每个像素点的像素值。
可选地,所述得到与Gabor滤波器个数相同的Gabor响应图像,提取Gabor响应图像中每个像素点的像素值的步骤包括:
得到Gabor幅值响应图像,提取所述Gabor幅值响应图像中每个像素点的像素值;
或者得到Gabor相位响应图像,提取所述Gabor相位响应图像中每个像素点的像素值。
可选地,所述根据Gabor滤波器的方向对所述响应图像的每个像素点确定至少两个与所述像素点相邻的像素点,像素点之间形成多边形邻域的步骤包括:
根据Gabor滤波器的8个方向对所述响应图像的每个像素点确定3个与所述像素点相邻的像素点,像素点之间形成平行四边形邻域。
可选地,所述通过预设的排序编码表,对所述像素点的像素值的大小关系进行编码的步骤包括:
将所述像素点的像素值的大小关系与预设的排序编码表进行比对,确定所述像素点的像素值的大小关系对应的编码。
可选地,所述对所述像素点的像素值的大小关系进行编码,得到编码图像的步骤之后,还包括:
将所述编码图像划分为多个图像小块,统计每个图像小块内各个编码值长度,得到局部直方图;
将所有图像小块的局部直方图进行连接,得到所述编码图像的直方图;
将所有编码图像的直方图进行连接,得到目标直方图。
可选地,所述将所有编码图像的直方图进行连接,得到目标直方图的步骤之后,还包括:
获取待测试图像,基于所述图像特征编码方法得到测试图像直方图;
将测试图像直方图与目标直方图进行比对,确定所述待测试图像是否为目标图像。
可选地,所述将测试图像直方图与目标直方图进行比对的步骤包括:
通过欧几里得或曼哈顿距离进行计算,将测试图像直方图与目标直方图进行比对;
或者通过稀疏重构将测试图像直方图与目标直方图进行比对。
本发明还提供一种终端设备,所述终端设备包括:存储器、处理器以及存储在所述存储器上并可在所述处理器上运行的图像特征编码程序,所述图像特征编码程序被所述处理器执行时实现上述的图像特征编码方法的步骤。
本发明还提供一种计算机可读存储介质,所述计算机可读存储介质上存储有图像特征编码程序,所述图像特征编码程序被处理器执行时实现上述的图像特征编码方法的步骤。
本发明提供的一种图像特征编码方法、终端设备及计算机可读存储介质,通过获取待处理图像,采用多个Gabor滤波器和待处理图像进行卷积操作或者傅立叶变换,得到与Gabor滤波器个数相同的Gabor响应图像,提取Gabor响应图像中每个像素点的像素值;根据Gabor滤波器的方向对所述响应图像的每个像素点确定至少两个与所述像素点相邻的像素点,像素点之间形成多边形邻域;根据所述像素点的像素值的大小关系进行排序,通过预设的排序编码表,对所述像素点的像素值的大小关系进行编码,得到编码图像。通过根据Gabor滤波器的方向对应的平行四边形邻域有效地提取Gabor响应的纹理信息,进而根据Gabor滤波器的不同方向进行自适应像素点的像素值的大小关系排序编码,通过编码的特征向量进行图像识别,实现图像特征提取速度快、图像进行Gabor变换后充分利用不同方向的纹理信息,图像识别准确度高以及图像特征提取方法鲁棒性好的技术效果。
附图说明
图1是本发明实施例方案涉及的硬件运行环境的终端/装置结构示意图;
图2为本发明图像特征编码方法一实施例的流程示意图;
图3为本发明图像特征编码方法中得到Gabor响应图像的示意图;
图4为本发明图像特征编码方法中不同Gabor滤波器的方向下的邻域设计;
图5为本发明图像特征编码方法中不同Gabor滤波器的方向下的另一邻域设计;
图6为本发明图像特征编码方法中根据像素点的像素值的大小关系进行编码得到编码图像的示意图;
图7为本发明图像特征编码方法中对编码图像处理得到目标直方图的示意图;
图8为本发明图像特征编码方法中对待测试图像进行识别的流程示意图。
本发明目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不用于限定本发明。
在后续的描述中,使用用于表示元件的诸如“模块”、“部件”或“单元”的后缀仅为了有利于本发明的说明,其本身没有特定的意义。因此,“模块”、“部件”或“单元”可以混合地使用。
如图1所示,图1是本发明实施例方案涉及的硬件运行环境的终端设备(以下简称终端)结构示意图。
本发明实施例终端可以是PC,也可以是智能手机、平板电脑、电子书阅读器、MP3(Moving Picture Experts Group Audio Layer III,动态影像专家压缩标准音频层面3)播放器、MP4(Moving Picture Experts Group Audio Layer IV,动态影像专家压缩标准音频层面3)播放器、便携计算机等具有显示功能的可移动式终端设备。
