CN104268521A - Image recognition method based on convolutional neural network in non-finite category - Google Patents
Image recognition method based on convolutional neural network in non-finite category Download PDFInfo
- Publication number
- CN104268521A CN104268521A CN201410488286.2A CN201410488286A CN104268521A CN 104268521 A CN104268521 A CN 104268521A CN 201410488286 A CN201410488286 A CN 201410488286A CN 104268521 A CN104268521 A CN 104268521A
- Authority
- CN
- China
- Prior art keywords
- layer
- convolutional neural
- neural networks
- output
- convolutional
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an image recognition method based on a convolutional neural network in a non-finite category. The method includes the steps of model training, data registration and match recognition, wherein in the model training process, a training sample is input in a convolutional neural network model, the error of a binary code of an output layer and a category binary code of the sample is calculated, and parameters of the model are adjusted; in the data registration process, sample images needing to be registered are input in the convolutional neural network model, and an output result of a hidden layer before the output layer serves as a feature vector and is stored; in the match recognition process, matches to be recognized are input in the convolutional neural network, an output result of the hidden layer before the output layer serves as a feature vector, the feature vector is matched with the registered feature vector, and therefore a match recognition judgment result is acquired.
Description
Technical field
The present invention relates to image identification technical field, especially based on the image identification technical field of convolutional neural networks.
Background technology
At present, the output layer of known convolutional neural networks is classification coding.This just requires, after model training terminates, the image to be identified used a model needs and the sample of training pattern has identical classification, and the classification number that model can identify also is fixing.
Such convolutional neural networks is applicable in other field of image recognition of fixed class, and, in other field of image recognition of many fixed class, achieve good effect, as hand-written Letter identification, Handwritten Digit Recognition etc.
But, also have many field of image recognition, the particularly field of image recognition of biological characteristic, as recognition of face, fingerprint recognition, hand vein recognition etc., after model training, the image pattern that identifies and the sample of model training is needed to belong to a different category, and, need the classification number that identifies to change along with the data variation registered in use procedure.This just makes known convolutional neural networks can not be used for these field of image recognition.
Summary of the invention
The field of image recognition of non-limiting classification can not be used for overcome existing convolutional neural networks model, the present invention proposes a kind of image-recognizing method of the convolutional neural networks based on non-limiting classification.After the method does not limit training pattern, the sample of discriminator and training sample have identical classification, and the classification number also not limiting classification immobilizes.Meanwhile, the method has higher discrimination.
The image-recognizing method of a kind of convolutional neural networks based on non-limiting classification proposed by the invention comprises S100 training pattern, S200 log-on data and S300 and identifies coupling three parts.Fig. 1 gives overview flow chart of the present invention.
The convolutional neural networks of non-limiting classification of the present invention, its structure is: comprise an input layer I, after input layer, is alternately distributed convolutional layer C
1, down-sampled layer S
1..., convolutional layer C
k, down-sampled layer S
k, convolutional layer C
k+1, an in the end convolutional layer C
k+1be several hidden layers H afterwards
1, H
2... H
n, an in the end hidden layer H
nafterwards, be output layer O.Fig. 2 gives the structural representation of convolutional neural networks.
Each node of described input layer corresponds to a pixel of input picture.Described input picture, can be the original image gathered, also can be through the image after filtering or normalization.
Every one deck of described convolutional layer comprises multiple characteristic pattern, the characteristic pattern of same layer measure-alike, and the pixel of each characteristic pattern, corresponding to the pixel set of some characteristic pattern respective window positions of specifying of front one deck.
Every one deck of described down-sampled layer comprises the characteristic pattern of multiple same size; The characteristic pattern of often opening of down-sampled layer corresponds to a characteristic pattern of front one deck convolutional layer; The pixel of the characteristic pattern of down-sampled layer corresponds to the sample area of front one deck individual features figure; All sample area do not have lap.
Each node of each node of described hidden layer and each node of front one deck and later layer is connected each other by the limit of Weight.
Each node of described output layer only exports 0 or 1, therefore the output of output layer is a binary-coded output vector.
Described training pattern S100 training pattern comprises the step of S110-S130.
S110 initialization convolutional neural networks, this process comprises the step of S111-S116.
S111 arranges training time end condition parameter.
S112 arranges number and the convolution window size of the characteristic pattern of each convolutional layer.
S113 arranges the number of the characteristic pattern of each down-sampled layer and down-sampled ratio.
S114 arranges the corresponding relation of each convolutional layer and front one deck characteristic pattern.
