WO2021159594A1 - 图像识别方法及装置、电子设备和存储介质 - Google Patents

图像识别方法及装置、电子设备和存储介质 Download PDF

Info

Publication number
WO2021159594A1
WO2021159594A1 PCT/CN2020/081371 CN2020081371W WO2021159594A1 WO 2021159594 A1 WO2021159594 A1 WO 2021159594A1 CN 2020081371 W CN2020081371 W CN 2020081371W WO 2021159594 A1 WO2021159594 A1 WO 2021159594A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
area
network
information
target
Prior art date
Application number
PCT/CN2020/081371
Other languages
English (en)
French (fr)
Inventor
杨钰鑫
惠维
朱铖恺
武伟
李江涛
Original Assignee
深圳市商汤科技有限公司
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 深圳市商汤科技有限公司 filed Critical 深圳市商汤科技有限公司
Priority to JP2021536000A priority Critical patent/JP2022522596A/ja
Priority to SG11202106622XA priority patent/SG11202106622XA/en
Priority to US17/353,045 priority patent/US20210312214A1/en
Publication of WO2021159594A1 publication Critical patent/WO2021159594A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • 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
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/253—Fusion techniques of extracted features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G06V20/625—License plates
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection

Definitions

  • the present disclosure relates to the field of computer technology, and in particular to an image recognition method and device, electronic equipment, and storage medium.
  • the present disclosure proposes a technical solution for image recognition.
  • an image recognition method including: performing key point detection on an image to be processed, and determining multiple contour key point information of a target area in the image to be processed; and according to the multiple contour key points Information, correcting the target area in the image to be processed to obtain the area image information of the correction area corresponding to the target area; recognizing the area image information to obtain the recognition result of the target area.
  • the performing key point detection on the image to be processed and determining multiple contour key point information of the target area in the image to be processed includes: extracting and fusing features of the image to be processed, Obtain the feature map of the image to be processed; perform key point detection on the feature map of the image to be processed to obtain multiple contour key point information of the target area in the image to be processed.
  • the plurality of contour key point information includes the first positions of the plurality of contour key points, and according to the plurality of contour key point information, the information in the to-be-processed image Correcting the target area to obtain the area image information of the correction area corresponding to the target area includes: determining the target area and the correction area according to the first position of the plurality of contour key points and the second position of the correction area The homography transformation matrix between the correction areas; according to the homography transformation matrix, the image or feature of the target area is corrected to obtain the area image information of the correction area.
  • the homography transformation matrix between the target area and the correction area is determined according to the first position of the plurality of contour key points and the second position of the correction area , Including: performing normalization processing on the first position and the second position respectively to obtain a normalized first position and a normalized second position; according to the normalized first position A position and the normalized second position determine a homography transformation matrix between the target area and the correction area.
  • the correcting the image of the target area according to the homography transformation matrix to obtain the area image information of the correction area includes: according to multiple targets in the correction area The third position of the point and the homography transformation matrix determine the pixel point corresponding to each of the third positions in the target area; the pixel information of the pixel point corresponding to each of the third positions is mapped to each The target points are interpolated between each of the target points to obtain the area image information of the correction area.
  • the recognizing the area image information to obtain the recognition result of the target area includes: performing feature extraction on the area image information to obtain a feature vector of the area image information ; Decoding the feature vector to obtain the recognition result of the target area.
  • the method is implemented by a neural network, the neural network includes a target detection network, a correction network, and a recognition network, and the target detection network is used to perform key point detection on the image to be processed,
  • the correction network is used for correcting the target area
  • the recognition network is used for recognizing the image information of the area, wherein the method further includes:
  • the training set includes a plurality of sample images, the outline key point labeling information of the target area in each sample image, and the background labeling information And category labeling information; training the correction network and the recognition network according to the training set and the trained target detection network.
  • the target detection network includes a feature extraction sub-network, a feature fusion sub-network, and a detection sub-network.
  • the target detection network is trained according to a preset training set to obtain the trained target Detection network, including:
  • the target area includes a license plate area of a vehicle
  • the recognition result of the target area includes a character category of the license plate area
  • an image recognition device including: a key point detection module, configured to perform key point detection on an image to be processed, and determine multiple contour key point information of a target area in the image to be processed; Module, used to correct the target area in the image to be processed according to the multiple contour key point information, to obtain the area image information of the corrected area corresponding to the target area; the recognition module, used to correct the The area image information is recognized, and the recognition result of the target area is obtained.
  • a key point detection module configured to perform key point detection on an image to be processed, and determine multiple contour key point information of a target area in the image to be processed
  • Module used to correct the target area in the image to be processed according to the multiple contour key point information, to obtain the area image information of the corrected area corresponding to the target area
  • the recognition module used to correct the The area image information is recognized, and the recognition result of the target area is obtained.
  • the key point detection module includes: a feature extraction and fusion sub-module for feature extraction and fusion of the image to be processed to obtain a feature map of the image to be processed; The module is used to perform key point detection on the feature map of the image to be processed to obtain multiple contour key point information of the target area in the image to be processed.
  • the plurality of contour key point information includes the first positions of the plurality of contour key points
  • the correction module includes: a transformation matrix determining sub-module for determining the sub-module according to the plurality of contours The first position of the key point and the second position of the correction area determine the homography transformation matrix between the target area and the correction area; The image or feature of the target area is corrected to obtain the area image information of the corrected area.
  • the transformation matrix determining submodule is used to: perform normalization processing on the first position and the second position respectively to obtain a normalized first position and a normalized position.
  • the correction sub-module is configured to: determine, according to the third positions of the multiple target points in the correction area and the homography transformation matrix, the target area and each of the first Pixels corresponding to three positions; map the pixel information of the pixel corresponding to each of the third positions to each of the target points, and perform interpolation processing between each of the target points to obtain the area of the correction area Image information.
  • the recognition module includes: extracting features of the regional image information to obtain a feature vector of the regional image information; and decoding the feature vector to obtain the recognition of the target region result.
  • the device is implemented by a neural network
  • the neural network includes a target detection network, a correction network, and a recognition network
  • the target detection network is used to detect key points of the image to be processed
  • the correction network is used for correcting the target area
  • the recognition network is used for recognizing the image information of the area
  • the device further includes:
  • the first training module is used to train the target detection network according to a preset training set to obtain a trained target detection network.
  • the training set includes a plurality of sample images and the contour key of the target region in each sample image Point labeling information, background labeling information, and category labeling information; the second training module is used to train the correction network and the recognition network according to the training set and the trained target detection network.
  • the target detection network includes a feature extraction sub-network, a feature fusion sub-network, and a detection sub-network
  • the first training module is configured to: compare the sample image with the feature extraction sub-network. Perform feature extraction to obtain the first feature of the sample image; perform feature fusion on the first feature through the feature fusion sub-network to obtain the fusion feature of the sample image; perform the fusion feature on the sample image through the detection sub-network Feature detection to obtain contour key point detection information and background detection information of the target in the sample image; according to the contour key point detection information and background detection information of the multiple sample images, and the contour key of the multiple sample images Point labeling information and background labeling information are trained to train the target detection network to obtain a trained target detection network.
  • the target area includes a license plate area of a vehicle
  • the recognition result of the target area includes a character category of the license plate area
  • an electronic device including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to call the instructions stored in the memory to execute the foregoing method.
  • a computer-readable storage medium having computer program instructions stored thereon, and the computer program instructions implement the above-mentioned method when executed by a processor.
  • a computer program including computer readable code, and when the computer readable code runs in an electronic device, a processor in the electronic device executes the above method.
  • multiple outline key point information of the target area in the image to be processed can be determined, the target area is corrected according to the multiple outline key point information, the corrected area image information is recognized, and the recognition of the target area is obtained. As a result, the accuracy of target recognition is improved.
  • Fig. 1 shows a flowchart of an image recognition method according to an embodiment of the present disclosure.
  • Fig. 2 shows a schematic diagram of a key point detection process according to an embodiment of the present disclosure.
  • Fig. 3 shows a schematic diagram of an image recognition process according to an embodiment of the present disclosure.
  • Fig. 4 shows a block diagram of an image recognition device according to an embodiment of the present disclosure.
  • Fig. 5 shows a block diagram of an electronic device according to an embodiment of the present disclosure.
  • Fig. 6 shows a block diagram of an electronic device according to an embodiment of the present disclosure.
  • Fig. 1 shows a flowchart of an image recognition method according to an embodiment of the present disclosure. As shown in Fig. 1, the method includes:
  • step S11 key point detection is performed on the image to be processed, and multiple contour key point information of the target area in the image to be processed is determined;
  • step S12 the target area in the image to be processed is corrected according to the multiple contour key point information to obtain the area image information of the correction area corresponding to the target area;
  • step S13 the region image information is recognized to obtain the recognition result of the target region.
  • the image recognition method can be executed by electronic equipment such as a terminal device or a server, and the terminal device can be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, or a cordless
  • UE user equipment
  • PDAs personal digital assistants
  • the method can be implemented by a processor invoking computer-readable instructions stored in a memory.
  • the method can be executed by a server.
  • the image to be processed may be an image or video frame captured by an image capture device (such as a camera), and the image to be processed includes a target to be recognized, such as a pedestrian, a vehicle, a license plate, and the like.
  • an image capture device such as a camera
  • the image to be processed includes a target to be recognized, such as a pedestrian, a vehicle, a license plate, and the like.
  • key point detection may be performed on the image to be processed in step S11 to determine multiple contour key point information on the contour of the image area (which may be referred to as the target area) where the target in the image to be processed is located.
  • the target area is a quadrilateral area
  • the multiple contour key points of the target area may be, for example, four vertices of the target area. It should be understood that those skilled in the art can set the number of detected contour key points according to the actual situation, as long as the detected contour key points can define the range of the target area. The number is not limited.
  • the target area in the image to be processed may have distortion, rotation, deformation, etc.
  • the target area in the image to be processed can be corrected based on the multiple contour key point information, for example, by homography transformation, to obtain the area image information of the corrected area corresponding to the target area.
  • the correction area is an area displayed when the target area is viewed squarely.
  • the correction area is a rectangular area where the license plate is located when the license plate is viewed squarely.
  • the area image information of the correction area may be an image or a feature map of the correction area.
  • the area image information may be recognized in step S13 to obtain the recognition result of the target area.
  • a neural network can perform feature extraction on regional image information, and decode the extracted features to obtain a recognition result.
  • the target area includes a license plate area of a vehicle