如图1所示,该终端可以包括:处理器1001,例如CPU,网络接口1004,用户接口1003,存储器1005,通信总线1002。其中,通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏(Display)、输入单元比如键盘(Keyboard),可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如WI-FI接口)。存储器1005可以是高速RAM存储器,也可以是稳定的存储器(non-volatile memory),例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
可选地,终端还可以包括摄像头、RF(Radio Frequency,射频)电路,传感器、音频电路、WiFi模块等等。其中,传感器比如光传感器、运动传感器以及其他传感器。具体地,光传感器可包括环境光传感器及接近传感器,其中,环境光传感器可根据环境光线的明暗来调节显示屏的亮度,接近传感器可在移动终端移动到耳边时,关闭显示屏和/或背光。作为运动传感器的一种,重力加速度传感器可检测各个方向上(一般为三轴)加速度的大小,静止时可检测出重力的大小及方向,可用于识别移动终端姿态的应用(比如横竖屏切换、相关游戏、磁力计姿态校准)、振动识别相关功能(比如计步器、敲击)等;当然,移动终端还可配置陀螺仪、气压计、湿度计、温度计、红外线传感器等其他传感器,在此不再赘述。
本领域技术人员可以理解,图1中示出的终端结构并不构成对终端的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。
如图1所示,作为一种计算机存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及图像特征编码程序。
在图1所示的终端中,网络接口1004主要用于连接后台服务器,与后台服务器进行数据通信;用户接口1003主要用于连接客户端(用户端),与客户端进行数据通信;而处理器1001可以用于调用存储器1005中存储的图像特征编码程序。
基于上述终端硬件结构以及通信网络系统,提出本发明图像特征编码方法各个实施例。
本发明提供一种图像特征编码方法,在图像特征编码方法第一实施例中,参照附图2,该方法包括:
步骤S10,获取待处理图像,采用多个Gabor滤波器和待处理图像进行卷积操作或者傅立叶变换,得到与Gabor滤波器个数相同的Gabor响应图像,提取Gabor响应图像中每个像素点的像素值;
Gabor滤波器是一个带通滤波器。Gabor滤波器与哺乳动物视觉皮层简单细胞二维感受野剖面非常相似,具有优良的空间局部性和方向选择性,能够抓住图像局部区域内多个方向的空间频率和局部性结构特征。Gabor滤波器可以看作是一个对方向和尺度敏感的有方向性的显微镜。同时,Gabor滤波器也类似于增强边缘以及峰、谷、脊轮廓等底层图像特征,这相当于增强了被认为是面部关键部件的眼睛、鼻子、嘴巴等信息,同时也增强了诸如黑痣、酒窝、伤疤等局部特征,从而使得在保留总体人脸信息的同时增强局部特征性成为可能。
Gabor滤波器一般可分为5个尺度和8个方向,即40个不同的Gabor滤波器。Gabor滤波器实际上是时域中两个函数相乘,一个为高斯函数,一个为复指函数。由频域卷积定理可知,时域中两个函数相乘等于频域中两者的傅立叶变换相卷积,高斯函数的傅立叶变换是冲激函数,因为任何函数和冲激函数相卷积等于该函数,所以卷积的结果任然是高斯函数,即Gabor滤波器在频域中也是一个高斯函数形式,当在频域中对频域窗口尺寸和方向进行采样时,即获得不同尺度和方向的Gabor滤波器。
Gabor特征是一个复值响应,根据实部与虚部的不同选取方法,Gabor特征可分为奇特征、偶特征、幅值特征、相位特征等,偶特征为Gabor特征复值响应的实部,奇特征是相应的虚部。
如图3所示,通过对待处理图像采用5个尺度和8个方向的Gabor滤波器进行卷积操作或者傅立叶变换,得到40个Gabor响应图像,当然,也可以根据实际情况选择其他个数的Gabor滤波器进行卷积操作或者傅立叶变换,从而得到Gabor响应图像,响应可以是虚部、实部、幅值、相位等。
步骤S20,根据Gabor滤波器的方向对所述响应图像的每个像素点确定至少两个与所述像素点相邻的像素点,像素点之间形成多边形邻域;
对上面步骤中得到的每个响应图像的每个像素点根据Gabor滤波器的方向设定邻域编码方案,在一像素点附近确定多个像素点,例如2个、3个或者4个,像素点之间形成三角形邻域、四边形邻域或者五边形邻域。以4个像素点,形成平行四边形为例,如图4所示,虚线表示Gabor滤波器的方向,Gabor滤波器的8个方向分别为对Gabor滤波器的8个方向设计4种平行四边形邻域,平行四边形的顶点处即像素点,P0,P1,P2,P3这四个像素点。如图5所示,对Gabor滤波器的8个方向设计另外4种平行四边形邻域,平行四边形的顶点处即像素点,P0,P1,P2,P3这四个像素点。
