CN114463831B - Training method and recognition method of iris recognition model for eyelashes - Google Patents

本申请公开一种针对睫毛的虹膜识别模型的训练方法，其包括：获取包括多张虹膜图像的虹膜训练集；对所述虹膜训练集中的每一张虹膜图像进行图像分割，获得虹膜区域H和睫毛区域M；分别计算每一虹膜图像的虹膜区域H的虹膜像素面积S_H和睫毛区域M的睫毛像素面积S_M，并计算该虹膜图像的睫毛像素面积S_M与虹膜像素面积S_H的面积比，该面积比记为P，P＝S_M/S_H；设定阈值P₀，比较所述虹膜训练集中每一虹膜图像的面积比P和阈值P₀的大小，将所述虹膜训练集中所有虹膜图像放入修正为：P＜P₀；以及将修正后的所述虹膜训练集输入CNN神经网络进行虹膜识别模型的学习训练。本申请还提供一种针对睫毛的虹膜识别方法。

The present application discloses a training method for an iris recognition model for eyelashes, which includes: obtaining an iris training set including multiple iris images; performing image segmentation on each iris image in the iris training set to obtain an iris region H and an eyelash region M; respectively calculating an iris pixel area SH of the iris region _H and an eyelash pixel area _SM of the eyelash region M of each iris image, and calculating an area ratio of the eyelash pixel area _SM of the iris image to the iris pixel area _SH , the area ratio being recorded as P, P= _SM / _SH ; setting a threshold _P0 , comparing the area ratio P of each iris image in the iris training set with the threshold _P0 , putting all iris images in the iris training set into a correction condition of: P<_P0; and inputting the corrected iris training set into a CNN neural network for learning and training an iris recognition model. The present application also provides an iris recognition method for eyelashes.

针对睫毛的虹膜识别模型的训练方法及识别方法Training method and recognition method of iris recognition model for eyelashes

技术领域Technical Field

本申请涉及图像处理领域，更具体地说，是针对睫毛的虹膜识别模型的训练方法及识别方法。The present application relates to the field of image processing, and more specifically, to a training method and a recognition method for an iris recognition model for eyelashes.

背景技术Background Art

现有虹膜识别技术主要分为两类，第一类是基于传统的模式识别方法，即通过手动设计特征提取图片的特征，并接上分类器，得到分类结果；第二类是基于深度学习CNN分类方法，提取的过程为数据推动。Existing iris recognition technologies are mainly divided into two categories. The first category is based on traditional pattern recognition methods, that is, manually designing features to extract image features and connecting them to a classifier to obtain classification results. The second category is based on deep learning CNN classification methods, and the extraction process is data-driven.

现有的虹膜识别技术，无论是早期的传统模式识别还是最近的深度学习，都是基于比较干净的无睫毛遮挡的虹膜数据进行识别效果较好。考虑到近年来人们，尤其是女性，因为爱美打扮等原因，对原有的睫毛进行修整，甚至接假睫毛等，这对虹膜识别构成了新的挑战。通过不带睫毛的虹膜数据训练出来的虹膜识别模型针对带睫毛的虹膜并没有较好的表现，导致在这类情况下虹膜识别模型的准确率下降较多。Existing iris recognition technologies, whether early traditional pattern recognition or recent deep learning, are based on relatively clean iris data without eyelashes for better recognition results. Considering that in recent years, people, especially women, have trimmed their original eyelashes or even attached false eyelashes for reasons such as beauty and dressing up, this poses a new challenge to iris recognition. The iris recognition model trained with iris data without eyelashes does not perform well for irises with eyelashes, resulting in a significant decrease in the accuracy of the iris recognition model in such cases.

发明内容Summary of the invention

针对现有技术，本申请解决的技术问题是提供一种针对睫毛的虹膜识别模型的训练方法及识别方法，该训练方法及识别方法有利于训练出针对带睫毛的虹膜识别模型，有利于解决当存在睫毛情况下的虹膜识别问题。In view of the prior art, the technical problem solved by the present application is to provide a training method and a recognition method for an iris recognition model for eyelashes. The training method and the recognition method are conducive to training an iris recognition model for eyes with eyelashes, and are conducive to solving the iris recognition problem when eyelashes are present.