  • the recognition result of the target area includes a character category of the license plate area. That is to say, when the target to be recognized is the license plate of the vehicle, multiple outline key points (for example, 4 vertices) of the license plate area in the image can be detected, and then the license plate area can be corrected and recognized to obtain the character type of the license plate area.
  • the license plate area includes the characters 9815QW.
  • the recognition result of the target area is the text and/or number on the billboard or shop sign; the target to be recognized is In the case of a traffic sign, the recognition result of the target area obtained is the sign type of the traffic sign. This disclosure does not limit this.
  • multiple outline key point information of the target area in the image to be processed can be determined, the target area is corrected according to the multiple outline key point information, the corrected area image information is recognized, and the recognition of the target area is obtained. As a result, the accuracy of target recognition is improved.
  • step S11 may include:
  • the key point detection of the image to be processed can be realized through the target detection network
  • the target detection network can be, for example, a convolutional neural network.
  • the target detection network may include a feature extraction sub-network, a feature fusion sub-network, and a detection sub-network.
  • feature extraction may be performed on the image to be processed through a feature extraction sub-network to obtain features of multiple scales of the image to be processed.
  • the feature extraction sub-network can adopt the residual network Resnet, which includes multiple residual layers or residual blocks. It should be understood that the feature extraction sub-network may also adopt network structures such as googlenet (Google network), vggnet (vgg network), shufflenet (shuffle network), darknet (dark network), etc., which is not limited in the present disclosure.
  • the feature fusion sub-network may be used to fuse features of multiple scales of the image to be processed to obtain a feature of one scale, that is, the feature map of the image to be processed.
  • the feature fusion sub-network can adopt the feature pyramid network FPN, and can also adopt network structures such as NAS-FPN (automatically searched feature pyramid network), hourglass (hourglass network), etc. The present disclosure does not limit this.
  • the key point detection can be performed on the feature map of the image to be processed through the detection sub-network to obtain multiple contour key point information of the target area in the image to be processed.
  • the detection sub-network may include multiple convolutional layers and multiple detection layers (for example, including a fully connected layer).
  • the feature information in the feature map of the image to be processed is further extracted through multiple convolutional layers, and then multiple detection layers are used.
  • the positions of the key points in the feature information are respectively detected.
  • the target area is a quadrilateral, four positioning heat maps can be predicted to locate the positions of the upper left, upper right, lower right, and lower left vertices (that is, 4 key points) of the target area respectively.
  • Each heat map can be defined as the position of the vertex coordinates as 1, and the rest as 0.
  • the 01 code can be selected, or it can be replaced by Gauss code, which is not limited in the present disclosure.
  • Fig. 2 shows a schematic diagram of a key point detection process according to an embodiment of the present disclosure.
  • the image 21 to be processed may be input to the target detection network, and feature extraction and fusion are performed through the residual network (Res) 22 and the feature pyramid network (FPN) 23 in turn to obtain a feature map 24.
  • Res residual network
  • FPN feature pyramid network
  • the size of the image 21 to be processed may be 320 ⁇ 280, for example, after feature extraction and fusion, a feature map 24 with a size of 80 ⁇ 70 ⁇ 64 is obtained; the feature map 24 is further scrolled through the detection sub-network (not shown) Product and key point detection, obtain the location heat map of the four key points of 80 ⁇ 70 ⁇ 4, thus determine the position of the top left, top right, bottom right and bottom left vertices of the target area.
  • the multiple contour key point information includes the first positions of the multiple contour key points
  • step S12 may include:
  • the image or feature of the target area is corrected to obtain the area image information of the correction area.
  • the target area can be corrected.
  • the multiple contour key point information may include the position coordinates of each contour key point in the image to be processed or the feature map of the image to be processed (that is, the first position of each contour key point).
  • the target area is a quadrilateral area, 4 contour key points can be included.
  • the scale of the image to be processed or its feature map can be set as h (height) ⁇ w (width) ⁇ C (number of channels), and the contour key point coordinates are (x1, y1, x2, y2, x3, y3, x4, y4), the corrected area after correction is h H (height) ⁇ w H (width) ⁇ C (number of channels).
  • the position of the target area can be determined according to the first positions of the multiple contour key points, and then according to the position of the target area and the second position of the correction area, the homography transformation matrix between the target area and the correction area can be determined. It should be understood that the homography transformation matrix between the target area and the correction area can be determined in a manner known in the art, and the present disclosure does not limit this.
  • the homography transformation matrix between the target area and the correction area is determined according to the first position of the plurality of contour key points and the second position of the correction area
  • the steps can include:
  • the input contour key point coordinates (x1, y1, x2, y2, x3, y3, x4, y4) and the output correction area h H (height) ⁇ w H (width) ⁇ C (channel) are respectively normalized, and the input coordinates and output coordinates are normalized to between [-1,1], and the normalized first position and the normalized second position are obtained.
  • the homography transformation matrix between the normalized target area and the correction area is determined (for example, a 3 ⁇ 3 matrix is obtained).
  • the determination method of the homography transformation matrix is not limited.
  • the scales of the target area and the correction area can be unified, the error caused by the difference between the scales of the target area and the correction area can be reduced, and the accuracy of the homography transformation matrix can be improved.
  • the step of correcting the image or feature of the target area according to the homography transformation matrix to obtain the area image information of the correction area may include:
  • the pixel information of the pixel points corresponding to each of the third positions is mapped to each of the target points, and interpolation processing is performed between each of the target points to obtain the area image information of the correction area.
  • w H and h H points can be taken at equal intervals between [-1,1] on the x-axis and y-axis to obtain the correction area Rasterized coordinates (h H ⁇ w H coordinates in total), the rasterized coordinates are used as multiple target points in the correction area.
  • the positions of the corresponding pixel points in the target area can be calculated, so as to determine the pixel points corresponding to each third position in the target area.
  • the pixel information (ie pixel value) of the pixel corresponding to each third position can be mapped to each target point, and interpolation processing between each target point can be performed to obtain the area of the correction area Image information.
  • the bilinear interpolation method may be used, or other interpolation methods may be used, which is not limited in the present disclosure.
  • the area image information may be an area image or an area feature map, which is not limited in the present disclosure.
  • the obliquely rotated target area can be corrected to the horizontal direction.
  • This process can be called Homopooling operation.
  • This operation can be differentiated and back-propagated to correct the image or feature of the target area. It can be embedded in any neural network for end-to-end training, so that it can be in a unified network Realize the entire image recognition process.
  • step S13 includes:
  • regional image information can be identified through a recognition network, which can include multiple convolutional layers, a group normalization layer, a RELU activation layer, and a maximum pooling layer.
  • a recognition network which can include multiple convolutional layers, a group normalization layer, a RELU activation layer, and a maximum pooling layer.
  • the identification network may also include a fully connected layer and a CTC (Connectionist Temporal Classification) decoder.
  • the feature vector is processed by the fully connected layer, and the character probability distribution vector of the regional image information can be obtained; the character probability distribution vector can be decoded by the CTC decoder to obtain the recognition result of the target region.
  • the recognition result of the target area is the character corresponding to the license plate, for example, the character 9815QW. In this way, the accuracy of the recognition result can be improved.
  • Fig. 3 shows a schematic diagram of an image recognition process according to an embodiment of the present disclosure.
  • the image recognition method according to the embodiment of the present disclosure can be implemented by a neural network.
  • the neural network includes a target detection network 31, a correction network 32, and a recognition network 33.
  • the target detection network 31 is used to analyze the image to be processed.
  • the correction network 32 is used to correct the target area
  • the recognition network 33 is used to recognize the image information of the area.
  • the target in the image to be processed 34 is the license plate of the vehicle.
  • the image to be processed 34 can be input to the target detection network 31 for key point detection to obtain an image 35 including the four vertices of the license plate; through the correction network 32, The four vertices in the image 35 are corrected for the license plate area of the image 34 to be processed to obtain the license plate image 36; the license plate image 36 is input into the recognition network 33 for recognition, and the recognition result 37 of the license plate area is obtained, that is, the characters corresponding to the license plate 9815QW.
  • the image recognition method according to the embodiment of the present disclosure further includes:
  • the training set includes multiple sample images, contour key point labeling information of the target area in each sample image, and background labeling information And category labeling information;
  • the neural network can be trained in two stages, that is, the target detection network is trained first, and then the correction network and the recognition network are trained.
  • the sample images in the training set can be input into the target detection network, and the contour key point detection information of the target area in the sample image can be output; the contour key point detection information and contour key point labeling information of multiple sample images Adjust the parameters of the target detection network until the preset training conditions are met to obtain the trained target detection network.
  • the sample images in the training set can be input into the trained target detection network, and the training and recognition results of the target area in the sample image can be obtained through the trained target detection network, correction network and recognition network processing;
  • the step of training the target detection network according to a preset training set to obtain a trained target detection network includes:
  • the outline key point detection information and background detection information of the multiple sample images train the target detection network to obtain a trained target detection network .
  • background detection can be added in the training process to improve the training effect.
  • the sample image can be input into the feature extraction sub-network for feature extraction to obtain the first feature of the sample image; the first feature can be input into the feature fusion sub-network for feature fusion to obtain the fusion feature of the sample image; the fusion feature is input into the detection sub-network
  • the key point detection information and background detection information of the target in the sample image are obtained. That is, when the target is a license plate, the detection information of the four vertices and the detection information of the background in the sample image can be obtained.
  • the outline key point detection information and background detection information of the multiple sample images, and the outline key point label information and background label information of the multiple sample images can determine the network loss of the target detection network , Thereby adjusting the parameters of the target detection network according to the network loss until the preset training conditions are met, and the trained target detection network is obtained.
  • the training effect of the target detection network can be greatly improved.
  • the image recognition method of the embodiment of the present disclosure it is possible to accurately recognize objects with variable lengths (such as license plates, billboards, traffic signs, etc.) in the image of the image from multiple angles.
  • This method uses key point recognition to replace the bounding box-based license plate detection.
  • This method does not require pixel-by-pixel regression, does not need to detect anchors, eliminates non-maximum suppression, and greatly improves the detection speed.
  • Using the heat map of key points as the regression target improves the accuracy of positioning.
  • the increase in points can obtain more license plate information, which can be used for homography pooling to correct the license plate.
  • the license plate images or features can be corrected by homography pooling, which can be embedded in any network, thereby realizing a unified network of end-to-end joint training.
  • Each part of the network can be jointly optimized to ensure speed and Accuracy.
  • the image recognition method according to the embodiments of the present disclosure can be applied to scenarios such as smart cities, intelligent transportation, security monitoring, parking lots, vehicle re-recognition, and license plate recognition, to quickly and accurately recognize license plate numbers, and then use license plate numbers for charging, Fines, inspection of licensed vehicles, etc.
  • the present disclosure also provides image recognition devices, electronic equipment, computer-readable storage media, and programs, all of which can be used to implement any of the image recognition methods provided in the present disclosure.
  • image recognition devices electronic equipment, computer-readable storage media, and programs, all of which can be used to implement any of the image recognition methods provided in the present disclosure.
  • Fig. 4 shows a block diagram of an image recognition device according to an embodiment of the present disclosure. As shown in Fig. 4, the device includes:
  • the key point detection module 41 is configured to perform key point detection on the image to be processed and determine multiple contour key point information of the target area in the to be processed image; the correction module 42 is configured to perform correction on the multiple contour key point information The target area in the image to be processed is corrected to obtain the area image information of the corrected area corresponding to the target area; the recognition module 43 is configured to recognize the area image information to obtain the recognition result of the target area .