步骤S30,根据所述像素点的像素值的大小关系进行排序,通过预设的排序编码表,对所述像素点的像素值的大小关系进行编码,得到编码图像。
预设的排序编码表,每一组像素点的像素值的大小关系对应一个编码,将所有的像素点的像素值的大小关系进行编码,并且对应存储,得到排序编码表。
具体地,步骤S30包括:
步骤S31,将排序得到的所述像素点的像素值的大小关系与预设的排序编码表进行比对,确定所述像素点的像素值的的大小关系对应的编码。
例如,P0,P1,P2,P3四个实部或者虚部响应图像中像素点的像素值的大小顺序为:P3>P2>P1>P0,该大小顺序对应的排序编码表中的编码为0,那么该四个像素点的像素值的大小关系顺序编码为0。对所有像素点均进行上述的排序操作,那么就会有24种大小关系,则,可以分别编号为0-23。对图像中的所有像素点编码完成,即得到编码图像。
如图6所示,根据Gabor滤波器方向选择图4(c)所示的平行四边形邻域,像素点P0,P1,P2和P3。根据这四个位置像素点的像素值的大小顺序,如,P3>P2>P1>P0,根据预设的排序编码表进行比对,将该排序编码为整数0。将每个响应图像的像素进行上述编码,则可以获得和响应图像大小相同的编码图像F。
将40个Gabor滤波器响应图像进行上述特征编码过程,则可以获得同样数目的Gabor特征编码图像。
在本实施例中,基于Gabor滤波器的特性,通过采用不同尺度和方向的Gabor滤波器对待处理图像进行卷积操作得到响应图像,并且对响应图像中每个像素点对应方向的多边形邻域上的像素点的像素值的大小关系进行排序,并对其编码,得到编码图像。引入多边形的邻域和方向自适应响应编码来表示图像每个方向的更多细节变化,对待处理图像提供出更多的细节信息,而且方向自适应响应编码是局部特征模式编码,可以更加减少待处理图像获取时造成的噪声和偏移的影响,不需要由于噪声采取屏蔽的做法,可以应用于包括非接触式、3D、多光谱等更多场景的数据库。
进一步地,在本发明图像特征编码方法一实施例中,步骤S10中所述采用多个Gabor滤波器和待处理图像进行卷积操作或者傅立叶变换,得到与Gabor滤波器个数相同的Gabor响应图像,提取Gabor响应图像中每个像素点的像素值的步骤包括:
步骤S11,采用5个尺度和8个方向的Gabor滤波器对待处理图像进行卷积;
或者将待处理图像与5个尺度和8个方向的Gabor滤波器分别进行快速傅立叶变换,将变换得到的待处理图像和Gabor滤波器进行乘积操作,再将所述乘积进行快速反傅立叶变换;
选择5个尺度和8个方向的Gabor滤波器,也就是40个Gabor滤波器对待处理图像进行卷积操作。或者与卷积操作类似,将待处理图像进行快速傅立叶变换,将5个尺度和8个方向的40个Gabor滤波器也进行快速傅立叶变换,将变换之后的待处理图像和40个Gabor滤波器分别相乘,再将所述乘积进行反傅立叶变换,两种不同方式均得到40幅Gabor响应图像。
具体地,5个尺度,8个方向的40个Gabor滤波器表示如下:
其中
u表示5个尺度,v表示8个方向,(x,y)为空间域像素点的位置,θv为Gabor滤波器的方向,fu为Gabor滤波器的尺度,fmax是最大采样频率,σ是窗函数的尺度,j代表虚数单位。
将40个Gabor滤波器和图像F(x,y)进行卷积操作,得到40个卷积后的响应图像
步骤S12,得到40幅Gabor虚部或者实部响应图像,提取所述Gabor虚部或者实部响应图像中每个像素点的像素值。
提取上述Gabor响应图像的Gabor虚部或者实部响应,偶特征为Gabor特征复值响应的实部,奇特征是相应的虚部,即提取偶特征或者奇特征,并提取所述Gabor虚部或者实部响应图像中每个像素点的像素值
当然通过得到的Gabor响应图像提取的响应也可以是Gabor幅值或者Gabor相位等。
在本实施例中,通过5个尺度和8个方向的Gabor滤波器对待处理图像进行卷积得到40幅Gabor响应图像,并且对Gabor响应图像的中像素点的像素值进行提取。利用不同尺度和方向的Gabor滤波器对待处理图像进行Gabor变换,使得处理之后的待处理图像显示更多的图像细节,利于对待处理图像的进一步处理或者识别,且准确率高,等误率低,鲁棒性强。
进一步地,在本发明图像特征编码方法一实施例中,在步骤S20中所述根据Gabor滤波器的方向对所述响应图像的每个像素点确定至少两个与所述像素点相邻的像素点,像素点之间形成多边形邻域的步骤,具体可以为:
步骤S21,根据Gabor滤波器的8个方向对所述响应图像的每个像素点确定3个与所述像素点相邻的像素点,像素点之间形成平行四边形邻域。
如图4所示,Gabor滤波器的8个方向分别为 对Gabor滤波器的8个方向设计4种平行四边形邻域,P0,P1,P2,P3这四个像素点在相应的平行四边形邻域顶点处。当然,如图5所示,也可以改变平行四边形的位置,或者采用三角形、正方形或者五边形等有更多或者更少像素点的多边形邻域,或者同时改变像素点的位置和个数,只要基于像素点处于Gabor滤波器的自适应方向对应的多边形邻域即可,在此不作具体限定。