为解决上述技术问题，第一方面，本申请提供一种针对睫毛的虹膜识别模型的训练方法，包括：In order to solve the above technical problems, in a first aspect, the present application provides a training method for an iris recognition model for eyelashes, comprising:

获取包括多张虹膜图像的虹膜训练集；Obtain an iris training set including a plurality of iris images;

对所述虹膜训练集中的每一张虹膜图像进行图像分割，获得虹膜区域H和睫毛区域M；Performing image segmentation on each iris image in the iris training set to obtain an iris region H and an eyelash region M;

分别计算每一虹膜图像的虹膜区域H的虹膜像素面积S_H和睫毛区域M的睫毛像素面积S_M，并计算该虹膜图像的睫毛像素面积S_M与虹膜像素面积S_H的面积比，该面积比记为P，P＝S_M/S_H；Calculate the iris pixel area _SH of the iris region H and the eyelash pixel area _SM of the eyelash region M of each iris image respectively, and calculate the area ratio of the eyelash pixel area _SM to the iris pixel area _SH of the iris image, the area ratio is recorded as P, P = _SM / _SH ;

设定阈值P₀，比较所述虹膜训练集中每一虹膜图像的面积比P和阈值P₀的大小，将所述虹膜训练集中所有P≥P₀对应的虹膜图像修正为P＜P₀；以及，Setting a threshold value P ₀ , comparing the area ratio P of each iris image in the iris training set with the threshold value P ₀ , and correcting all iris images corresponding to P ≥ P ₀ in the iris training set to P < P ₀ ; and,

将修正后的所述虹膜训练集输入CNN神经网络进行虹膜识别模型的学习训练。The modified iris training set is input into the CNN neural network for learning and training of the iris recognition model.

在一种可能的实现方式中，定阈值P₀，比较所述虹膜训练集中每一虹膜图像的面积比P和阈值P₀的大小，将所述虹膜训练集中所有P≥P₀对应的虹膜图像修正为P＜P₀的步骤包括：In a possible implementation, the steps of determining a threshold value P ₀ , comparing the area ratio P of each iris image in the iris training set with the threshold value P ₀ , and correcting all iris images corresponding to P ≥ P ₀ in the iris training set to P < P ₀ include:

选定所述虹膜训练集中一面积比P≥P₀的虹膜图像C和一面积比P＜P₀的虹膜图像D；Selecting an iris image C with an area ratio P≥P ₀ and an iris image D with an area ratio P＜P ₀ in the iris training set;

将虹膜图像C的图像分割获得虹膜区域和睫毛区域分别记为H_C和M_C，将虹膜图像D的图像分割获得虹膜区域和睫毛区域分别记为H_D和M_D；The iris image C is segmented to obtain an iris region and an eyelash region, which are respectively recorded as _HC and M _C ; the iris image D is segmented to obtain an iris region and an eyelash region, which are respectively recorded as _HD and _MD ;

将虹膜图像C的睫毛区域的睫毛移植至虹膜图像D的睫毛区域上，生成由虹膜图像D的虹膜和虹膜图像C的睫毛组成新的虹膜图像F；Transplant the eyelashes in the eyelash area of iris image C to the eyelash area of iris image D, and generate a new iris image F composed of the iris in iris image D and the eyelashes in iris image C;

由新的虹膜图像F替代所述虹膜训练集中的虹膜图像C。The iris image C in the iris training set is replaced by the new iris image F.

在一种可能的实现方式中，在将修正后的所述虹膜训练集输入CNN神经网络进行学习训练的过程中，基于向量维度为K的one-hot函数进行类别标签编码：In a possible implementation, when the modified iris training set is input into the CNN neural network for learning and training, the category label is encoded based on a one-hot function with a vector dimension of K:

利用one-hot函数设定修正后所述虹膜训练集中任一虹膜图像t的类别标签编码为 The category label encoding of any iris image t in the iris training set after correction is set using the one-hot function:

其中，P_t为所述虹膜图像t的虹膜像素面积与睫毛像素面积的面积比,为P_t的负指数函数值。Wherein, _Pt is the area ratio of the iris pixel area to the eyelash pixel area of the iris image t, is the negative exponential function value of _Pt .