  • the key point detection module includes: a feature extraction and fusion sub-module for feature extraction and fusion of the image to be processed to obtain a feature map of the image to be processed; The module is used to perform key point detection on the feature map of the image to be processed to obtain multiple contour key point information of the target area in the image to be processed.
  • the plurality of contour key point information includes the first positions of the plurality of contour key points
  • the correction module includes: a transformation matrix determining sub-module for determining the sub-module according to the plurality of contours The first position of the key point and the second position of the correction area determine the homography transformation matrix between the target area and the correction area; The image or feature of the target area is corrected to obtain the area image information of the corrected area.
  • the transformation matrix determining submodule is used to: perform normalization processing on the first position and the second position respectively to obtain a normalized first position and a normalized position.
  • the correction sub-module is configured to: determine, according to the third positions of the multiple target points in the correction area and the homography transformation matrix, the target area and each of the first Pixels corresponding to three positions; map the pixel information of the pixel corresponding to each of the third positions to each of the target points, and perform interpolation processing between each of the target points to obtain the area of the correction area Image information.
  • the recognition module includes: extracting features of the regional image information to obtain a feature vector of the regional image information; and decoding the feature vector to obtain the recognition of the target region result.
  • the device is implemented by a neural network
  • the neural network includes a target detection network, a correction network, and a recognition network
  • the target detection network is used to detect key points of the image to be processed
  • the correction network is used for correcting the target area
  • the recognition network is used for recognizing the image information of the area
  • the device further includes:
  • the first training module is used to train the target detection network according to a preset training set to obtain a trained target detection network.
  • the training set includes a plurality of sample images and the contour key of the target region in each sample image Point labeling information, background labeling information, and category labeling information; the second training module is used to train the correction network and the recognition network according to the training set and the trained target detection network.
  • the target detection network includes a feature extraction sub-network, a feature fusion sub-network, and a detection sub-network
  • the first training module is configured to: compare the sample image with the feature extraction sub-network. Perform feature extraction to obtain the first feature of the sample image; perform feature fusion on the first feature through the feature fusion sub-network to obtain the fusion feature of the sample image; perform the fusion feature on the sample image through the detection sub-network Feature detection to obtain contour key point detection information and background detection information of the target in the sample image; according to the contour key point detection information and background detection information of the multiple sample images, and the contour key of the multiple sample images Point labeling information and background labeling information are trained to train the target detection network to obtain a trained target detection network.
  • the target area includes a license plate area of a vehicle
  • the recognition result of the target area includes a character category of the license plate area
  • the functions or modules contained in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments.
  • the functions or modules contained in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments.
  • the embodiments of the present disclosure also provide a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above-mentioned method when executed by a processor.
  • the computer-readable storage medium may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium.
  • An embodiment of the present disclosure also proposes an electronic device, including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above method.
  • the embodiments of the present disclosure also provide a computer program product, including computer-readable code.
  • the processor in the device executes the image recognition method for implementing the image recognition method provided by any of the above embodiments. instruction.
  • the embodiments of the present disclosure also provide another computer program product for storing computer-readable instructions, which when executed, cause the computer to perform the operation of the image recognition method provided by any of the foregoing embodiments.
  • the electronic device can be provided as a terminal, server or other form of device.
  • FIG. 5 shows a block diagram of an electronic device 800 according to an embodiment of the present disclosure.
  • the electronic device 800 may be a mobile phone, a computer, a digital broadcasting terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, and other terminals.
  • the electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, and a sensor component 814 , And communication component 816.
  • the processing component 802 generally controls the overall operations of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations.
  • the processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the foregoing method.
  • the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components.
  • the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.
  • the memory 804 is configured to store various types of data to support operations in the electronic device 800. Examples of these data include instructions for any application or method to operate on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc.
  • the memory 804 can be implemented by any type of volatile or non-volatile storage device or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic Disk or Optical Disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read-only memory
  • EPROM erasable Programmable Read Only Memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • Magnetic Disk Magnetic Disk or Optical Disk.
  • the power supply component 806 provides power for various components of the electronic device 800.
  • the power supply component 806 may include a power management system, one or more power supplies, and other components associated with the generation, management, and distribution of power for the electronic device 800.
  • the multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user.
  • the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure related to the touch or slide operation.
  • the multimedia component 808 includes a front camera and/or a rear camera. When the electronic device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
  • the audio component 810 is configured to output and/or input audio signals.
  • the audio component 810 includes a microphone (MIC), and when the electronic device 800 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal.
  • the received audio signal may be further stored in the memory 804 or transmitted via the communication component 816.
  • the audio component 810 further includes a speaker for outputting audio signals.
  • the I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module.
  • the above-mentioned peripheral interface module may be a keyboard, a click wheel, a button, and the like. These buttons may include, but are not limited to: home button, volume button, start button, and lock button.
  • the sensor component 814 includes one or more sensors for providing the electronic device 800 with various aspects of state evaluation.
  • the sensor component 814 can detect the on/off status of the electronic device 800 and the relative positioning of the components.
  • the component is the display and the keypad of the electronic device 800.
  • the sensor component 814 can also detect the electronic device 800 or the electronic device 800.
  • the position of the component changes, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration/deceleration of the electronic device 800, and the temperature change of the electronic device 800.
  • the sensor component 814 may include a proximity sensor configured to detect the presence of nearby objects when there is no physical contact.
  • the sensor component 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • the sensor component 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
  • the communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices.
  • the electronic device 800 can access a wireless network based on a communication standard, such as WiFi, 2G, or 3G, or a combination thereof.
  • the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication component 816 further includes a near field communication (NFC) module to facilitate short-range communication.
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field-available A programmable gate array (FPGA), controller, microcontroller, microprocessor, or other electronic components are implemented to implement the above methods.
  • ASIC application-specific integrated circuits
  • DSP digital signal processors
  • DSPD digital signal processing devices
  • PLD programmable logic devices
  • FPGA field-available A programmable gate array
  • controller microcontroller, microprocessor, or other electronic components are implemented to implement the above methods.
  • a non-volatile computer-readable storage medium such as the memory 804 including computer program instructions, which can be executed by the processor 820 of the electronic device 800 to complete the foregoing method.
  • FIG. 6 shows a block diagram of an electronic device 1900 according to an embodiment of the present disclosure.
  • the electronic device 1900 may be provided as a server. 6
  • the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by the memory 1932, for storing instructions executable by the processing component 1922, such as application programs.
  • the application program stored in the memory 1932 may include one or more modules each corresponding to a set of instructions.
  • the processing component 1922 is configured to execute instructions to perform the above-described methods.
  • the electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input output (I/O) interface 1958 .
  • the electronic device 1900 can operate based on an operating system stored in the memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or the like.
  • a non-volatile computer-readable storage medium such as the memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to complete the foregoing method.
  • the present disclosure may be a system, method and/or computer program product.
  • the computer program product may include a computer-readable storage medium loaded with computer-readable program instructions for enabling a processor to implement various aspects of the present disclosure.
  • the computer-readable storage medium may be a tangible device that can hold and store instructions used by the instruction execution device.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Non-exhaustive list of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) Or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device, such as a printer with instructions stored thereon
  • RAM random access memory
  • ROM read-only memory
  • EPROM erasable programmable read-only memory
  • flash memory flash memory
  • SRAM static random access memory
  • CD-ROM compact disk read-only memory
  • DVD digital versatile disk
  • memory stick floppy disk
  • mechanical encoding device such as a printer with instructions stored thereon
  • the computer-readable storage medium used here is not interpreted as the instantaneous signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (for example, light pulses through fiber optic cables), or through wires Transmission of electrical signals.
  • the computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to various computing/processing devices, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and/or a wireless network.
  • the network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers.
  • the network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network, and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing/processing device .
  • the computer program instructions used to perform the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or in one or more programming languages.
  • Source code or object code written in any combination, the programming language includes object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as "C" language or similar programming languages.
  • Computer-readable program instructions can be executed entirely on the user's computer, partly on the user's computer, executed as a stand-alone software package, partly on the user's computer and partly executed on a remote computer, or entirely on the remote computer or server implement.
  • the remote computer can be connected to the user's computer through any kind of network-including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect to the user's computer) connect).
  • LAN local area network
  • WAN wide area network
  • an electronic circuit such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), can be customized by using the status information of the computer-readable program instructions.
  • the computer-readable program instructions are executed to realize various aspects of the present disclosure.
  • These computer-readable program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine that makes these instructions when executed by the processor of the computer or other programmable data processing device , A device that implements the functions/actions specified in one or more blocks in the flowcharts and/or block diagrams is produced. It is also possible to store these computer-readable program instructions in a computer-readable storage medium. These instructions make computers, programmable data processing apparatuses, and/or other devices work in a specific manner. Thus, the computer-readable medium storing the instructions includes An article of manufacture, which includes instructions for implementing various aspects of the functions/actions specified in one or more blocks in the flowcharts and/or block diagrams.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of an instruction, and the module, program segment, or part of an instruction contains one or more components for realizing the specified logical function.
  • Executable instructions may also occur in a different order from the order marked in the drawings. For example, two consecutive blocks can actually be executed in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or actions Or it can be realized by a combination of dedicated hardware and computer instructions.
  • the computer program product can be specifically implemented by hardware, software, or a combination thereof.
  • the computer program product is specifically embodied as a computer storage medium.
  • the computer program product is specifically embodied as a software product, such as a software development kit (SDK), etc. Wait.
  • SDK software development kit