在本实施例中,基于像素点处于Gabor滤波器的自适应方向对应的平行四边形邻域确定像素点处于平行四边形邻域的3个像素点,以自适应方向的平行四边形邻域来处理每个像素点,有效提取Gabor相应图像的纹理信息,准确率高。
可选地,在本发明图像特征编码方法一实施例中,步骤S30所述对所述像素点的像素值的大小关系进行编码,得到编码图像的步骤之后,还包括:
步骤S40,将所述编码图像划分为多个图像小块,统计每个图像小块内编码值长度,得到局部直方图;
将上述编码图像划分为m×n个图像小块,其中m与n为正整数,m与n可以相等也可以不相等。划分为m×n个图像小块之后,对每个图像小块内编码值进行统计,直接连接得到局部直方图。
步骤S50,将所有图像小块的局部直方图进行连接,得到所述编码图像的直方图;
步骤S60,将所有编码图像的直方图进行连接,得到目标直方图。
基于局部直方图,将所有图像小块的局部直方图直接连接,得到编码图像的直方图,然后根据每个编码图像的直方图,将其直接连接,即得到目标直方图,也就是待处理图像编码之后的直方图。
如图7所示,例如,上面实施例中得到的编码图像F,将编码图像F划分为5×5个图像小块,对每个图像内的编码值统计长度为24的直方图,将25个编码值长度为24的直方图连接,得到编码值长度为600编码图像。总共40幅编码图像可生成编码值长度为24000的直方图。
在步骤S60将所有编码图像的直方图进行连接,得到目标直方图之后,还包括:
步骤S70,获取待测试图像,基于所述图像特征编码方法得到测试图像直方图;
步骤S80,将测试图像直方图与目标直方图进行比对,确定所述待测试图像是否为目标图像。
如图8所示,当需要对某一图像进行测试,判断是否为目标图像或者将待测试图像进行匹配时,对获取的待测试图像,根据上面提到的图像特征编码方法,以及局部直方图法得到测试图像直方图。将测试图像直方图与图像集的目标直方图进行比对,即可以识别待测试图像与目标图像的匹配度。
其中,步骤S80中将测试图像直方图与目标直方图进行比对的比对方法可以是通过欧几里得或曼哈顿距离进行计算,将测试图像直方图与目标直方图进行比对;或者通过稀疏重构将测试图像直方图与注册集重构直方图进行比对。
欧几里得距离,二维空间中两个点之间的距离公式如下:
x1为第一个点的第一维坐标,x2为第一个点的第二维坐标;y1为第二个点的第一维坐标,y2为第二个点的第二维坐标。
欧几里得距离看作特征向量的相似程度,欧几里得距离越小,两个特征向量相似度就越大,欧几里得距离越大,两个特征向量相似度就越小。
曼哈顿距离,两个点在标准坐标系上的绝对轴距总和,二维空间中两个点之间的距离公式如下:
d=|x1-x2|+|y1-y2|
x1为第一个点的第一维坐标,x2为第一个点的第二维坐标;y1为第二个点的第一维坐标,y2为第二个点的第二维坐标。
曼哈顿距离看作特征向量的相似程度,曼哈顿距离越小,两个特征向量相似度就越大,曼哈顿距离越大,两个特征向量相似度就越小。
稀疏重构,把测试图像特征向量重构为注册集特征向量的稀疏线性组合,通过计算重构误差评价测试图像与目标图像的相似度。
除上述三种图像识别与匹配的方法之外,还可以采用其他图像识别与匹配方法,在此不作具体限定。
在本实施例中,通过利用图像特征编码方法得到的编码图像,并对编码图像直方化,得到直方图,利用直方图进行图像识别与匹配。无需用训练数据进行学习,使用简单,在不同的应用场合配置方便,而且通过平行四边形邻域提取Gabor响应的纹理信息准确率高,等误率低,鲁棒性强。
本发明还提供一种终端设备,所述终端设备包括:存储器、处理器以及存储在所述存储器上并可在所述处理器上运行的图像特征编码程序,所述图像特征编码程序被所述处理器执行时实现上述图像特征编码方法的步骤。
本发明还提供一种计算机可读存储介质,所述计算机可读存储介质上存储有图像特征编码程序,所述图像特征编码程序被处理器执行时实现上述的图像特征编码方法的步骤。
在本发明终端设备和计算机可读存储介质的实施例中,包含了上述图像特征编码方法各实施例的全部技术特征,说明书拓展和解释内容与上述图像特征编码方法各实施例基本相同,在此不做赘述。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本发明实施例序号仅仅为了描述,不代表实施例的优劣。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本发明各个实施例所述的方法。
以上仅为本发明的优选实施例,并非因此限制本发明的专利范围,凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本发明的专利保护范围内。