在一种可能的实现方式中，在将修正后的所述虹膜训练集输入CNN神经网络进行识别虹膜模型的学习训练过程中，设定softmax作为训练激活函数，且设定所述虹膜图像t在CNN神经网络中的类别置信度为 In a possible implementation, when the modified iris training set is input into the CNN neural network for learning and training the iris model, softmax is set as the training activation function, and the category confidence of the iris image t in the CNN neural network is set to

在一种可能的实现方式中，In one possible implementation,

其中，i表示为属于所述虹膜区域的像素点，j表示为属于所述睫毛区域的像素点。Among them, i represents the pixel point belonging to the iris area, and j represents the pixel point belonging to the eyelash area.

在一种可能的实现方式中，所述P₀设定为10％。In a possible implementation, the P ₀ is set to 10%.

在一种可能的实现方式中，利用PSPNet分割模型对所述虹膜训练集中的每一张虹膜图像进行图像分割。In a possible implementation, the PSPNet segmentation model is used to perform image segmentation on each iris image in the iris training set.

在一种可能的实现方式中，CNN神经网络为基于mobilenet模型结构的网络。In a possible implementation, the CNN neural network is a network based on a mobilenet model structure.

在所述针对睫毛的虹膜识别模型的训练方法中，通过设定阈值P₀，将用于CNN神经网络进行虹膜识别模型训练的虹膜训练集中的每一虹膜图像调整为的睫毛区域和虹膜区域的面积比小于P₀，如此以保证虹膜训练集中虹膜图像的有效性，从而训练出针对解决存在睫毛情况下的虹膜识别模型，有利于解决带睫毛的虹膜图像的识别问题。In the training method for the iris recognition model for eyelashes, by setting a threshold value P ₀ , each iris image in the iris training set used for the CNN neural network to train the iris recognition model is adjusted so that the area ratio of the eyelash region to the iris region is less than P ₀ , so as to ensure the validity of the iris images in the iris training set, thereby training an iris recognition model for solving the problem of eyelashes, which is beneficial to solving the problem of recognizing iris images with eyelashes.

第二方面，本申请提供一种针对睫毛的虹膜识别方法，包括：In a second aspect, the present application provides an iris recognition method for eyelashes, comprising:

获取待识别人员J的虹膜图像，对该识别人员J的虹膜图像进行图像分割，获得虹膜区域H_j和睫毛区域M_j；Acquire an iris image of a person to be identified J, perform image segmentation on the iris image of the identified person J, and obtain an iris region H _j and an eyelash region M _j ;

设定阈值P₁，计算睫毛区域M_j和虹膜区域H_j的面积比P_j，若P_j≥P₁，则重新获取该待识别人员J的虹膜图像直至该待识别人员J的虹膜图像面积比P_j＜P₁；Set a threshold value P ₁ , calculate the area ratio P _j of the eyelash area M _j and the iris area H _j , if P _j ≥ P ₁ , then reacquire the iris image of the person to be identified J until the iris image area ratio P _j < P ₁ ;

利用所述针对睫毛的虹膜识别模型的训练方法训练的虹膜识别模型进行虹膜识别。Iris recognition is performed using an iris recognition model trained using the training method for an iris recognition model for eyelashes.

在一种可能的实现方式中，所述P₁设定为10％。In a possible implementation, the _P1 is set to 10%.