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Mathematical Physics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

本公开涉及一种图像识别方法及装置、电子设备和存储介质，所述方法包括：对待处理图像进行关键点检测，确定所述待处理图像中目标区域的多个轮廓关键点信息；根据所述多个轮廓关键点信息，对所述待处理图像中的目标区域进行校正，得到与所述目标区域对应的校正区域的区域图像信息；对所述区域图像信息进行识别，得到所述目标区域的识别结果。本公开实施例可提高目标识别的准确率。

Description

图像识别方法及装置、电子设备和存储介质
本申请要求在2020年2月12日提交中国专利局、申请号为202010089651.8、发明名称为“图像识别方法及装置、电子设备和存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及计算机技术领域，尤其涉及一种图像识别方法及装置、电子设备和存储介质。
背景技术
在计算机视觉以及智能视频监控等领域中，需要对图像中的各种目标(例如行人、车辆等)进行检测与识别。
发明内容
本公开提出了一种图像识别技术方案。
根据本公开的一方面，提供了一种图像识别方法，包括：对待处理图像进行关键点检测，确定所述待处理图像中目标区域的多个轮廓关键点信息；根据所述多个轮廓关键点信息，对所述待处理图像中的目标区域进行校正，得到与所述目标区域对应的校正区域的区域图像信息；对所述区域图像信息进行识别，得到所述目标区域的识别结果。
在一种可能的实现方式中，所述对待处理图像进行关键点检测，确定所述待处理图像中目标区域的多个轮廓关键点信息，包括：对所述待处理图像进行特征提取及融合，得到所述待处理图像的特征图；对所述待处理图像的特征图进行关键点检测，得到所述待处理图像中目标区域的多个轮廓关键点信息。
在一种可能的实现方式中，所述多个轮廓关键点信息包括所述多个轮廓关键点的第一位置，所述根据所述多个轮廓关键点信息，对所述待处理图像中的目标区域进行校正，得到与所述目标区域对应的校正区域的区域图像信息，包括：根据所述多个轮廓关键点的第一位置及所述校正区域的第二位置，确定所述目标区域与所述校正区域之间的单应变换矩阵；根据所述单应变换矩阵，对所述目标区域的图像或特征进行校正，得到所述校正区域的区域图像信息。
在一种可能的实现方式中，所述根据所述多个轮廓关键点的第一位置及所述校正区域的第二位置，确定所述目标区域与所述校正区域之间的单应变换矩阵，包括：对所述第一位置与所述第二位置分别进行归一化处理，得到归一化后的第一位置和归一化后的 第二位置；根据所述归一化后的第一位置和所述归一化后的第二位置，确定所述目标区域与所述校正区域之间的单应变换矩阵。
在一种可能的实现方式中，所述根据所述单应变换矩阵，对所述目标区域的图像进行校正，得到所述校正区域的区域图像信息，包括：根据所述校正区域中多个目标点的第三位置以及所述单应变换矩阵，确定所述目标区域中与各个所述第三位置对应的像素点；将与各个所述第三位置对应的像素点的像素信息映射到各个所述目标点，并对各个所述目标点之间进行插值处理，得到所述校正区域的区域图像信息。
在一种可能的实现方式中，所述对所述区域图像信息进行识别，得到所述目标区域的识别结果，包括：对所述区域图像信息进行特征提取，得到所述区域图像信息的特征向量；对所述特征向量进行解码，得到所述目标区域的识别结果。
在一种可能的实现方式中，所述方法通过神经网络实现，所述神经网络包括目标检测网络、校正网络及识别网络，所述目标检测网络用于对所述待处理图像进行关键点检测，所述校正网络用于对所述目标区域进行校正，所述识别网络用于对所述区域图像信息进行识别，其中，所述方法还包括：
根据预设的训练集，训练所述目标检测网络，得到训练后的目标检测网络，所述训练集中包括多个样本图像、所述各样本图像中目标区域的轮廓关键点标注信息、背景标注信息及类别标注信息；根据所述训练集及所述训练后的目标检测网络，训练所述校正网络及所述识别网络。
在一种可能的实现方式中，所述目标检测网络包括特征提取子网络、特征融合子网络以及检测子网络，所述根据预设的训练集，训练所述目标检测网络，得到训练后的目标检测网络，包括：
通过所述特征提取子网络对所述样本图像进行特征提取，得到所述样本图像的第一特征；通过所述特征融合子网络对所述第一特征进行特征融合，得到所述样本图像的融合特征；通过所述检测子网络对所述融合特征进行检测，得到所述样本图像中目标的轮廓关键点检测信息及背景检测信息；根据所述多个样本图像的轮廓关键点检测信息及背景检测信息，和所述多个样本图像的轮廓关键点标注信息及背景标注信息，训练所述目标检测网络，得到训练后的目标检测网络。
在一种可能的实现方式中，所述目标区域包括车辆的车牌区域，所述目标区域的识别结果包括所述车牌区域的字符类别。
根据本公开的一方面，提供了一种图像识别装置，包括：关键点检测模块，用于对待处理图像进行关键点检测，确定所述待处理图像中目标区域的多个轮廓关键点信息；校正模块，用于根据所述多个轮廓关键点信息，对所述待处理图像中的目标区域进行校正，得到与所述目标区域对应的校正区域的区域图像信息；识别模块，用于对所述区域 图像信息进行识别，得到所述目标区域的识别结果。
在一种可能的实现方式中，所述关键点检测模块包括：特征提取及融合子模块，用于对所述待处理图像进行特征提取及融合，得到所述待处理图像的特征图；检测子模块，用于对所述待处理图像的特征图进行关键点检测，得到所述待处理图像中目标区域的多个轮廓关键点信息。
在一种可能的实现方式中，所述多个轮廓关键点信息包括所述多个轮廓关键点的第一位置，所述校正模块包括：变换矩阵确定子模块，用于根据所述多个轮廓关键点的第一位置及所述校正区域的第二位置，确定所述目标区域与所述校正区域之间的单应变换矩阵；校正子模块，用于根据所述单应变换矩阵，对所述目标区域的图像或特征进行校正，得到所述校正区域的区域图像信息。
在一种可能的实现方式中，所述变换矩阵确定子模块用于：对所述第一位置与所述第二位置分别进行归一化处理，得到归一化后的第一位置和归一化后的第二位置；根据所述归一化后的第一位置和所述归一化后的第二位置，确定所述目标区域与所述校正区域之间的单应变换矩阵。
在一种可能的实现方式中，所述校正子模块用于：根据所述校正区域中多个目标点的第三位置以及所述单应变换矩阵，确定所述目标区域中与各个所述第三位置对应的像素点；将与各个所述第三位置对应的像素点的像素信息映射到各个所述目标点，并对各个所述目标点之间进行插值处理，得到所述校正区域的区域图像信息。
在一种可能的实现方式中，所述识别模块包括：对所述区域图像信息进行特征提取，得到所述区域图像信息的特征向量；对所述特征向量进行解码，得到所述目标区域的识别结果。
在一种可能的实现方式中，所述装置通过神经网络实现，所述神经网络包括目标检测网络、校正网络及识别网络，所述目标检测网络用于对所述待处理图像进行关键点检测，所述校正网络用于对所述目标区域进行校正，所述识别网络用于对所述区域图像信息进行识别，其中，所述装置还包括：
第一训练模块，用于根据预设的训练集，训练所述目标检测网络，得到训练后的目标检测网络，所述训练集中包括多个样本图像、所述各样本图像中目标区域的轮廓关键点标注信息、背景标注信息及类别标注信息；第二训练模块，用于根据所述训练集及所述训练后的目标检测网络，训练所述校正网络及所述识别网络。
在一种可能的实现方式中，所述目标检测网络包括特征提取子网络、特征融合子网络以及检测子网络，所述第一训练模块用于：通过所述特征提取子网络对所述样本图像进行特征提取，得到所述样本图像的第一特征；通过所述特征融合子网络对所述第一特征进行特征融合，得到所述样本图像的融合特征；通过所述检测子网络对所述融合特征 进行检测，得到所述样本图像中目标的轮廓关键点检测信息及背景检测信息；根据所述多个样本图像的轮廓关键点检测信息及背景检测信息，和所述多个样本图像的轮廓关键点标注信息及背景标注信息，训练所述目标检测网络，得到训练后的目标检测网络。
在一种可能的实现方式中，所述目标区域包括车辆的车牌区域，所述目标区域的识别结果包括所述车牌区域的字符类别。
根据本公开的一方面，提供了一种电子设备，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为调用所述存储器存储的指令，以执行上述方法。
根据本公开的一方面，提供了一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述方法。
根据本公开的一方面，提供了一种计算机程序，所述计算机程序包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行上述方法。
根据本公开的实施例，能够确定出待处理图像中目标区域的多个轮廓关键点信息，根据多个轮廓关键点信息校正目标区域，对校正得到的区域图像信息进行识别，得到目标区域的识别结果，从而提高目标识别的准确率。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，而非限制本公开。根据下面参考附图对示例性实施例的详细说明，本公开的其它特征及方面将变得清楚。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，这些附图示出了符合本公开的实施例，并与说明书一起用于说明本公开的技术方案。
图1示出根据本公开实施例的图像识别方法的流程图。
图2示出根据本公开实施例的关键点检测过程的示意图。
图3示出根据本公开实施例的图像识别过程的示意图。
图4示出根据本公开实施例的图像识别装置的框图。
图5示出根据本公开实施例的一种电子设备的框图。
图6示出根据本公开实施例的一种电子设备的框图。
具体实施方式
以下将参考附图详细说明本公开的各种示例性实施例、特征和方面。附图中相同的附图标记表示功能相同或相似的元件。尽管在附图中示出了实施例的各种方面，但是除 非特别指出，不必按比例绘制附图。
在这里专用的词“示例性”意为“用作例子、实施例或说明性”。这里作为“示例性”所说明的任何实施例不必解释为优于或好于其它实施例。
本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中术语“至少一种”表示多种中的任意一种或多种中的至少两种的任意组合，例如，包括A、B、C中的至少一种，可以表示包括从A、B和C构成的集合中选择的任意一个或多个元素。
另外，为了更好地说明本公开，在下文的具体实施方式中给出了众多的具体细节。本领域技术人员应当理解，没有某些具体细节，本公开同样可以实施。在一些实例中，对于本领域技术人员熟知的方法、手段、元件和电路未作详细描述，以便于凸显本公开的主旨。
图1示出根据本公开实施例的图像识别方法的流程图，如图1所示，所述方法包括：
在步骤S11中，对待处理图像进行关键点检测，确定所述待处理图像中目标区域的多个轮廓关键点信息；
在步骤S12中，根据所述多个轮廓关键点信息，对所述待处理图像中的目标区域进行校正，得到与所述目标区域对应的校正区域的区域图像信息；
在步骤S13中，对所述区域图像信息进行识别，得到所述目标区域的识别结果。
在一种可能的实现方式中，所述图像识别方法可以由终端设备或服务器等电子设备执行，终端设备可以为用户设备(User Equipment，UE)、移动设备、用户终端、终端、蜂窝电话、无绳电话、个人数字处理(Personal Digital Assistant，PDA)、手持设备、计算设备、车载设备、可穿戴设备等，所述方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。或者，可通过服务器执行所述方法。
举例来说，待处理图像可以为图像采集设备(例如摄像头)所采集的图像或视频帧等，待处理图像中包括待识别的目标，例如行人、车辆、车牌等。
在一种可能的实现方式中，可在步骤S11中对待处理图像进行关键点检测，确定待处理图像中的目标所在图像区域(可称为目标区域)的轮廓上的多个轮廓关键点信息。在目标区域为四边形区域的情况下，目标区域的多个轮廓关键点可例如为目标区域的四个顶点。应当理解，本领域技术人员可根据实际情况设置所检测的轮廓关键点的数量，只要检测到的轮廓关键点能够限定目标区域的范围即可，本公开对目标区域的具体形状以及轮廓关键点的数量不作限制。
在一种可能的实现方式中，由于待处理图像的拍摄角度问题，待处理图像中的目标区域可能存在扭曲、旋转、变形等。在该情况下，可在步骤S12中，根据多个轮廓关键点 信息，对待处理图像中的目标区域进行校正，例如通过单应变换进行校正，得到与目标区域对应的校正区域的区域图像信息。该校正区域为正视目标区域时所展示的区域，例如在目标为车牌时，该校正区域为正视车牌时车牌所在的矩形区域。校正区域的区域图像信息可以为校正区域的图像或特征图。