Claims (10)

1.一种图像特征编码方法,其特征在于,所述图像特征编码方法包括以下步骤:
获取待处理图像,采用多个Gabor滤波器和待处理图像进行卷积操作或者傅立叶变换,得到与Gabor滤波器个数相同的Gabor响应图像,提取Gabor响应图像中每个像素点的像素值;
根据Gabor滤波器的方向对所述响应图像的每个像素点确定至少两个与所述像素点相邻的像素点,像素点之间形成多边形邻域;
根据所述像素点的像素值的大小关系进行排序,通过预设的排序编码表,对所述像素点的像素值的大小关系进行编码,得到编码图像。
2.如权利要求1所述的图像特征编码方法,其特征在于,所述采用多个Gabor滤波器和待处理图像进行卷积操作或者傅立叶变换,得到与Gabor滤波器个数相同的Gabor响应图像,提取Gabor响应图像中每个像素点的像素值的步骤包括:
采用5个尺度和8个方向的Gabor滤波器对待处理图像进行卷积,或者将待处理图像与5个尺度和8个方向的Gabor滤波器分别进行快速傅立叶变换,将变换得到的待处理图像和Gabor滤波器进行乘积操作,再将所述乘积进行快速反傅立叶变换;
得到40幅Gabor虚部或者实部响应图像,提取所述Gabor虚部或者实部响应图像中每个像素点的像素值。
3.如权利要求1所述的图像特征编码方法,其特征在于,所述得到与Gabor滤波器个数相同的Gabor响应图像,提取Gabor响应图像中每个像素点的像素值的步骤包括:
得到Gabor幅值响应图像,提取所述Gabor幅值响应图像中每个像素点的像素值;
或者得到Gabor相位响应图像,提取所述Gabor相位响应图像中每个像素点的像素值。
4.如权利要求2所述的图像特征编码方法,其特征在于,所述根据Gabor滤波器的方向对所述响应图像的每个像素点确定至少两个与所述像素点相邻的像素点,像素点之间形成多边形邻域的步骤包括:
根据Gabor滤波器的8个方向对所述响应图像的每个像素点确定3个与所述像素点相邻的像素点,像素点之间形成平行四边形邻域。
5.如权利要求1所述的图像特征编码方法,其特征在于,所述通过预设的排序编码表,对所述像素点的像素值的大小关系进行编码的步骤包括:
将所述像素点的像素值的大小关系与预设的排序编码表进行比对,确定所述像素点的像素值的大小关系对应的编码。
6.如权利要求1所述的图像特征编码方法,其特征在于,所述对所述像素点的像素值的大小关系进行编码,得到编码图像的步骤之后,还包括:
将所述编码图像划分为多个图像小块,统计每个图像小块内各个编码值的长度,得到局部直方图;
将所有图像小块的局部直方图进行连接,得到所述编码图像的直方图;
将所有编码图像的直方图进行连接,得到目标直方图。
7.如权利要求6所述的图像特征编码方法,其特征在于,所述将所有编码图像的直方图进行连接,得到目标直方图的步骤之后,还包括:
获取待测试图像,基于所述图像特征编码方法得到测试图像直方图;
将测试图像直方图与目标直方图进行比对,确定所述待测试图像是否为目标图像。
8.如权利要求7所述的图像特征编码方法,其特征在于,所述将测试图像直方图与目标直方图进行比对的步骤包括:
通过欧几里得或曼哈顿距离进行计算,将测试图像直方图与目标直方图进行比对;
或者通过稀疏重构将测试图像直方图与目标直方图进行比对。
9.一种终端设备,其特征在于,所述终端设备包括:存储器、处理器以及存储在所述存储器上并可在所述处理器上运行的图像特征编码程序,所述图像特征编码程序被所述处理器执行时实现如权利要求1至8中任一项所述的图像特征编码方法的步骤。
10.一种计算机可读存储介质,其特征在于,所述计算机可读存储介质上存储有图像特征编码程序,所述图像特征编码程序被处理器执行时实现如权利要求1至8中任一项所述的图像特征编码方法的步骤。
CN201810375628.8A 2018-04-24 2018-04-24 图像特征编码方法、终端设备及计算机可读存储介质 Active CN108596250B (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810375628.8A CN108596250B (zh) 2018-04-24 2018-04-24 图像特征编码方法、终端设备及计算机可读存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810375628.8A CN108596250B (zh) 2018-04-24 2018-04-24 图像特征编码方法、终端设备及计算机可读存储介质