S115 arranges the node number of output layer, makes this node number identical with the binary-coded figure place of the classification of training sample.
The weight parameter on the limit in S116 initialization convolutional neural networks is random number.
S120 performs training process, repeats the step of S121-S128, till meeting training end condition.
Training image is inputted the input layer of convolutional neural networks by S121.
If S122 current layer is convolutional layer, then according to convolutional calculation formula, convolutional calculation is carried out to the view data in selected by front one deck, thus obtains the result of the characteristic pattern of convolutional layer.Its computation process is: chosen by front one deck view data and corresponding convolution kernel to calculate the convolution of respective regions according to formula (1); Then the convolution results calculated is drawn the result of calculation of Sigm function according to formula (2); Finally, according to formula (3), to respectively choosing the convolution results of image to sue for peace, obtain the corresponding convolution results of convolutional layer.Fig. 3 gives the schematic diagram of convolution process.
(1)。
(2)。
S = Σ S
i (3)。
If S123 current layer is down-sampled layer, then carry out down-sampled calculating according to the corresponding characteristic pattern of front one deck, thus obtain the characteristic pattern result of down-sampled layer.Formula (4) gives down-sampled computing formula.Wherein, C is the area data of last layer characteristic pattern, N
1with N
2be respectively the down-sampled multiple of last layer characteristic pattern in two dimensions of image.Fig. 4 gives the schematic diagram of down-sampled process.
(4)。
S124 repeated execution of steps S122 and step S123, till the result of calculation of last convolutional layer completes.
S125, according to the weight on the output data of the last node layer of hidden layer, the limit between hidden layer and last node layer, calculates the output data of hidden layer node.Repeat, till the output of last hidden layer has been calculated.Formula (5) gives the computing method of hidden layer node.Fig. 5 gives the schematic diagram of hidden layer structure.
y = Sigm (Σw
ix
i + b) (5)。
S126 is according to the Output rusults of last hidden layer, and the weight on limit between hidden layer and output layer, calculates the output vector of output layer.The computing formula of output layer is identical with formula (5).
Error between the binary coding of the classification belonging to the sample of S127 output layer output vector and input.Formula (6) gives the computing formula of error.
(6)。
The error that step S127 calculates is inputted convolutional neural networks by output layer by S128, successively adjusts the weight parameter in convolutional neural networks between each layer.
Described S200 log-on data comprises the step of S210-S220.
The convolutional neural networks that S210 will need the image input of registration to be trained by S100, through performing step S122-S125.
The Output rusults of last hidden layer that step S210 obtains by S220 is stored as the proper vector of this registered images.
Described S300 identifies that coupling comprises the step of S310-S330.
The convolutional neural networks that the input of the image of coupling to be identified is trained by S100 by S310, through performing step S122-S125.
The Output rusults of last hidden layer that step S310 obtains by S320 is as the proper vector of this band identification matching image, and the proper vector of the log-on data stored with S200 calculates distance.
S330, according to the result of calculation of step S320, provides the court verdict identifying coupling.
The invention has the beneficial effects as follows, by in the process of log-on data, identification coupling, use the output vector of last hidden layer of the convolutional neural networks trained as proper vector, adopt the characteristic of division to training sample in training process on the one hand, break away from again the restriction that convolutional neural networks only can be classified to training sample generic on the other hand, thus achieve the object that the image of non-limiting classification is classified; Meanwhile, the present invention has higher discrimination.
Accompanying drawing explanation
Fig. 1 gives a kind of overview flow chart of image-recognizing method of the convolutional neural networks based on non-limiting classification.
Fig. 2 gives the structural representation of convolutional neural networks.
Fig. 3 gives the schematic diagram of convolution process.
Fig. 4 gives the schematic diagram of down-sampled process.
Fig. 5 gives the schematic diagram of hidden layer structure.
Claims (10)
1. based on an image-recognizing method for the convolutional neural networks of non-limiting classification, it is characterized in that: comprise training volume model, log-on data, identification coupling three parts.
2. convolutional neural networks according to claim 1, it is characterized in that: comprise an input layer, after input layer, be alternately distributed convolutional layer, down-sampled layer ..., down-sampled layer, convolutional layer, be in the end several hidden layers after a convolutional layer, in the end after a hidden layer, it is output layer.
3. input layer according to claim 2, is characterized in that: input layer corresponds to input picture, and each node corresponds to a pixel of input picture; Input picture can be original image, also can be through the image after filtering or normalization.
