CN112906574B - Dynamic threshold management method and system - Google Patents
Dynamic threshold management method and system Download PDFInfo
- Publication number
- CN112906574B CN112906574B CN202110195658.2A CN202110195658A CN112906574B CN 112906574 B CN112906574 B CN 112906574B CN 202110195658 A CN202110195658 A CN 202110195658A CN 112906574 B CN112906574 B CN 112906574B
- Authority
- CN
- China
- Prior art keywords
- comparison
- target object
- threshold
- image processing
- distribution result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a dynamic threshold management method and a system, wherein the method comprises the following steps: obtaining a comparison score distribution result through similarity comparison of the face images; and dynamically adjusting the comparison threshold value of the image processing equipment or each target object according to the comparison score distribution result. In order to overcome the influence of actual working conditions such as application environment, application equipment, quality of an underlying library and the like on the passing rate and the false recognition rate, the comparison threshold value of the image processing equipment or each target object is dynamically adjusted according to the distribution rule of the comparison score distribution result of the target object which is the user or is not the user, and the higher passing rate and the lower false recognition rate are guaranteed.
Description
The present application is a divisional application of a patent application having an application date of 16/07/2020 and an application number of 202010683491X entitled "a dynamic threshold management method, system, device, and medium".
Technical Field
The present invention relates to image recognition technologies, and in particular, to a dynamic threshold management method and system.
Background
In the process of face recognition, the selection of the judgment threshold of face recognition is particularly critical, and in the prior art, face recognition is performed by setting a static threshold, which may cause that: the higher the threshold value is, the lower the passing rate and the false recognition rate are; the lower the threshold, the higher the passage rate and the misrecognition rate.
In the delivery process of the face recognition device, because experience deviation of different delivery personnel and the environment of a delivery site are complex and changeable, the work difficulty of debugging the threshold value according to experience and the condition of the delivery site is serious, on one hand, a large amount of time of the delivery personnel can be wasted, and on the other hand, the identification accuracy is influenced because the passing rate and the false recognition rate are too high or too low due to the fact that a proper threshold value is not adjusted at the beginning.
Disclosure of Invention
In view of the above drawbacks of the prior art, an object of the present invention is to provide a dynamic threshold management method and system, which are used to solve the problem that the false recognition rate and the passing rate are not ideal due to setting a static threshold for face recognition in the prior art.
To achieve the above and other related objects, the present invention provides a dynamic threshold management method, including:
obtaining a comparison score distribution result through similarity comparison of the face images;
and dynamically adjusting the comparison threshold value of the image processing equipment or each target object according to the comparison score distribution result.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result includes:
and acquiring the maximum value of the non-personal comparison score according to the comparison score distribution result, and taking the maximum value of the non-personal comparison score as a comparison threshold of the image processing equipment or each target object.
Optionally, after the step of obtaining a comparison score distribution result through similarity comparison of face images, the method further includes:
and judging the waveform of the comparison score distribution result, and skipping the dynamic adjustment of the image processing equipment or the comparison threshold of each target object if the waveform is three peaks or more.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
judging the waveform of the comparison score distribution result, if the waveform is a double-peak, acquiring the maximum value of the comparison score in the first waveform and taking the maximum value of the non-personal comparison score as the comparison threshold of the image processing equipment or each target object, wherein the first waveform is the waveform with a smaller comparison score.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
judging the waveform of the comparison score distribution result, and if the waveform is a single peak, determining the mean value of the comparison score distribution result of the waveform;
and if the mean value of the comparison score distribution results is smaller than a preset threshold value, acquiring the maximum value of the comparison scores in the waveform and taking the maximum value of the non-personal comparison scores as the comparison threshold value of the image processing equipment or each target object.
Optionally, the step of determining the mean of the comparison score distribution result of the waveform includes:
and fitting the comparison score distribution result through a normal distribution curve algorithm, and determining the mean value of the comparison score distribution result.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
recording comparison threshold values of the image processing equipment or each target object;
acquiring a comparison threshold value of the current image processing equipment or each target object according to the comparison score distribution result;
comparing the current comparison threshold with the recorded comparison threshold, and taking the larger value as an updated comparison threshold;
and according to the updated comparison threshold, dynamically adjusting the comparison threshold of the image processing equipment or each target object.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
and traversing a base library of the image processing equipment, if no face image of the target object exists, acquiring the maximum value of the non-personal comparison score, and taking the maximum value of the non-personal comparison score as a comparison threshold of the image processing equipment.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
and traversing each target object, acquiring the maximum value of the non-personal comparison scores of the corresponding target object, and taking the maximum value of the non-personal comparison scores as the comparison threshold of the target object.