在一种可能的实现方式中，在得到区域图像信息后，可在步骤S13中对区域图像信息进行识别，得到目标区域的识别结果。可例如通过神经网络对区域图像信息进行特征提取，并对提取到的特征进行解码，得到识别结果。
在一种可能的实现方式中，目标区域包括车辆的车牌区域，所述目标区域的识别结果包括所述车牌区域的字符类别。也就是说，待识别的目标为车辆的车牌时，可检测出图像中车牌区域的多个轮廓关键点(例如4个顶点)，进而对车牌区域进行校正及识别，得到车牌区域的字符类别，例如车牌区域包括字符9815QW。
在一种可能的实现方式中，在待识别的目标为广告牌或店铺招牌等时，得到的目标区域的识别结果为广告牌或店铺招牌上的文字和/或数字；在待识别的目标为交通标志物时，得到的目标区域的识别结果为交通标志物的标志类型。本公开对此不作限制。
根据本公开的实施例，能够确定出待处理图像中目标区域的多个轮廓关键点信息，根据多个轮廓关键点信息校正目标区域，对校正得到的区域图像信息进行识别，得到目标区域的识别结果，从而提高目标识别的准确率。
在一种可能的实现方式中，步骤S11可包括：
对所述待处理图像进行特征提取及融合，得到所述待处理图像的特征图；
对所述待处理图像的特征图进行关键点检测，得到所述待处理图像中目标区域的多个轮廓关键点信息。
举例来说，可通过目标检测网络实现待处理图像进行关键点检测，目标检测网络可例如为卷积神经网络。其中，目标检测网络可包括特征提取子网络、特征融合子网络以及检测子网络。
在一种可能的实现方式中，可通过特征提取子网络对待处理图像进行特征提取，得到待处理图像的多个尺度的特征。特征提取子网络可采用残差网络Resnet，包括多个残差层或残差块。应当理解，特征提取子网络还可以采用googlenet(谷歌网络)、vggnet(vgg网络)、shufflenet(混洗网络)、darknet(黑暗网络)等网络结构，本公开对此不作限制。
在一种可能的实现方式中，可通过特征融合子网络对待处理图像的多个尺度的特征进行融合，得到一个尺度的特征，也即待处理图像的特征图。其中，特征融合子网络可采用特征金字塔网络FPN，还可以采用NAS-FPN(自动搜索的特征金字塔网络)，hourglass(沙漏网络)等网络结构，本公开对此不作限制。
在一种可能的实现方式中，可通过检测子网络对待处理图像的特征图进行关键点检 测，得到待处理图像中目标区域的多个轮廓关键点信息。其中，检测子网络可包括多个卷积层及多个检测层(例如包括全连接层)，通过多个卷积层进一步提取待处理图像的特征图中的特征信息，再通过多个检测层分别检测该特征信息中的关键点的位置。在目标区域为四边形的情况下，可预测出4个定位热力图，分别定位目标区域的左上，右上，右下及左下顶点(也即4个关键点)的位置。每个热力图可定义为顶点坐标所在位置为1，其余为0，可以选择01编码，也可以替换为高斯编码，本公开对此不作限制。
图2示出根据本公开实施例的关键点检测过程的示意图。如图2所示，可将待处理图像21输入目标检测网络，依次经由残差网络(Res)22和特征金字塔网络(FPN)23进行特征提取及融合，得到特征图24。其中，待处理图像21的尺寸可例如为320×280，经特征提取及融合后，得到尺寸为80×70×64的特征图24；通过检测子网络(未示出)对特征图24进一步卷积及关键点检测，得到80×70×4的四个关键点的定位热力图，从而确定出目标区域的左上，右上，右下及左下顶点的位置。
通过这种方式，能够快速确定目标区域的多个轮廓关键点信息，从而精确限定目标区域的边界轮廓，提高了处理速度及精度。
在一种可能的实现方式中，多个轮廓关键点信息包括所述多个轮廓关键点的第一位置，步骤S12可包括：
根据所述多个轮廓关键点的第一位置及所述校正区域的第二位置，确定所述目标区域与所述校正区域之间的单应变换矩阵；
根据所述单应变换矩阵，对所述目标区域的图像或特征进行校正，得到所述校正区域的区域图像信息。
举例来说，在确定目标区域的多个轮廓关键点信息后，可对目标区域进行校正。其中，多个轮廓关键点信息可包括各个轮廓关键点在待处理图像中或待处理图像的特征图中的位置坐标(即各个轮廓关键点的第一位置)。在目标区域为四边形区域时，可包括4个轮廓关键点。
在一种可能的实现方式中，可设定待处理图像或其特征图的尺度为h(高度)×w(宽度)×C(通道数)，轮廓关键点坐标为(x1，y1，x2，y2，x3，y3，x4，y4)，经校正后的校正区域为h H(高度)×w H(宽度)×C(通道数)。可根据多个轮廓关键点的第一位置确定目标区域的位置，再根据目标区域的位置和校正区域的第二位置，可确定出目标区域与校正区域之间的单应变换矩阵。应当理解，可以采用本领域公知的方式确定目标区域与校正区域之间的单应变换矩阵，本公开对此不作限制。
在一种可能的实现方式中，所述根据所述多个轮廓关键点的第一位置及所述校正区域的第二位置，确定所述目标区域与所述校正区域之间的单应变换矩阵的步骤，可包括：
对所述第一位置与所述第二位置分别进行归一化处理，得到归一化后的第一位置和 归一化后的第二位置；
根据所述归一化后的第一位置和所述归一化后的第二位置，确定所述目标区域与所述校正区域之间的单应变换矩阵。
也就是说，可对输入的轮廓关键点坐标(x1，y1，x2，y2，x3，y3，x4，y4)，和输出的校正区域h H(高度)×w H(宽度)×C(通道数)的坐标分别进行归一化，将输入坐标和输出坐标归一化到[-1,1]之间，得到归一化后的第一位置和归一化后的第二位置。根据归一化后的第一位置和归一化后的第二位置，确定归一化后的目标区域与校正区域之间的单应变换矩阵(例如得到3×3的矩阵)，本公开对单应变换矩阵的确定方式不作限制。
通过这种方式，可统一目标区域与校正区域的尺度，降低目标区域与校正区域的尺度差异导致的误差，提高单应变换矩阵的准确度。
在一种可能的实现方式中，所述根据所述单应变换矩阵，对所述目标区域的图像或特征进行校正，得到所述校正区域的区域图像信息的步骤可包括：
根据所述校正区域中多个目标点的第三位置以及所述单应变换矩阵，确定所述目标区域中与各个所述第三位置对应的像素点；
将与各个所述第三位置对应的像素点的像素信息映射到各个所述目标点，并对各个所述目标点之间进行插值处理，得到所述校正区域的区域图像信息。
举例来说，针对校正区域归一化后的第二位置，可在坐标x轴和y轴上的[-1,1]之间分别等间隔取w H和h H个点，得到校正区域的栅格化坐标(共有h H×w H个坐标)，将栅格化坐标作为校正区域中的多个目标点。根据多个目标点的第三位置以及单应变换矩阵，可计算出目标区域中对应的像素点的位置，从而确定目标区域中与各个第三位置对应的像素点。
在一种可能的实现方式中，可将与各个第三位置对应的像素点的像素信息(即像素值)映射到各个目标点，并对各个目标点之间进行插值处理，得到校正区域的区域图像信息。可以采用双线性插值的方式，也可以采用其他插值方式，本公开对此不作限制。该区域图像信息可以为区域图像或区域特征图，本公开对此不作限制。
通过这种方式，可将倾斜旋转的目标区域校正到水平方向。该处理过程可称为单应池化(Homopooling)操作，该操作可以微分以及反向传播用以校正目标区域的图像或特征，可嵌入任何神经网络进行端到端的训练，从而能够在统一的网络中实现整个图像识别过程。
在一种可能的实现方式中，步骤S13包括：
对所述区域图像信息进行特征提取，得到所述区域图像信息的特征向量；对所述特征向量进行解码，得到所述目标区域的识别结果。
举例来说，可通过识别网络对区域图像信息进行识别，该识别网络可包括多个卷积层，组正则化(group normalization)层，RELU激活层以及最大池化层等网络层。经由各个网络层提取区域图像信息的特征，可得到宽度为1的特征向量，例如尺寸为1×47的特征向量。
在一种可能的实现方式中，该识别网络还可包括全连接层和CTC(Connectionist Temporal Classification，连接时间分类)解码器。通过全连接层对特征向量进行处理，可得到区域图像信息的字符概率分布向量；通过CTC解码器对字符概率分布向量进行解码，可得到目标区域的识别结果。在目标为车牌时，目标区域的识别结果为车牌所对应的字符，例如字符9815QW。通过这种方式，可提高识别结果的准确性。
图3示出根据本公开实施例的图像识别过程的示意图。如图3所示，根据本公开实施例的图像识别方法可通过神经网络实现，该神经网络包括目标检测网络31、校正网络32及识别网络33，目标检测网络31用于对所述待处理图像进行关键点检测，校正网络32用于对所述目标区域进行校正，识别网络33用于对所述区域图像信息进行识别。
如图3所示，待处理图像34中的目标为车辆的车牌，可将待处理图像34输入目标检测网络31进行关键点检测，得到包括车牌的四个顶点的图像35；通过校正网络32，对图像35中的四个顶点对待处理图像34的车牌区域进行校正，得到车牌图像36；将车牌图像36输入识别网络33中进行识别，得到车牌区域的识别结果37，也即车牌所对应的字符9815QW。
在部署神经网络之前，需要对神经网络进行训练。根据本公开实施例的图像识别方法，还包括：
根据预设的训练集，训练所述目标检测网络，得到训练后的目标检测网络，所述训练集中包括多个样本图像、各所述样本图像中目标区域的轮廓关键点标注信息、背景标注信息及类别标注信息；
根据所述训练集及所述训练后的目标检测网络，训练所述校正网络及所述识别网络。
举例来说，可以分两个阶段对神经网络进行训练，也即先训练目标检测网络，再训练校正网络及所述识别网络。
在训练的第一阶段，可将训练集中的样本图像输入目标检测网络中，输出样本图像中目标区域的轮廓关键点检测信息；根据多个样本图像的轮廓关键点检测信息与轮廓关键点标注信息之间的差异，调整目标检测网络的参数，直到满足预设的训练条件，得到训练后的目标检测网络。
在训练的第二阶段，可将训练集中的样本图像输入训练后的目标检测网络，经由训练后的目标检测网络、校正网络及识别网络处理，得到样本图像中目标区域的训练识别结果；根据多个样本图像的训练识别结果及类别标注信息之间的差异，调整校正网络及 识别网络的参数，直到满足预设的训练条件，得到训练后的校正网络及识别网络。
通过这种方式，可以提高训练效果，加快训练速度。
在一种可能的实现方式中，所述根据预设的训练集，训练所述目标检测网络，得到训练后的目标检测网络的步骤包括：
通过所述特征提取子网络对样本图像进行特征提取，得到所述样本图像的第一特征；
通过所述特征融合子网络对所述第一特征进行特征融合，得到所述样本图像的融合特征；
通过所述检测子网络对所述融合特征进行检测，得到所述样本图像中目标的轮廓关键点检测信息及背景检测信息；
根据所述多个样本图像的轮廓关键点检测信息及背景检测信息，和所述多个样本图像的轮廓关键点标注信息及背景标注信息，训练所述目标检测网络，得到训练后的目标检测网络。
举例来说，可在训练过程中添加对背景的检测，以便提高训练效果。可将样本图像输入特征提取子网络中进行特征提取，得到样本图像的第一特征；将第一特征输入特征融合子网络中进行特征融合，得到样本图像的融合特征；将融合特征输入检测子网络中进行检测，得到样本图像中目标的轮廓关键点检测信息及背景检测信息。也即，在目标为车牌时，可得到四个顶点的检测信息以及样本图像中背景的检测信息。
在一种可能的实现方式中，多个样本图像的轮廓关键点检测信息及背景检测信息，和所述多个样本图像的轮廓关键点标注信息及背景标注信息，可确定目标检测网络的网络损失，从而根据网络损失调整目标检测网络的参数，直到满足预设的训练条件，得到训练后的目标检测网络。
通过添加背景检测作为监督信号，能够大幅提高目标检测网络的训练效果。
根据本公开实施例的图像识别方法，能够准确识别图像的图像中多角度，不定字长的目标(例如车牌、广告牌、交通标识物等)。该方法利用关键点识别取代基于边界框的车牌检测，该方式不用逐像素回归，不需要检测锚，省去了非极大值抑制，极大提高了检测速度。利用关键点的热力图作为回归目标提高了定位的准确率。同时点数增加可以获取更多的车牌信息，用于单应池化校正车牌。
根据本公开实施例的图像识别方法，能够利用单应池化校正车牌图片或者特征，可以嵌入到任何网络中，从而实现端到端联合训练的统一网络，网络各部分可以联合优化，保证速度与精度。
根据本公开实施例的图像识别方法，能够应用于智慧城市、智能交通、安防监控、停车场、车辆重识别，套牌车识别等场景中，快速精准识别车牌号码，进而利用车牌号码进行收费、罚款、检测套牌车等。
可以理解，本公开提及的上述各个方法实施例，在不违背原理逻辑的情况下，均可以彼此相互结合形成结合后的实施例，限于篇幅，本公开不再赘述。本领域技术人员可以理解，在具体实施方式的上述方法中，各步骤的具体执行顺序应当以其功能和可能的内在逻辑确定。
此外，本公开还提供了图像识别装置、电子设备、计算机可读存储介质、程序，上述均可用来实现本公开提供的任一种图像识别方法，相应技术方案和描述和参见方法部分的相应记载，不再赘述。