在所述针对睫毛的虹膜识别方法中，通过设定阈值P₀，将用于CNN神经网络进行虹膜识别模型训练的虹膜训练集中的每一虹膜图像调整为的睫毛区域和虹膜区域的面积比小于P₀，如此以保证虹膜训练集中虹膜图像的有效性，从而训练出针对解决存在睫毛情况下的虹膜识别模型，从而有利于解决带睫毛的虹膜图像的识别问题；并且通过设定阈值P₁，可有效防止采集的待识别人员J的虹膜图像的睫毛过长，从而影响虹膜识别过程。故，该针对睫毛的虹膜识别方法能有效解决现实中带睫毛的虹膜图像的识别问题。In the iris recognition method for eyelashes, by setting a threshold value P ₀ , each iris image in the iris training set used for CNN neural network iris recognition model training is adjusted to have an area ratio of eyelash area to iris area less than P ₀ , so as to ensure the effectiveness of the iris images in the iris training set, thereby training an iris recognition model for solving the problem of eyelashes, which is conducive to solving the problem of identifying iris images with eyelashes; and by setting a threshold value P ₁ , it is possible to effectively prevent the eyelashes of the iris image of the person to be identified J from being too long, thereby affecting the iris recognition process. Therefore, the iris recognition method for eyelashes can effectively solve the problem of identifying iris images with eyelashes in reality.

附图说明BRIEF DESCRIPTION OF THE DRAWINGS

为了更清楚地说明本申请实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

图1为本申请实施例的针对睫毛的虹膜识别模型的训练方法的流程图；FIG1 is a flow chart of a method for training an iris recognition model for eyelashes according to an embodiment of the present application;

图2为本申请实施例的将所述虹膜训练集中所有P≥P₀对应的虹膜图像修正为P＜P₀的步骤流程图；FIG2 is a flowchart of the steps of correcting all iris images corresponding to P≥P ₀ in the iris training set to P＜P ₀ in an embodiment of the present application;

图3为本申请实施例的一面积比P≥P₀的虹膜图像图C进行图像分割获得睫毛区域的示意图；FIG3 is a schematic diagram of obtaining eyelash regions by performing image segmentation on an iris image C with an area ratio P ≥ P ₀ according to an embodiment of the present application;

图4为本申请实施例的选取的一面积比P＜P₀的虹膜图像D；FIG. 4 is an iris image D with an area ratio P<P ₀ selected according to an embodiment of the present application;

图5为本申请实施例的为将图3中的睫毛移植至图4中的睫毛区域的生成虹膜图像F的结果示意图；FIG. 5 is a schematic diagram showing a result of generating an iris image F by transplanting the eyelashes in FIG. 3 to the eyelash region in FIG. 4 according to an embodiment of the present application;

图6为本申请实施例的针对睫毛的虹膜识别方法的流程图。FIG. 6 is a flow chart of an iris recognition method for eyelashes according to an embodiment of the present application.

具体实施方式DETAILED DESCRIPTION

为了使本申请所要解决的技术问题、技术方案及有益效果更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。In order to make the technical problems, technical solutions and beneficial effects to be solved by the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

需要说明的是，当元件被称为“固定于”或“设置于”另一个元件，它可以直接在另一个元件上或者间接在该另一个元件上。当一个元件被称为是“连接于”另一个元件，它可以是直接连接到另一个元件或间接连接至该另一个元件上。It should be noted that when an element is referred to as being "fixed to" or "disposed on" another element, it can be directly on the other element or indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or indirectly connected to the other element.

需要理解的是，术语“长度”、“宽度”、“上”、“下”、“前”、“后”、“左”、“右”、“竖直”、“水平”、“顶”、“底”、“内”、“外”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本申请和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本申请的限制。It should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个该特征。在本申请的描述中，“多个”的含义是两个或两个以上，除非另有明确具体的限定。In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

现结合附图对本申请的针对睫毛的虹膜识别模型的训练方法和针对睫毛的虹膜识别方法系统进行具体说明。The training method of the iris recognition model for eyelashes and the iris recognition method system for eyelashes of the present application are now described in detail with reference to the accompanying drawings.

参照图1，本申请实施例提供的针对睫毛的虹膜识别模型的训练方法包括如下步骤：1 , the training method for the iris recognition model for eyelashes provided in the embodiment of the present application includes the following steps:

步骤S10：获取包括多张虹膜图像的虹膜训练集；Step S10: obtaining an iris training set including a plurality of iris images;

步骤S11：对所述虹膜训练集中的每一张虹膜图像进行图像分割，获得虹膜区域H和睫毛区域M；Step S11: performing image segmentation on each iris image in the iris training set to obtain an iris region H and an eyelash region M;