A dynamic threshold management system, comprising:
the acquisition module is used for acquiring a comparison score distribution result through similarity comparison of the face images;
and the adjusting module is used for dynamically adjusting the comparison threshold of the image processing equipment or each target object according to the comparison score distribution result.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result includes:
and acquiring the maximum value of the non-personal comparison score according to the comparison score distribution result, and taking the maximum value of the non-personal comparison score as a comparison threshold of the image processing equipment or each target object.
Optionally, after the step of obtaining a comparison score distribution result through similarity comparison of face images, the method further includes:
and judging the waveform of the comparison score distribution result, and skipping the dynamic adjustment of the image processing equipment or the comparison threshold of each target object if the waveform is three peaks or more.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
judging the waveform of the comparison score distribution result, if the waveform is a double-peak, acquiring the maximum value of the comparison score in the first waveform and taking the maximum value of the non-personal comparison score as the comparison threshold of the image processing equipment or each target object, wherein the first waveform is the waveform with a smaller comparison score.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
judging the waveform of the comparison score distribution result, and if the waveform is a single peak, determining the mean value of the comparison score distribution result of the waveform;
and if the mean value of the comparison score distribution results is smaller than a preset threshold value, acquiring the maximum value of the comparison scores in the waveform and taking the maximum value of the non-personal comparison scores as the comparison threshold value of the image processing equipment or each target object.
Optionally, the step of determining the mean of the comparison score distribution result of the waveform includes:
and fitting the comparison score distribution result through a normal distribution curve algorithm, and determining the mean value of the comparison score distribution result.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
recording comparison threshold values of the image processing equipment or each target object;
acquiring a comparison threshold value of the current image processing equipment or each target object according to the comparison score distribution result;
comparing the current comparison threshold with the recorded comparison threshold, and taking the larger value as an updated comparison threshold;
and according to the updated comparison threshold, dynamically adjusting the comparison threshold of the image processing equipment or each target object.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
and traversing a base library of the image processing equipment, if no face image of the target object exists, acquiring the maximum value of the non-personal comparison score, and taking the maximum value of the non-personal comparison score as a comparison threshold of the image processing equipment.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
and traversing each target object, acquiring the maximum value of the non-personal comparison scores of the corresponding target object, and taking the maximum value of the non-personal comparison scores as the comparison threshold of the target object.
An apparatus, comprising:
one or more processors; and
one or more machine-readable media having instructions stored thereon that, when executed by the one or more processors, cause the apparatus to perform one or more of the methods described.
One or more machine-readable media having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform one or more of the described methods.
As described above, the dynamic threshold management method and system provided by the present invention have the following beneficial effects:
in order to overcome the influence of actual working conditions such as application environment, application equipment, quality of an underlying library and the like on the passing rate and the false recognition rate, the comparison threshold value of the image processing equipment or each target object is dynamically adjusted according to the distribution rule of the comparison score distribution result of the target object which is the user or is not the user, and the higher passing rate and the lower false recognition rate are guaranteed.
Drawings
Fig. 1 is a flowchart illustrating a dynamic threshold management method according to an embodiment of the present invention.
Fig. 2 is a diagram illustrating a waveform of the result of the binary distribution as a double peak.
Fig. 3 is a diagram illustrating a waveform of the result of the binary distribution as a single peak.
FIG. 4 is a graph showing the maximum value of the non-self alignment score in FIG. 3.
Fig. 5 is a schematic flow chart of S2 according to another embodiment of the present invention.
Fig. 6 is a schematic structural diagram of a dynamic threshold management system according to an embodiment of the present invention.
Fig. 7 is a schematic diagram of a hardware structure of a terminal device according to an embodiment.
Fig. 8 is a schematic diagram of a hardware structure of a terminal device according to another embodiment.