4. convolutional layer according to claim 2, it is characterized in that: each convolutional layer comprises the measure-alike of the characteristic pattern of multiple characteristic pattern same layer, and the pixel of each characteristic pattern, corresponding to the pixel set of some characteristic pattern respective window positions that front one deck is specified.
5. down-sampled layer according to claim 2, is characterized in that: each down-sampled layer comprised the characteristic pattern of a same size; The characteristic pattern of often opening of down-sampled layer corresponds to a characteristic pattern of front one deck convolutional layer; The pixel of the characteristic pattern of down-sampled layer corresponds to the sample area of front one deck individual features figure; All sample area do not have lap.
6. hidden layer according to claim 2, is characterized in that: each node of each node of this layer and each node of front one deck and later layer is connected each other by the limit of Weight.
7. output layer according to claim 2, is characterized in that: each node of this layer only exports 0 or 1, thus output layer defines one group of binary coding.
8. training pattern according to claim 1, is characterized in that: the classification of training sample carries out binary coding with 0,1, and the length of coding is consistent with the nodes of output layer; The parameter of initialization convolutional neural networks is random number; Training sample is inputted convolutional neural networks, the error of calculation of the scale-of-two classification of the output encoder of output layer and training sample being encoded; Error is entered convolutional neural networks from output layer back transfer, the parameter of adjustment convolutional neural networks; Then, again training sample is inputted convolutional neural networks, repeat said process, till error is less than appointment threshold value or frequency of training reaches requirement.
9. log-on data according to claim 1, is characterized in that: the view data of registration is sent into convolutional neural networks, using the proper vector of the output vector of last hidden layer as this sample, is stored in database.
10. identification coupling according to claim 1, it is characterized in that: view data to be identified is sent into convolutional neural networks, using the proper vector of the output vector of last hidden layer as this sample, registered proper vector in this proper vector and database according to claim 9 is calculated distance, thus makes the court verdict identifying coupling.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410488286.2A CN104268521A (en) | 2014-09-23 | 2014-09-23 | Image recognition method based on convolutional neural network in non-finite category |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410488286.2A CN104268521A (en) | 2014-09-23 | 2014-09-23 | Image recognition method based on convolutional neural network in non-finite category |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104268521A true CN104268521A (en) | 2015-01-07 |
Family
ID=52160041
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410488286.2A Pending CN104268521A (en) | 2014-09-23 | 2014-09-23 | Image recognition method based on convolutional neural network in non-finite category |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104268521A (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104268524A (en) * | 2014-09-24 | 2015-01-07 | 朱毅 | Convolutional neural network image recognition method based on dynamic adjustment of training targets |
CN104573679A (en) * | 2015-02-08 | 2015-04-29 | 天津艾思科尔科技有限公司 | Deep learning-based face recognition system in monitoring scene |
CN104778448A (en) * | 2015-03-24 | 2015-07-15 | 孙建德 | Structure adaptive CNN (Convolutional Neural Network)-based face recognition method |
CN105389596A (en) * | 2015-12-21 | 2016-03-09 | 长沙网动网络科技有限公司 | Method for enabling convolutional neural network to be suitable for recognition of pictures of various sizes |
WO2016149881A1 (en) * | 2015-03-20 | 2016-09-29 | Intel Corporation | Object recogntion based on boosting binary convolutional neural network features |
CN106096510A (en) * | 2016-05-31 | 2016-11-09 | 北京小米移动软件有限公司 | The method and apparatus of fingerprint recognition |
CN106250911A (en) * | 2016-07-20 | 2016-12-21 | 南京邮电大学 | A kind of picture classification method based on convolutional neural networks |
CN106407369A (en) * | 2016-09-09 | 2017-02-15 | 华南理工大学 | Photo management method and system based on deep learning face recognition |
WO2017173605A1 (en) * | 2016-04-06 | 2017-10-12 | Xiaogang Wang | Method and system for person recognition |