图4示出根据本公开实施例的图像识别装置的框图，如图4所示，所述装置包括：
关键点检测模块41，用于对待处理图像进行关键点检测，确定所述待处理图像中目标区域的多个轮廓关键点信息；校正模块42，用于根据所述多个轮廓关键点信息，对所述待处理图像中的目标区域进行校正，得到与所述目标区域对应的校正区域的区域图像信息；识别模块43，用于对所述区域图像信息进行识别，得到所述目标区域的识别结果。
在一种可能的实现方式中，所述关键点检测模块包括：特征提取及融合子模块，用于对所述待处理图像进行特征提取及融合，得到所述待处理图像的特征图；检测子模块，用于对所述待处理图像的特征图进行关键点检测，得到所述待处理图像中目标区域的多个轮廓关键点信息。
在一种可能的实现方式中，所述多个轮廓关键点信息包括所述多个轮廓关键点的第一位置，所述校正模块包括：变换矩阵确定子模块，用于根据所述多个轮廓关键点的第一位置及所述校正区域的第二位置，确定所述目标区域与所述校正区域之间的单应变换矩阵；校正子模块，用于根据所述单应变换矩阵，对所述目标区域的图像或特征进行校正，得到所述校正区域的区域图像信息。
在一种可能的实现方式中，所述变换矩阵确定子模块用于：对所述第一位置与所述第二位置分别进行归一化处理，得到归一化后的第一位置和归一化后的第二位置；根据所述归一化后的第一位置和所述归一化后的第二位置，确定所述目标区域与所述校正区域之间的单应变换矩阵。
在一种可能的实现方式中，所述校正子模块用于：根据所述校正区域中多个目标点的第三位置以及所述单应变换矩阵，确定所述目标区域中与各个所述第三位置对应的像素点；将与各个所述第三位置对应的像素点的像素信息映射到各个所述目标点，并对各个所述目标点之间进行插值处理，得到所述校正区域的区域图像信息。
在一种可能的实现方式中，所述识别模块包括：对所述区域图像信息进行特征提取，得到所述区域图像信息的特征向量；对所述特征向量进行解码，得到所述目标区域的识别结果。
在一种可能的实现方式中，所述装置通过神经网络实现，所述神经网络包括目标检 测网络、校正网络及识别网络，所述目标检测网络用于对所述待处理图像进行关键点检测，所述校正网络用于对所述目标区域进行校正，所述识别网络用于对所述区域图像信息进行识别，其中，所述装置还包括：
第一训练模块，用于根据预设的训练集，训练所述目标检测网络，得到训练后的目标检测网络，所述训练集中包括多个样本图像、所述各样本图像中目标区域的轮廓关键点标注信息、背景标注信息及类别标注信息；第二训练模块，用于根据所述训练集及所述训练后的目标检测网络，训练所述校正网络及所述识别网络。
在一种可能的实现方式中，所述目标检测网络包括特征提取子网络、特征融合子网络以及检测子网络，所述第一训练模块用于：通过所述特征提取子网络对所述样本图像进行特征提取，得到所述样本图像的第一特征；通过所述特征融合子网络对所述第一特征进行特征融合，得到所述样本图像的融合特征；通过所述检测子网络对所述融合特征进行检测，得到所述样本图像中目标的轮廓关键点检测信息及背景检测信息；根据所述多个样本图像的轮廓关键点检测信息及背景检测信息，和所述多个样本图像的轮廓关键点标注信息及背景标注信息，训练所述目标检测网络，得到训练后的目标检测网络。
在一种可能的实现方式中，所述目标区域包括车辆的车牌区域，所述目标区域的识别结果包括所述车牌区域的字符类别。
在一些实施例中，本公开实施例提供的装置具有的功能或包含的模块可以用于执行上文方法实施例描述的方法，其具体实现可以参照上文方法实施例的描述，为了简洁，这里不再赘述。
本公开实施例还提出一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述方法。计算机可读存储介质可以是非易失性计算机可读存储介质或易失性计算机可读存储介质。
本公开实施例还提出一种电子设备，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为调用所述存储器存储的指令，以执行上述方法。
本公开实施例还提供了一种计算机程序产品，包括计算机可读代码，当计算机可读代码在设备上运行时，设备中的处理器执行用于实现如上任一实施例提供的图像识别方法的指令。
本公开实施例还提供了另一种计算机程序产品，用于存储计算机可读指令，指令被执行时使得计算机执行上述任一实施例提供的图像识别方法的操作。
电子设备可以被提供为终端、服务器或其它形态的设备。
图5示出根据本公开实施例的一种电子设备800的框图。例如，电子设备800可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等终端。
参照图5，电子设备800可以包括以下一个或多个组件：处理组件802，存储器804，电源组件806，多媒体组件808，音频组件810，输入/输出(I/O)的接口812，传感器组件814，以及通信组件816。
处理组件802通常控制电子设备800的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件802可以包括一个或多个处理器820来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件802可以包括一个或多个模块，便于处理组件802和其他组件之间的交互。例如，处理组件802可以包括多媒体模块，以方便多媒体组件808和处理组件802之间的交互。
存储器804被配置为存储各种类型的数据以支持在电子设备800的操作。这些数据的示例包括用于在电子设备800上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器804可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电源组件806为电子设备800的各种组件提供电力。电源组件806可以包括电源管理系统，一个或多个电源，及其他与为电子设备800生成、管理和分配电力相关联的组件。
多媒体组件808包括在所述电子设备800和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件808包括一个前置摄像头和/或后置摄像头。当电子设备800处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件810被配置为输出和/或输入音频信号。例如，音频组件810包括一个麦克风(MIC)，当电子设备800处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器804或经由通信组件816发送。在一些实施例中，音频组件810还包括一个扬声器，用于输出音频信号。
I/O接口812为处理组件802和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件814包括一个或多个传感器，用于为电子设备800提供各个方面的状态评估。例如，传感器组件814可以检测到电子设备800的打开/关闭状态，组件的相对定位，例如所述组件为电子设备800的显示器和小键盘，传感器组件814还可以检测电子设备800或电子设备800一个组件的位置改变，用户与电子设备800接触的存在或不存在，电子设备800方位或加速/减速和电子设备800的温度变化。传感器组件814可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件814还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件814还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件816被配置为便于电子设备800和其他设备之间有线或无线方式的通信。电子设备800可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信组件816经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件816还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，电子设备800可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质，例如包括计算机程序指令的存储器804，上述计算机程序指令可由电子设备800的处理器820执行以完成上述方法。
图6示出根据本公开实施例的一种电子设备1900的框图。例如，电子设备1900可以被提供为一服务器。参照图6，电子设备1900包括处理组件1922，其进一步包括一个或多个处理器，以及由存储器1932所代表的存储器资源，用于存储可由处理组件1922的执行的指令，例如应用程序。存储器1932中存储的应用程序可以包括一个或一个以上的每一个对应于一组指令的模块。此外，处理组件1922被配置为执行指令，以执行上述方法。
电子设备1900还可以包括一个电源组件1926被配置为执行电子设备1900的电源管理，一个有线或无线网络接口1950被配置为将电子设备1900连接到网络，和一个输入输出(I/O)接口1958。电子设备1900可以操作基于存储在存储器1932的操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM或类似。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质，例如包括计算机程序指令的存储器1932，上述计算机程序指令可由电子设备1900的处理组件1922执行以 完成上述方法。
本公开可以是系统、方法和/或计算机程序产品。计算机程序产品可以包括计算机可读存储介质，其上载有用于使处理器实现本公开的各个方面的计算机可读程序指令。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计算机可读存储介质例如可以是――但不限于――电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(SRAM)、便携式压缩盘只读存储器(CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过电线传输的电信号。
这里所描述的计算机可读程序指令可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。
用于执行本公开操作的计算机程序指令可以是汇编指令、指令集架构(ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，所述编程语言包括面向对象的编程语言—诸如Smalltalk、C++等，以及常规的过程式编程语言—诸如“C”语言或类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、现场可编程门阵列(FPGA)或可编程逻辑阵列(PLA)，该电子电路可以执行计算机可读程序指令，从而实现本公开的各个方面。
这里参照根据本公开实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/ 或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其它可编程数据处理装置的处理器，从而生产出一种机器，使得这些指令在通过计算机或其它可编程数据处理装置的处理器执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上，使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本公开的多个实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，所述模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
该计算机程序产品可以具体通过硬件、软件或其结合的方式实现。在一个可选实施例中，所述计算机程序产品具体体现为计算机存储介质，在另一个可选实施例中，计算机程序产品具体体现为软件产品，例如软件开发包(Software Development Kit，SDK)等等。
在不违背逻辑的情况下，本公开不同实施例之间可以相互结合，不同实施例描述有所侧重，为侧重描述的部分可以参见其他实施例的记载。
以上已经描述了本公开的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中的技术的改进，或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。