Publications (2)

Publication Number Publication Date
CN108596250A CN108596250A (zh) 2018-09-28
CN108596250B true CN108596250B (zh) 2019-05-14

Family

ID=63609383

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810375628.8A Active CN108596250B (zh) 2018-04-24 2018-04-24 图像特征编码方法、终端设备及计算机可读存储介质

Country Status (1)

Country Link
CN (1) CN108596250B (zh)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109598205A (zh) * 2018-11-09 2019-04-09 国网山东省电力公司淄博供电公司 基于Gabor变换的指纹特征提取与压缩编码的方法
CN109724364B (zh) * 2018-11-13 2020-11-20 徐州云创物业服务有限公司 存放物品容量解析平台
CN109829383B (zh) * 2018-12-29 2024-03-15 平安科技(深圳)有限公司 掌纹识别方法、装置和计算机设备
CN112488233B (zh) * 2020-12-09 2021-12-17 中国农业科学院农业资源与农业区划研究所 一种基于果纹图谱信息的编码和识别方法及装置
CN112667842B (zh) * 2020-12-29 2022-08-02 中国电子科技集团公司第五十八研究所 图像纹理检索方法
CN115861050A (zh) * 2022-08-29 2023-03-28 如你所视(北京)科技有限公司 用于生成全景图像的方法、装置、设备和存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101122949A (zh) * 2007-08-30 2008-02-13 中国科学技术大学 一种基于局部频率特征和局部方向特征的虹膜识别方法
CN101404060A (zh) * 2008-11-10 2009-04-08 北京航空航天大学 一种基于可见光与近红外Gabor信息融合的人脸识别方法
CN101763507A (zh) * 2010-01-20 2010-06-30 北京智慧眼科技发展有限公司 人脸识别方法及人脸识别系统
CN101854551A (zh) * 2010-06-08 2010-10-06 浙江大学 帧内预测模式编解码方法及装置
CN102223541A (zh) * 2011-07-14 2011-10-19 北京工业大学 一种混合图像的编码方法
WO2012018887A3 (en) * 2010-08-03 2012-04-12 Cornell University Angle sensitive pixel (asp)-based image processing system, method, and applications
CN103902977A (zh) * 2014-03-31 2014-07-02 华为技术有限公司 基于Gabor二值模式的人脸识别方法及装置
CN104408449A (zh) * 2014-10-27 2015-03-11 西安电子科技大学宁波信息技术研究院 智能移动终端场景文字处理方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101408932B (zh) * 2008-04-11 2012-06-20 浙江师范大学 一种基于指纹结构特征与纹理分析的指纹图像匹配方法
CN101572818B (zh) * 2009-06-01 2010-12-01 北京邮电大学 一种帧内预测模式的预测方法
CN103955950B (zh) * 2014-04-21 2017-02-08 中国科学院半导体研究所 一种利用关键点特征匹配的图像跟踪方法

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101122949A (zh) * 2007-08-30 2008-02-13 中国科学技术大学 一种基于局部频率特征和局部方向特征的虹膜识别方法
CN101404060A (zh) * 2008-11-10 2009-04-08 北京航空航天大学 一种基于可见光与近红外Gabor信息融合的人脸识别方法
CN101763507A (zh) * 2010-01-20 2010-06-30 北京智慧眼科技发展有限公司 人脸识别方法及人脸识别系统
CN101854551A (zh) * 2010-06-08 2010-10-06 浙江大学 帧内预测模式编解码方法及装置
WO2012018887A3 (en) * 2010-08-03 2012-04-12 Cornell University Angle sensitive pixel (asp)-based image processing system, method, and applications
CN102223541A (zh) * 2011-07-14 2011-10-19 北京工业大学 一种混合图像的编码方法
CN103902977A (zh) * 2014-03-31 2014-07-02 华为技术有限公司 基于Gabor二值模式的人脸识别方法及装置
CN104408449A (zh) * 2014-10-27 2015-03-11 西安电子科技大学宁波信息技术研究院 智能移动终端场景文字处理方法

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
"GABOR PHASE FEATURE-BASED HYPERSPECTRAL IMAGERY CLASSIFICATION";Sen Jia 等;《Proceedings of the IEEE International Conference on Multimedia and Expo (ICME) 2017》;20170714;第1467-1471页
"基于Gabor 小波与Memetic 算法的人脸识别方法";周家锐 等;《电子学报》;20120430(第4期);第642-646页
"手指多模态Gabor 编码特征局部融合方法研究";卢中宁 等;《信号处理》;20151130;第31卷(第11期);第1291-1296页