步骤S12：分别计算每一虹膜图像的虹膜区域H的虹膜像素面积S_H和睫毛区域M的睫毛像素面积S_M，并计算该虹膜图像的睫毛像素面积S_M与虹膜像素面积S_H的面积比，该面积比记为P，P＝S_M/S_H；Step S12: Calculate the iris pixel area _SH of the iris region H and the eyelash pixel area _SM of the eyelash region M of each iris image, and calculate the area ratio of the eyelash pixel area _SM to the iris pixel area _SH of the iris image, the area ratio is recorded as P, P = _SM / _SH ;

步骤S12：设定阈值P₀，比较所述虹膜训练集中每一虹膜图像的面积比P和阈值P₀的大小，将所述虹膜训练集中所有P≥P₀对应的虹膜图像修正为P＜P₀；Step S12: setting a threshold value P ₀ , comparing the area ratio P of each iris image in the iris training set with the threshold value P ₀ , and correcting all iris images corresponding to P ≥ P ₀ in the iris training set to P < P ₀ ;

步骤S14：将修正后的所述虹膜训练集输入CNN神经网络进行虹膜识别模型的学习训练。Step S14: input the modified iris training set into the CNN neural network to perform learning and training of the iris recognition model.

在所述针对睫毛的虹膜识别模型的训练方法中，通过设定阈值P₀，将用于CNN神经网络进行虹膜识别模型训练的虹膜训练集中的每一虹膜图像调整为的睫毛区域和虹膜区域的面积比小于P₀，如此以保证虹膜训练集中虹膜图像的有效性，从而训练出针对解决存在睫毛情况下的虹膜识别模型，有利于解决带睫毛的虹膜图像的识别问题。In the training method for the iris recognition model for eyelashes, by setting a threshold value P ₀ , each iris image in the iris training set used for the CNN neural network to train the iris recognition model is adjusted so that the area ratio of the eyelash region to the iris region is less than P ₀ , so as to ensure the validity of the iris images in the iris training set, thereby training an iris recognition model for solving the problem of eyelashes, which is beneficial to solving the problem of recognizing iris images with eyelashes.

可以理解地，在训练虹膜识别模型时，若训练集中的虹膜图像都是在睫毛遮挡虹膜大部分区域或完全遮挡虹膜区域的情况下进行的，在一定程度上会影响虹膜识别过程中虹膜特征的提取，从而影响训练出有效的虹膜识别模型。It is understandable that when training an iris recognition model, if the iris images in the training set are taken when the eyelashes cover most of the iris area or completely cover the iris area, it will affect the extraction of iris features during the iris recognition process to a certain extent, thereby affecting the training of an effective iris recognition model.

在步骤S10中，所述虹膜训练集中所有的虹膜图像的尺寸比例一样且均为带睫毛的虹膜，且每一虹膜图像中虹膜和睫毛基本占据整张图像，虹膜训练集中存在带睫毛的虹膜图像和不带睫毛的虹膜图像，带睫毛的虹膜图像包括面积比大于等于P₀的虹膜图像和面积比小于P₀的虹膜图像，数据的多样性可增加训练出的虹膜识别模型的适应性。In step S10, all iris images in the iris training set have the same size ratio and are all irises with eyelashes, and in each iris image, the iris and eyelashes basically occupy the entire image. The iris training set includes iris images with eyelashes and iris images without eyelashes. The iris images with eyelashes include iris images with an area ratio greater than or equal to P ₀ and iris images with an area ratio less than P _0. The diversity of data can increase the adaptability of the trained iris recognition model.

在步骤S11中，利用PSPNet分割模型对所述虹膜训练集中的每一张虹膜图像进行图像分割，利用PSPNet方法对虹膜训练集中的每一张虹膜图像进行语义分割获得虹膜区域H和睫毛区域M。In step S11, the PSPNet segmentation model is used to perform image segmentation on each iris image in the iris training set, and the PSPNet method is used to perform semantic segmentation on each iris image in the iris training set to obtain an iris region H and an eyelash region M.