CN107392158A (en) * | 2017-07-27 | 2017-11-24 | 济南浪潮高新科技投资发展有限公司 | A kind of method and device of image recognition |
WO2018120740A1 (en) * | 2016-12-29 | 2018-07-05 | 深圳光启合众科技有限公司 | Picture classification method, device and robot |
CN108553028A (en) * | 2018-04-12 | 2018-09-21 | 深圳市沃特沃德股份有限公司 | Drive mouse method and sweeping robot |
CN109102532A (en) * | 2017-06-20 | 2018-12-28 | 西门子保健有限责任公司 | The metaplasia of deep learning for medical imaging |
CN109187534A (en) * | 2018-08-01 | 2019-01-11 | 江苏凯纳水处理技术有限公司 | Water quality detection method and its water sample pattern recognition device |
WO2019200735A1 (en) * | 2018-04-17 | 2019-10-24 | 平安科技(深圳)有限公司 | Livestock feature vector acquisition method, apparatus, computer device and storage medium |
CN110573859A (en) * | 2017-04-13 | 2019-12-13 | 美国西门子医学诊断股份有限公司 | Method and apparatus for HILN characterization using convolutional neural networks |
CN111914984A (en) * | 2019-05-07 | 2020-11-10 | 财团法人成大研究发展基金会 | Artificial neural network normalization system for identification device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070047802A1 (en) * | 2005-08-31 | 2007-03-01 | Microsoft Corporation | Training convolutional neural networks on graphics processing units |
CN103544506A (en) * | 2013-10-12 | 2014-01-29 | Tcl集团股份有限公司 | Method and device for classifying images on basis of convolutional neural network |
CN104036323A (en) * | 2014-06-26 | 2014-09-10 | 叶茂 | Vehicle detection method based on convolutional neural network |
-
2014
- 2014-09-23 CN CN201410488286.2A patent/CN104268521A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070047802A1 (en) * | 2005-08-31 | 2007-03-01 | Microsoft Corporation | Training convolutional neural networks on graphics processing units |
CN103544506A (en) * | 2013-10-12 | 2014-01-29 | Tcl集团股份有限公司 | Method and device for classifying images on basis of convolutional neural network |
CN104036323A (en) * | 2014-06-26 | 2014-09-10 | 叶茂 | Vehicle detection method based on convolutional neural network |
Non-Patent Citations (3)
Title |
---|
肖柏旭: "基于卷积网络的人脸检测的研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
许可: "卷积神经网络在图像识别上的应用的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
陈先昌: "基于卷积神经网络的深度学习算法与应用研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104268524A (en) * | 2014-09-24 | 2015-01-07 | 朱毅 | Convolutional neural network image recognition method based on dynamic adjustment of training targets |
CN104573679A (en) * | 2015-02-08 | 2015-04-29 | 天津艾思科尔科技有限公司 | Deep learning-based face recognition system in monitoring scene |
CN104573679B (en) * | 2015-02-08 | 2018-06-22 | 天津艾思科尔科技有限公司 | Face identification system based on deep learning under monitoring scene |
WO2016149881A1 (en) * | 2015-03-20 | 2016-09-29 | Intel Corporation | Object recogntion based on boosting binary convolutional neural network features |
CN107430677B (en) * | 2015-03-20 | 2022-04-12 | 英特尔公司 | Target identification based on improving binary convolution neural network characteristics |
US10685262B2 (en) | 2015-03-20 | 2020-06-16 | Intel Corporation | Object recognition based on boosting binary convolutional neural network features |
CN107430677A (en) * | 2015-03-20 | 2017-12-01 | 英特尔公司 | Based on the target identification lifted to binary system convolutional neural networks feature |
CN104778448B (en) * | 2015-03-24 | 2017-12-15 | 孙建德 | A kind of face identification method based on structure adaptive convolutional neural networks |
CN104778448A (en) * | 2015-03-24 | 2015-07-15 | 孙建德 | Structure adaptive CNN (Convolutional Neural Network)-based face recognition method |
CN105389596A (en) * | 2015-12-21 | 2016-03-09 | 长沙网动网络科技有限公司 | Method for enabling convolutional neural network to be suitable for recognition of pictures of various sizes |
CN105389596B (en) * | 2015-12-21 | 2018-05-29 | 长沙网动网络科技有限公司 | The method that convolutional neural networks are suitable for identification sizes picture |
WO2017173605A1 (en) * | 2016-04-06 | 2017-10-12 | Xiaogang Wang | Method and system for person recognition |
CN106096510A (en) * | 2016-05-31 | 2016-11-09 | 北京小米移动软件有限公司 | The method and apparatus of fingerprint recognition |
CN106096510B (en) * | 2016-05-31 | 2019-08-30 | 北京小米移动软件有限公司 | The method and apparatus of fingerprint recognition |
CN106250911A (en) * | 2016-07-20 | 2016-12-21 | 南京邮电大学 | A kind of picture classification method based on convolutional neural networks |
CN106250911B (en) * | 2016-07-20 | 2019-05-24 | 南京邮电大学 | A kind of picture classification method based on convolutional neural networks |
CN106407369A (en) * | 2016-09-09 | 2017-02-15 | 华南理工大学 | Photo management method and system based on deep learning face recognition |