Claims (13)

  1. 一种图像识别方法，其特征在于，包括：
    对待处理图像进行关键点检测，确定所述待处理图像中目标区域的多个轮廓关键点信息；
    根据所述多个轮廓关键点信息，对所述待处理图像中的目标区域进行校正，得到与所述目标区域对应的校正区域的区域图像信息；
    对所述区域图像信息进行识别，得到所述目标区域的识别结果。
  2. 根据权利要求1所述的方法，其特征在于，所述对待处理图像进行关键点检测，确定所述待处理图像中目标区域的多个轮廓关键点信息，包括：
    对所述待处理图像进行特征提取及融合，得到所述待处理图像的特征图；
    对所述待处理图像的特征图进行关键点检测，得到所述待处理图像中目标区域的多个轮廓关键点信息。
  3. 根据权利要求1或2所述的方法，其特征在于，所述多个轮廓关键点信息包括所述多个轮廓关键点的第一位置，所述根据所述多个轮廓关键点信息，对所述待处理图像中的目标区域进行校正，得到与所述目标区域对应的校正区域的区域图像信息，包括：
    根据所述多个轮廓关键点的第一位置及所述校正区域的第二位置，确定所述目标区域与所述校正区域之间的单应变换矩阵；
    根据所述单应变换矩阵，对所述目标区域的图像或特征进行校正，得到所述校正区域的区域图像信息。
  4. 根据权利要求3所述的方法，其特征在于，所述根据所述多个轮廓关键点的第一位置及所述校正区域的第二位置，确定所述目标区域与所述校正区域之间的单应变换矩阵，包括：
    对所述第一位置与所述第二位置分别进行归一化处理，得到归一化后的第一位置和归一化后的第二位置；
    根据所述归一化后的第一位置和所述归一化后的第二位置，确定所述目标区域与所述校正区域之间的单应变换矩阵。
  5. 根据权利要求3或4所述的方法，其特征在于，所述根据所述单应变换矩阵，对所述目标区域的图像进行校正，得到所述校正区域的区域图像信息，包括：
    根据所述校正区域中多个目标点的第三位置以及所述单应变换矩阵，确定所述目标区域中与各个所述第三位置对应的像素点；
    将与各个所述第三位置对应的像素点的像素信息映射到各个所述目标点，并对各个所述目标点之间进行插值处理，得到所述校正区域的区域图像信息。
  6. 根据权利要求1-5中任意一项所述的方法，其特征在于，所述对所述区域图像信息进行识别，得到所述目标区域的识别结果，包括：
    对所述区域图像信息进行特征提取，得到所述区域图像信息的特征向量；
    对所述特征向量进行解码，得到所述目标区域的识别结果。
  7. 根据权利要求1-6中任意一项所述的方法，其特征在于，所述方法通过神经网络实现，所述神经网络包括目标检测网络、校正网络及识别网络，所述目标检测网络用于对所述待处理图像进行关键点检测，所述校正网络用于对所述目标区域进行校正，所述识别网络用于对所述区域图像信息进行识别，
    其中，所述方法还包括：
    根据预设的训练集，训练所述目标检测网络，得到训练后的目标检测网络，所述训练集中包括多个样本图像、各所述样本图像中目标区域的轮廓关键点标注信息、背景标注信息及类别标注信息；
    根据所述训练集及所述训练后的目标检测网络，训练所述校正网络及所述识别网络。
  8. 根据权利要求7所述的方法，其特征在于，所述目标检测网络包括特征提取子网络、特征融合子网络以及检测子网络，
    所述根据预设的训练集，训练所述目标检测网络，得到训练后的目标检测网络，包括：
    通过所述特征提取子网络对所述样本图像进行特征提取，得到所述样本图像的第一特征；
    通过所述特征融合子网络对所述第一特征进行特征融合，得到所述样本图像的融合特征；
    通过所述检测子网络对所述融合特征进行检测，得到所述样本图像中目标的轮廓关键点检测信息及背景检测信息；
    根据所述多个样本图像的轮廓关键点检测信息及背景检测信息，和所述多个样本图像的轮廓关键点标注信息及背景标注信息，训练所述目标检测网络，得到训练后的目标检测网络。
  9. 根据权利要求1-8中任意一项所述的方法，其特征在于，所述目标区域包括车辆 的车牌区域，所述目标区域的识别结果包括所述车牌区域的字符类别。
  10. 一种图像识别装置，其特征在于，包括：
    关键点检测模块，用于对待处理图像进行关键点检测，确定所述待处理图像中目标区域的多个轮廓关键点信息；
    校正模块，用于根据所述多个轮廓关键点信息，对所述待处理图像中的目标区域进行校正，得到与所述目标区域对应的校正区域的区域图像信息；
    识别模块，用于对所述区域图像信息进行识别，得到所述目标区域的识别结果。
  11. 一种电子设备，其特征在于，包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器被配置为调用所述存储器存储的指令，以执行权利要求1至9中任意一项所述的方法。
  12. 一种计算机可读存储介质，其上存储有计算机程序指令，其特征在于，所述计算机程序指令被处理器执行时实现权利要求1至9中任意一项所述的方法。
  13. 一种计算机程序，其特征在于，所述计算机程序包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行用于实现权利要求1至9中任意一项所述的方法。
PCT/CN2020/081371 2020-02-12 2020-03-26 图像识别方法及装置、电子设备和存储介质 WO2021159594A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2021536000A JP2022522596A (ja) 2020-02-12 2020-03-26 画像識別方法及び装置、電子機器並びに記憶媒体
SG11202106622XA SG11202106622XA (en) 2020-02-12 2020-03-26 Image recognition method and apparatus, electronic device and storage medium
US17/353,045 US20210312214A1 (en) 2020-02-12 2021-06-21 Image recognition method, apparatus and non-transitory computer readable storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010089651.8 2020-02-12
CN202010089651.8A CN111339846B (zh) 2020-02-12 2020-02-12 图像识别方法及装置、电子设备和存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/353,045 Continuation US20210312214A1 (en) 2020-02-12 2021-06-21 Image recognition method, apparatus and non-transitory computer readable storage medium