在步骤S12中，计算每一虹膜图像的虹膜区域H的虹膜像素面积S_H和睫毛区域M的睫毛像素面积S_M的公式如下：In step S12, the formula for calculating the iris pixel area _SH of the iris region H and the eyelash pixel area _SM of the eyelash region M of each iris image is as follows:

其中，i表示为属于所述虹膜区域的像素点，j表示为属于所述睫毛区域的像素点。Among them, i represents the pixel point belonging to the iris area, and j represents the pixel point belonging to the eyelash area.

参照图2，在步骤S13中，定阈值P₀，比较所述虹膜训练集中每一虹膜图像的面积比P和阈值P₀的大小，将所述虹膜训练集中所有P≥P₀对应的虹膜图像修正为P＜P₀的步骤包括：2 , in step S13, a threshold value P ₀ is determined, and the area ratio P of each iris image in the iris training set is compared with the threshold value P ₀ , and the step of correcting all iris images corresponding to P ≥ P ₀ in the iris training set to P < P ₀ includes:

步骤S131：选定所述虹膜训练集中一面积比P≥P₀的虹膜图像C和一面积比P＜P₀的虹膜图像D；Step S131: selecting an iris image C with an area ratio P≥P ₀ and an iris image D with an area ratio P＜P ₀ in the iris training set;

步骤S132：将虹膜图像C的图像分割获得虹膜区域和睫毛区域分别记为H_C和M_C，将虹膜图像D的图像分割获得虹膜区域和睫毛区域分别记为H_D和M_D；Step S132: segmenting the iris image C to obtain an iris region and an eyelash region, respectively denoted as _HC and M _C ; segmenting the iris image D to obtain an iris region and an eyelash region, respectively denoted as _HD and _MD ;

步骤S133：将虹膜图像C的睫毛区域的睫毛移植至虹膜图像D的睫毛区域上，生成由虹膜图像D的虹膜和虹膜图像C的睫毛组成新的虹膜图像F；Step S133: transplanting the eyelashes in the eyelash area of iris image C to the eyelash area of iris image D, generating a new iris image F composed of the iris of iris image D and the eyelashes of iris image C;

步骤S134：由新的虹膜图像F替代所述虹膜训练集中的虹膜图像C。Step S134: replacing the iris image C in the iris training set with the new iris image F.

图3为一面积比P≥P₀的虹膜图像图C进行图像分割获得睫毛区域的示意图，图4为面积比P＜P₀的虹膜图像D，图5为将图3中的睫毛移植至图4中的睫毛区域的生成虹膜图像F的结果示意图。FIG3 is a schematic diagram of obtaining the eyelash region by segmenting an iris image C with an area ratio _P≥P0 , FIG4 is an iris image D with an area ratio P＜ _P0 , and FIG5 is a schematic diagram of the result of transplanting the eyelashes in FIG3 to the eyelash region in FIG4 to generate an iris image F.

在一申请实施例中，所述P₀设定为10％，在其他实施例中，P₀可设定为其他值，可以依据实际情况调整。In one embodiment of the application, _P0 is set to 10%. In other embodiments, _P0 can be set to other values and can be adjusted according to actual conditions.

在步骤S14中，在将修正后的所述虹膜训练集输入CNN神经网络进行学习训练的过程中，基于向量维度为K的one-hot函数进行类别标签编码：In step S14, when the modified iris training set is input into the CNN neural network for learning and training, the category label is encoded based on a one-hot function with a vector dimension of K:

利用one-hot函数设定修正后所述虹膜训练集中任一虹膜图像t的类别标签编码为 The category label encoding of any iris image t in the iris training set after correction is set using the one-hot function:

其中，P_t为所述虹膜图像t的虹膜像素面积与睫毛像素面积的面积比,为P_t的负指数函数值。Wherein, _Pt is the area ratio of the iris pixel area to the eyelash pixel area of the iris image t, is the negative exponential function value of _Pt .

进一步地，在步骤S500中，进行识别虹膜模型的学习训练过程中，设定softmax作为训练激活函数，且设定所述虹膜图像t在CNN神经网络中的类别置信度为在一申请实施例中，CNN神经网络为基于mobilenet模型结构的网络。Furthermore, in step S500, during the learning and training process of the iris recognition model, softmax is set as the training activation function, and the category confidence of the iris image t in the CNN neural network is set to In one embodiment of the application, the CNN neural network is a network based on the mobilenet model structure.