Also Published As

Publication number Publication date
CN108596250A (zh) 2018-09-28

Similar Documents

Publication Publication Date Title
CN108596250B (zh) 图像特征编码方法、终端设备及计算机可读存储介质
Yuan et al. Fingerprint liveness detection using an improved CNN with image scale equalization
Barra et al. Ubiquitous iris recognition by means of mobile devices
Benzaoui et al. Ear biometric recognition using local texture descriptors
Rana et al. A fast iris recognition system through optimum feature extraction
Islam et al. Multibiometric human recognition using 3D ear and face features
Faraji et al. Face recognition under varying illuminations using logarithmic fractal dimension-based complete eight local directional patterns
WO2015090126A1 (zh) 人脸特征的提取、认证方法及装置
WO2015089949A1 (zh) 一种融合LBP、Gabor特征的人脸聚类方法
Kang et al. A study on performance evaluation of fingerprint sensors
CN112132099A (zh) 身份识别方法、掌纹关键点检测模型训练方法和装置
Kekre et al. Gabor filter based feature vector for dynamic signature recognition
Ren et al. Hand gesture recognition with multiscale weighted histogram of contour direction normalization for wearable applications
Raja et al. Collaborative representation of blur invariant deep sparse features for periocular recognition from smartphones
Das et al. Iris Recognition using a Scalar based Template in Eigen-space
Galdi et al. PROTECT: Pervasive and useR fOcused biomeTrics bordEr projeCT–a case study
Albadarneh et al. Iris recognition system for secure authentication based on texture and shape features
Mehboob et al. Live fingerprint detection using magnitude of perceived spatial stimuli and local phase information
El-Naggar et al. Which dataset is this iris image from?
CN113918912A (zh) 一种基于脑纹识别的身份认证方法、系统、设备及介质
Bhattacharya et al. Qdf: A face database with varying quality
Tsitiridis et al. Bio-inspired presentation attack detection for face biometrics
Tapia et al. Gender classification from Iris texture images using a new set of binary statistical image features
Günlü et al. Face recognition with discriminating 3D DCT coefficients
CN110781802B (zh) 一种基于信息论流形的人脸图像识别方法

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20180928

Assignee: SHENZHEN TRAFFIC INVESTMENT TECHNOLOGY CO.,LTD.

Assignor: SHENZHEN University

Contract record no.: X2022980023067

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221123

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20180928

Assignee: Foshan Jinggong Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980024389

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221201

Application publication date: 20180928

Assignee: Shenzhen Huijin Ruishu Intelligent Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980023727

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221129

Application publication date: 20180928

Assignee: INTERGROWTH Corp.

Assignor: SHENZHEN University

Contract record no.: X2022980023866

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221130

Application publication date: 20180928

Assignee: Foshan Dexin Intelligent Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980024254

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221130

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20180928

Assignee: SHENZHEN FANNISHI CULTURE TECHNOLOGY Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980024588

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221205

Application publication date: 20180928

Assignee: Shenzhen Pego Intelligent Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980024334

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221202

Application publication date: 20180928

Assignee: Shenzhen Senying Intelligent Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980023882

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221201

Application publication date: 20180928

Assignee: Shenzhen Lipsun Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980024442

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221202

Application publication date: 20180928

Assignee: SHENZHEN HEXUN HUAGU INFORMATION TECHNOLOGY CO.,LTD.

Assignor: SHENZHEN University

Contract record no.: X2022980024443

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221205

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20180928

Assignee: Shenzhen Bangqi Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980024743

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221207

Application publication date: 20180928

Assignee: Shenzhen Maiwo Innovation Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980024758

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221207

Application publication date: 20180928

Assignee: SHENZHEN XINGHUA ZHITONG TECHNOLOGY Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980024808

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221207

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20180928

Assignee: Shenzhen Brand Anti counterfeiting Tracing Center

Assignor: SHENZHEN University

Contract record no.: X2022980025057

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221208

Application publication date: 20180928

Assignee: Shenzhen Zhizhi Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980025612

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221210

Application publication date: 20180928

Assignee: Shenzhen Standard Technical Service Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980025987

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221211

Application publication date: 20180928

Assignee: Shenzhen High Intelligence Data Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980025935

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221211

Application publication date: 20180928

Assignee: Yimaitong (Shenzhen) Intelligent Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026148

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221211

Application publication date: 20180928

Assignee: Shenzhen Huahong Testing Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980025985

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221211

Application publication date: 20180928

Assignee: DONGGUAN FANNISHI CULTURE TECHNOLOGY Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980025517

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221210

Application publication date: 20180928

Assignee: Chongqing Taihuo Xinniao Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026159

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221211

Application publication date: 20180928

Assignee: SHENZHEN GRIMMBRO TECHNOLOGY CO.,LTD.

Assignor: SHENZHEN University

Contract record no.: X2022980026270

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221212

Application publication date: 20180928

Assignee: SHENZHEN ZHUOYUESHI INDUSTRIAL Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026660

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221210

Application publication date: 20180928

Assignee: Ruiwei (Shenzhen) Information Development Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026103

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221211

Application publication date: 20180928

Assignee: Shenzhen Zijing Photoelectric Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026541

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221211

Application publication date: 20180928

Assignee: Shenzhen Huilongda Electronic Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026310

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221211

Application publication date: 20180928

Assignee: Shenzhen High Tech Electronics Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026209

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221211

Application publication date: 20180928

Assignee: Shenzhen Fanyuan chuangpin Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026203

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221211

Application publication date: 20180928

Assignee: Tongtong Network Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026678

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221210

Application publication date: 20180928

Assignee: SHENZHEN GEAZAN TECHNOLOGY Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026200