Publications (1)

Publication Number Publication Date
WO2021159594A1 true WO2021159594A1 (zh) 2021-08-19

Family

ID=71183387

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/081371 WO2021159594A1 (zh) 2020-02-12 2020-03-26 图像识别方法及装置、电子设备和存储介质

Country Status (6)

Country Link
US (1) US20210312214A1 (zh)
JP (1) JP2022522596A (zh)
CN (1) CN111339846B (zh)
SG (1) SG11202106622XA (zh)
TW (1) TW202131219A (zh)
WO (1) WO2021159594A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115661577A (zh) * 2022-11-01 2023-01-31 吉咖智能机器人有限公司 用于对象检测的方法、设备和计算机可读存储介质
CN116958954A (zh) * 2023-07-27 2023-10-27 匀熵智能科技(无锡)有限公司 基于关键点与旁路矫正的车牌识别方法、装置及存储介质

Families Citing this family (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111768394A (zh) * 2020-07-01 2020-10-13 上海商汤智能科技有限公司 图像处理方法及装置、电子设备和存储介质
CN111753854B (zh) * 2020-07-28 2023-12-22 腾讯医疗健康(深圳)有限公司 图像处理方法、装置、电子设备及存储介质
CN112069901B (zh) * 2020-08-06 2022-07-08 南京领行科技股份有限公司 车内物品监控方法、电子设备及存储介质
CN111950547A (zh) * 2020-08-06 2020-11-17 广东飞翔云计算有限公司 一种车牌的检测方法、装置、计算机设备和存储介质
CN111898171A (zh) * 2020-08-11 2020-11-06 上海控软网络科技有限公司 余料的加工图纸确定方法、装置、电子设备及存储介质
CN111985556A (zh) * 2020-08-19 2020-11-24 南京地平线机器人技术有限公司 关键点识别模型的生成方法和关键点识别方法
CN112200765B (zh) * 2020-09-04 2024-05-14 浙江大华技术股份有限公司 车辆中被误检的关键点的确定方法及装置
CN112101183B (zh) * 2020-09-10 2021-08-24 深圳市商汤科技有限公司 车辆识别方法及装置、电子设备及存储介质
CN114169952A (zh) * 2020-09-11 2022-03-11 京东方科技集团股份有限公司 一种商品推荐方法、服务器、购物车和购物系统
CN112291445B (zh) * 2020-10-28 2023-04-25 北京字节跳动网络技术有限公司 图像处理的方法、装置、设备和存储介质
CN112364807B (zh) * 2020-11-24 2023-12-15 深圳市优必选科技股份有限公司 图像识别方法、装置、终端设备及计算机可读存储介质
CN112541500B (zh) * 2020-12-03 2023-07-25 北京智芯原动科技有限公司 一种端到端的车牌识别方法及装置
CN112989910A (zh) * 2020-12-12 2021-06-18 南方电网调峰调频发电有限公司 电力目标检测方法、装置、计算机设备和存储介质
CN114283305A (zh) * 2020-12-25 2022-04-05 上海商汤智能科技有限公司 图像检测方法及装置、电子设备和存储介质
CN112700464B (zh) * 2021-01-15 2022-03-29 腾讯科技（深圳）有限公司 地图信息的处理方法、装置、电子设备以及存储介质
CN112906708B (zh) * 2021-03-29 2023-10-24 北京世纪好未来教育科技有限公司 一种图片处理方法、装置、电子设备和计算机存储介质
CN113128407A (zh) * 2021-04-21 2021-07-16 湖北微果网络科技有限公司 扫描识物方法、系统、计算机设备及存储介质
TWI784720B (zh) * 2021-09-17 2022-11-21 英業達股份有限公司 基於電腦視覺的電磁敏感性測試方法
CN113919499A (zh) * 2021-11-24 2022-01-11 威盛电子股份有限公司 模型训练方法与模型训练系统
TWI805485B (zh) * 2021-12-20 2023-06-11 財團法人工業技術研究院 影像辨識的方法及其電子裝置
CN114387436B (zh) * 2021-12-28 2022-10-25 北京安德医智科技有限公司 壁冠状动脉检测方法及装置、电子设备和存储介质
EP4330935A1 (en) * 2021-12-29 2024-03-06 Shanghai United Imaging Healthcare Co., Ltd. Systems and methods for medical imaging
CN114359911B (zh) * 2022-03-18 2022-07-26 北京亮亮视野科技有限公司 文字关键信息的提取方法及装置
CN115375917B (zh) * 2022-10-25 2023-03-24 杭州华橙软件技术有限公司 一种目标边缘特征提取方法、装置、终端及存储介质
TWI814623B (zh) * 2022-10-26 2023-09-01 鴻海精密工業股份有限公司 圖像識別方法、電腦設備及儲存介質
CN115631465B (zh) * 2022-12-22 2023-03-28 中关村科学城城市大脑股份有限公司 重点人群风险感知方法、装置、电子设备和可读介质
TWI832642B (zh) * 2022-12-28 2024-02-11 國立中央大學 應用於穩定性招牌之偵測與辨識之影像處理方法
CN116935179B (zh) * 2023-09-14 2023-12-08 海信集团控股股份有限公司 一种目标检测方法、装置、电子设备及存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130329961A1 (en) * 2012-06-12 2013-12-12 Xerox Corporation Geometric pre-correction for automatic license plate recognition
CN110163199A (zh) * 2018-09-30 2019-08-23 腾讯科技（深圳）有限公司 车牌识别方法、车牌识别装置、车牌识别设备及介质
CN110728283A (zh) * 2019-10-11 2020-01-24 高新兴科技集团股份有限公司 一种车牌类型识别方法及设备

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5164222B2 (ja) * 2009-06-25 2013-03-21 Ｋｄｄｉ株式会社 画像検索方法およびシステム
CN106250894B (zh) * 2016-07-26 2021-10-26 北京小米移动软件有限公司 卡片信息识别方法及装置
CN108133220A (zh) * 2016-11-30 2018-06-08 北京市商汤科技开发有限公司 模型训练、关键点定位及图像处理方法、系统及电子设备
CN107742120A (zh) * 2017-10-17 2018-02-27 北京小米移动软件有限公司 银行卡卡号的识别方法及装置
CN108460411B (zh) * 2018-02-09 2021-05-04 北京市商汤科技开发有限公司 实例分割方法和装置、电子设备、程序和介质
WO2019169532A1 (zh) * 2018-03-05 2019-09-12 深圳前海达闼云端智能科技有限公司 车牌识别方法及云系统
CN109522910B (zh) * 2018-12-25 2020-12-11 浙江商汤科技开发有限公司 关键点检测方法及装置、电子设备和存储介质
CN110781813B (zh) * 2019-10-24 2023-04-07 北京市商汤科技开发有限公司 图像识别方法及装置、电子设备和存储介质

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130329961A1 (en) * 2012-06-12 2013-12-12 Xerox Corporation Geometric pre-correction for automatic license plate recognition
CN110163199A (zh) * 2018-09-30 2019-08-23 腾讯科技（深圳）有限公司 车牌识别方法、车牌识别装置、车牌识别设备及介质
CN110728283A (zh) * 2019-10-11 2020-01-24 高新兴科技集团股份有限公司 一种车牌类型识别方法及设备

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115661577A (zh) * 2022-11-01 2023-01-31 吉咖智能机器人有限公司 用于对象检测的方法、设备和计算机可读存储介质
CN115661577B (zh) * 2022-11-01 2024-04-16 吉咖智能机器人有限公司 用于对象检测的方法、设备和计算机可读存储介质
CN116958954A (zh) * 2023-07-27 2023-10-27 匀熵智能科技(无锡)有限公司 基于关键点与旁路矫正的车牌识别方法、装置及存储介质
CN116958954B (zh) * 2023-07-27 2024-03-22 匀熵智能科技(无锡)有限公司 基于关键点与旁路矫正的车牌识别方法、装置及存储介质

Also Published As

Publication number Publication date
TW202131219A (zh) 2021-08-16
JP2022522596A (ja) 2022-04-20
CN111339846B (zh) 2022-08-12
SG11202106622XA (en) 2021-09-29
US20210312214A1 (en) 2021-10-07
CN111339846A (zh) 2020-06-26

Similar Documents

Publication Publication Date Title
WO2021159594A1 (zh) 图像识别方法及装置、电子设备和存储介质
TWI749423B (zh) 圖像處理方法及裝置、電子設備和電腦可讀儲存介質
TWI728621B (zh) 圖像處理方法及其裝置、電子設備、電腦可讀儲存媒體和電腦程式
TWI740309B (zh) 圖像處理方法及裝置、電子設備和電腦可讀儲存介質
TWI747325B (zh) 目標對象匹配方法及目標對象匹配裝置、電子設備和電腦可讀儲存媒介
US11301726B2 (en) Anchor determination method and apparatus, electronic device, and storage medium
JP6392468B2 (ja) 領域認識方法及び装置
TWI702544B (zh) 圖像處理方法、電子設備和電腦可讀儲存介質
EP3099075B1 (en) Method and device for processing identification of video file
CN111104920B (zh) 视频处理方法及装置、电子设备和存储介质
CN110569835B (zh) 一种图像识别方法、装置和电子设备
WO2020220807A1 (zh) 图像生成方法及装置、电子设备及存储介质
CN111126108A (zh) 图像检测模型的训练和图像检测方法及装置
CN111680646B (zh) 动作检测方法及装置、电子设备和存储介质
WO2022141969A1 (zh) 图像分割方法及装置、电子设备、存储介质和程序
WO2022099988A1 (zh) 目标跟踪方法及装置、电子设备和存储介质
CN112990197A (zh) 车牌识别方法及装置、电子设备和存储介质
CN109889693B (zh) 视频处理方法及装置、电子设备和存储介质
CN113705447A (zh) 画面显示方法及装置、电子设备和存储介质

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2021536000

Country of ref document: JP

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20919160

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 13.12.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 20919160

Country of ref document: EP

Kind code of ref document: A1