可以理解地，因为睫毛越长对虹膜识别的准确率影响越大，意味着训练过程中对训练集的每一图像的判定结果越不可信和识别结果也越不可信，如此，在CNN神经网络训练过程中，对虹膜训练集中的任一虹膜图像t设定一个关于该虹膜图像t的面积比P的类别置信度，以该类别置信度不断影响训练过程，如此训练出更有信服度的虹膜识别模型，即训练出精确度更高的虹膜识别模型。故，利用上述设置的类别执置信度可以加入睫毛对训练过程的影响，从而更加符合实际情况，以保证训练出更加准确的虹膜识别模型。Understandably, because the longer the eyelashes are, the greater the impact on the accuracy of iris recognition, which means that the judgment result of each image in the training set is less reliable and the recognition result is less reliable during the training process. Thus, during the CNN neural network training process, a category confidence of the area ratio P of any iris image t in the iris training set is set, and the category confidence is used to continuously influence the training process, so as to train a more convincing iris recognition model, that is, to train a more accurate iris recognition model. Therefore, the above-set category confidence can be used to add the impact of eyelashes on the training process, so as to be more in line with the actual situation, so as to ensure that a more accurate iris recognition model is trained.

参照图6，本申请实施例中提供的针对睫毛的虹膜识别方法包括如下步骤：6 , the iris recognition method for eyelashes provided in the embodiment of the present application includes the following steps:

步骤S20：获取待识别人员J的虹膜图像，对该识别人员J的虹膜图像进行图像分割，获得虹膜区域H_j和睫毛区域M_j；Step S20: obtaining an iris image of the person to be identified J, performing image segmentation on the iris image of the person to be identified J, and obtaining an iris region H _j and an eyelash region M _j ;

步骤S21：设定阈值P₁，计算睫毛区域M_j和虹膜区域H_j的面积比P_j，若P_j≥P₁，则重新获取该待识别人员J的虹膜图像直至该待识别人员J的虹膜图像面积比P_j＜P₁；Step S21: setting a threshold value P ₁ , calculating the area ratio P _j of the eyelash area M _j and the iris area H _j , if P _j ≥ P ₁ , reacquiring the iris image of the person to be identified J until the iris image area ratio P _j < P ₁ ;

步骤S22：利用所述针对睫毛的虹膜识别模型的训练方法训练的虹膜识别模型进行虹膜识别。Step S22: performing iris recognition using the iris recognition model trained by the training method for the iris recognition model for eyelashes.

在一申请实施例中，所述P₁设定为10％。In one embodiment of the application, the P ₁ is set to 10%.

在本实施例中，通过设定阈值P₀，将用于CNN神经网络进行虹膜识别模型训练的虹膜训练集中的每一虹膜图像调整为的睫毛区域和虹膜区域的面积比小于P₀，如此以保证虹膜训练集中虹膜图像的有效性，从而训练出针对解决存在睫毛情况下的虹膜识别模型，从而有利于解决带睫毛的虹膜图像的识别问题；并且通过设定阈值P₁，可有效防止采集的待识别人员J的虹膜图像的睫毛过长，从而影响虹膜识别过程。故，该针对睫毛的虹膜识别方法能有效解决现实中带睫毛的虹膜图像的识别问题。In this embodiment, by setting a threshold value P ₀ , each iris image in the iris training set used for CNN neural network iris recognition model training is adjusted to have an area ratio of eyelash area to iris area less than P ₀ , so as to ensure the effectiveness of the iris images in the iris training set, thereby training an iris recognition model for solving the problem of eyelashes, which is conducive to solving the problem of identifying iris images with eyelashes; and by setting a threshold value P ₁ , it is possible to effectively prevent the eyelashes of the collected iris image of the person to be identified J from being too long, thereby affecting the iris recognition process. Therefore, the iris recognition method for eyelashes can effectively solve the problem of identifying iris images with eyelashes in reality.

以上所述仅为本申请的较佳实施例而已，并不用以限制本申请，凡在本申请的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本申请的保护范围之内。The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application.