WO2018120740A1 (en) * | 2016-12-29 | 2018-07-05 | 深圳光启合众科技有限公司 | Picture classification method, device and robot |
CN108256544A (en) * | 2016-12-29 | 2018-07-06 | 深圳光启合众科技有限公司 | Picture classification method and device, robot |
CN108256544B (en) * | 2016-12-29 | 2019-07-23 | 杭州光启人工智能研究院 | Picture classification method and device, robot |
CN110573859A (en) * | 2017-04-13 | 2019-12-13 | 美国西门子医学诊断股份有限公司 | Method and apparatus for HILN characterization using convolutional neural networks |
CN110573859B (en) * | 2017-04-13 | 2022-07-26 | 美国西门子医学诊断股份有限公司 | Method and apparatus for HILN characterization using convolutional neural networks |
CN109102532A (en) * | 2017-06-20 | 2018-12-28 | 西门子保健有限责任公司 | The metaplasia of deep learning for medical imaging |
US11154196B2 (en) * | 2017-06-20 | 2021-10-26 | Siemens Healthcare Gmbh | Deep-learnt tissue deformation for medical imaging |
CN109102532B (en) * | 2017-06-20 | 2022-07-15 | 西门子保健有限责任公司 | Deep learning tissue deformation for medical imaging |
US11925434B2 (en) | 2017-06-20 | 2024-03-12 | Siemens Healthineers Ag | Deep-learnt tissue deformation for medical imaging |
CN107392158A (en) * | 2017-07-27 | 2017-11-24 | 济南浪潮高新科技投资发展有限公司 | A kind of method and device of image recognition |
CN108553028A (en) * | 2018-04-12 | 2018-09-21 | 深圳市沃特沃德股份有限公司 | Drive mouse method and sweeping robot |
WO2019200735A1 (en) * | 2018-04-17 | 2019-10-24 | 平安科技(深圳)有限公司 | Livestock feature vector acquisition method, apparatus, computer device and storage medium |
CN109187534A (en) * | 2018-08-01 | 2019-01-11 | 江苏凯纳水处理技术有限公司 | Water quality detection method and its water sample pattern recognition device |
CN111914984A (en) * | 2019-05-07 | 2020-11-10 | 财团法人成大研究发展基金会 | Artificial neural network normalization system for identification device |
CN111914984B (en) * | 2019-05-07 | 2023-10-27 | 财团法人成大研究发展基金会 | Artificial neural network normalization system for identification device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104268521A (en) | Image recognition method based on convolutional neural network in non-finite category | |
CN104268524A (en) | Convolutional neural network image recognition method based on dynamic adjustment of training targets | |
CN109614922B (en) | Dynamic and static gesture recognition method and system | |
KR102068576B1 (en) | Convolutional neural network based image processing system and method | |
CN107798381B (en) | Image identification method based on convolutional neural network | |
CN106295637B (en) | A kind of vehicle identification method based on deep learning and intensified learning | |
CN107368845A (en) | A kind of Faster R CNN object detection methods based on optimization candidate region | |
CN113222011B (en) | Small sample remote sensing image classification method based on prototype correction | |
JP6933164B2 (en) | Learning data creation device, learning model creation system, learning data creation method, and program | |
CN107274378B (en) | Image fuzzy type identification and parameter setting method based on fusion memory CNN | |
CN113095370B (en) | Image recognition method, device, electronic equipment and storage medium | |
CN112766229B (en) | Human face point cloud image intelligent identification system and method based on attention mechanism | |
CN107146217A (en) | A kind of image detecting method and device | |
CN111832484A (en) | Loop detection method based on convolution perception hash algorithm | |
CN110168572A (en) | Information processing method, information processing unit, computer readable storage medium | |
CN110751072B (en) | Double-person interactive identification method based on knowledge embedded graph convolution network | |
CN107480723B (en) | Texture Recognition based on partial binary threshold learning network | |
Nazarenko et al. | Features of application of machine learning methods for classification of network traffic (features, advantages, disadvantages) | |
CN104408470A (en) | Gender detection method based on average face preliminary learning | |
CN105389596A (en) | Method for enabling convolutional neural network to be suitable for recognition of pictures of various sizes | |
CN115941112B (en) | Portable hidden communication method, computer equipment and storage medium | |
CN115331069A (en) | Personalized image classification model training method based on federal learning | |
CN114998958A (en) | Face recognition method based on lightweight convolutional neural network | |
CN109657548A (en) | A kind of method for detecting human face and system based on deep learning | |
CN112348079A (en) | Data dimension reduction processing method and device, computer equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150107 |