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221211

Application publication date: 20180928

Assignee: Chengdu Rundonghai He Information Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026155

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221211

Application publication date: 20180928

Assignee: Shenzhen Dongfang Renshou Life Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980025926

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221211

Application publication date: 20180928

Assignee: Shenzhen Jinchuang Yueda Electronic Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980025529

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221210

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20180928

Assignee: Shenzhen Juchuang Semiconductor Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026334

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221212

Application publication date: 20180928

Assignee: Zidong Precision Technology (Shenzhen) Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026379

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221212

Application publication date: 20180928

Assignee: SHENZHEN CASTELITS INTELLIGENT TECHNOLOGY Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026357

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221212

Application publication date: 20180928

Assignee: Shenzhen Yifan Time and Space Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026531

Denomination of invention: Image feature encoding method, terminal device and computer readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20221212

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20180928

Assignee: Shenzhen bear Video Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026722

Denomination of invention: Image feature encoding method, terminal device and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230106

Application publication date: 20180928

Assignee: Anwa Technology (Shenzhen) Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026659

Denomination of invention: Image feature encoding method, terminal device and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230106

Application publication date: 20180928

Assignee: Shenzhen Zhuoyuan Sensor Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026735

Denomination of invention: Image feature encoding method, terminal device and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230106

EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20180928

Assignee: Beijing Taiflamingo Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026674

Denomination of invention: Image feature encoding method, terminal device and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230111

Application publication date: 20180928

Assignee: Shenzhen yunhengtong Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026719

Denomination of invention: Image feature encoding method, terminal device and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230109

Application publication date: 20180928

Assignee: Shenzhen Hetang Huizhi Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026683

Denomination of invention: Image feature encoding method, terminal device and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230109

Application publication date: 20180928

Assignee: Shenzhen Haocai Digital Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026741

Denomination of invention: Image feature encoding method, terminal device and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230110

Application publication date: 20180928

Assignee: Shenzhen screen Networking Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026742

Denomination of invention: Image feature encoding method, terminal device and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230110

Application publication date: 20180928

Assignee: Guoxin Technology Group Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026708

Denomination of invention: Image feature encoding method, terminal device and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230111

Application publication date: 20180928

Assignee: Shenzhen Mutual Power Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026704

Denomination of invention: Image feature encoding method, terminal device and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230110

Application publication date: 20180928

Assignee: Guangdong Zhongke Huiju Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026703

Denomination of invention: Image feature encoding method, terminal device and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230110

Application publication date: 20180928

Assignee: SHENZHEN SIBROOD MICROELECTRONIC Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026690

Denomination of invention: Image feature encoding method, terminal device and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230110

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20180928

Assignee: Chongqing Taihuo Xinniao Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026805

Denomination of invention: Image feature encoding method, terminal device and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230116

EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20180928

Assignee: GUANGZHOU GUANGTAI INFORMATION TECHNOLOGY CO.,LTD.

Assignor: SHENZHEN University

Contract record no.: X2023980033660

Denomination of invention: Image feature encoding method, terminal device, and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230316

Application publication date: 20180928

Assignee: NEW TRANX INFORMATION TECHNOLOGY (SHENZHEN) CO.,LTD.

Assignor: SHENZHEN University

Contract record no.: X2023980033776

Denomination of invention: Image feature encoding method, terminal device, and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230317

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20180928

Assignee: SHENZHEN YIBU ZHIZAO TECHNOLOGY Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980034077

Denomination of invention: Image feature encoding method, terminal device, and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230324

Application publication date: 20180928

Assignee: Zhicheng Computer Aided Design (Shenzhen) Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980034108

Denomination of invention: Image feature encoding method, terminal device, and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230327

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20180928

Assignee: Lishui Taihuo Red Bird Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980034588

Denomination of invention: Image feature encoding method, terminal device, and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230411

Application publication date: 20180928

Assignee: Shenzhen Lingyu Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980034597

Denomination of invention: Image feature encoding method, terminal device, and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230411

Application publication date: 20180928

Assignee: Chengdu Rundong Industrial Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980034591

Denomination of invention: Image feature encoding method, terminal device, and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230411

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20180928

Assignee: SHENZHEN SUPERVISIONS TECHNOLOGY Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980035111

Denomination of invention: Image feature encoding method, terminal device, and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230426

Application publication date: 20180928

Assignee: Shenzhen Jiachen information engineering Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980035110

Denomination of invention: Image feature encoding method, terminal device, and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230426

Application publication date: 20180928

Assignee: SHENZHEN FANGDIRONGXIN TECHNOLOGY CO.,LTD.

Assignor: SHENZHEN University

Contract record no.: X2023980035109

Denomination of invention: Image feature encoding method, terminal device, and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230426

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20180928

Assignee: Shenzhen Pengcheng Future Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980036139

Denomination of invention: Image feature encoding method, terminal device, and computer-readable storage medium

Granted publication date: 20190514

License type: Common License

Record date: 20230531