Description of the element reference numerals
1100 input device
1101 first processor
1102 output device
1103 first memory
1104 communication bus
1200 processing assembly
1201 second processor
1202 second memory
1203 communication assembly
1204 Power supply Assembly
1205 multimedia assembly
1206 voice assembly
1207 input/output interface
1208 sensor assembly
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
The inventor finds that: setting a static threshold for face recognition may cause: the higher the threshold value is, the lower the passing rate and the false recognition rate are; the lower the threshold is, the higher the passing rate and the false positive rate are, and further the requirements of the passing rate and the false positive rate cannot be considered well, so the invention provides a dynamic threshold management method, please refer to fig. 1, the method includes:
s1: obtaining a comparison score distribution result through similarity comparison of the face images; for example, the light, the angle, the quality of the background library and the like of different image processing devices can influence the identification of the target object, the similarity of face images can be collected and processed through the image processing devices, corresponding comparison score distribution results are obtained, the characteristics displayed by the comparison score distribution results can show that the target object is the person or the non-person, and further, the more ideal high passing rate and low false recognition rate are achieved by mastering the distribution rule of the comparison score distribution results of the target object which is the person or the non-person;
s2: according to the comparison score distribution result, the comparison threshold of the image processing equipment or each target object is dynamically adjusted, in order to overcome the influence of actual working conditions such as application environment, application equipment and base quality on the passing rate and the false recognition rate, the comparison threshold of the image processing equipment or each target object is dynamically adjusted according to the distribution rule of the comparison score distribution result of the target object, namely the user or the non-user, and higher passing rate and lower false recognition rate are guaranteed.
In some implementations, the step S2 of dynamically adjusting the alignment threshold of the image processing apparatus or each target object according to the alignment score distribution result includes:
according to the comparison score distribution result, the non-personal comparison score and the personal comparison score in the comparison score distribution result are determined, the maximum value of the non-personal comparison score is obtained, the maximum value of the non-personal comparison score is used as the comparison threshold value of the image processing equipment or each target object, whether the face image of the target object is the person can be accurately and efficiently distinguished, the identification efficiency and the passing rate are improved, and the false identification rate is reduced.
In some implementations, after the step of S1 of obtaining a comparison score distribution result through similarity comparison of face images, the method further includes:
and judging the waveform of the comparison score distribution result, and skipping the dynamic adjustment of the image processing equipment or the comparison threshold of each target object if the waveform is three peaks or more. When three peaks and a plurality of peaks above the three peaks occur in the comparison process of the similarity, the distribution rule of the comparison score distribution result cannot well distinguish the user or the non-user, that is, whether the target object exists in the base or not cannot be judged through the peaks and the comparison score distribution result, and therefore the comparison threshold of the set image processing device or the set target object is not adjusted under the condition, so that the comparison threshold is not adjusted, and the passing rate and the recognition rate are not affected.
In some implementations, the step S2 of dynamically adjusting the alignment threshold of the image processing apparatus or each target object according to the alignment score distribution result further includes:
judging the waveform of the comparison score distribution result, if the waveform is a double-peak, obtaining the maximum value of the comparison score in the first waveform and taking the maximum value of the non-personal comparison score as the comparison threshold of the image processing device or each target object, wherein the first waveform is a waveform with a smaller comparison score, please refer to fig. 2. When the waveform of the comparison score distribution result is a double-wave peak, the comparison score distribution result is obvious in personal distribution and non-personal distribution, the maximum value of the comparison score in the non-personal distribution is selected as the comparison threshold, the comparison score and the comparison threshold can be reduced under the condition that low false recognition rate is fully guaranteed, and the passing rate is greatly improved.
In some implementations, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
judging the waveform of the comparison score distribution result, and if the waveform is a single peak, determining the mean value of the comparison score distribution result of the waveform;
if the mean value of the comparison score distribution result is smaller than the preset threshold (for example, the preset threshold may be set to 60, or may be set to 50 or 70 according to the requirements of the passing rate and the false recognition rate), please refer to fig. 3, in some implementation processes, the comparison score distribution result is fitted by a normal distribution curve algorithm, and the mean value μ of the comparison score distribution result is determined, it can be considered that the target object is a non-self, that is, the human face photograph of the target object does not exist in the base library at this time, the maximum value of the comparison score in the waveform is obtained and is used as the maximum value of the non-self comparison score, please refer to fig. 4, the maximum value of the non-self comparison score is used as the comparison threshold of the image processing device or each target object, and further, when a new target object of the face image does not exist in the base library, the maximum value of the current non-self comparison score is compared with the maximum value of the previous round, if the maximum value of the current round is larger than the maximum value of the previous round, the maximum value of the current round is saved and set as a comparison threshold value.
In order to facilitate dynamic setting and adjustment of the comparison threshold, referring to fig. 5, in some implementations, the step of dynamically adjusting the comparison threshold S2 of the image processing apparatus or each target object according to the comparison score distribution result further includes:
s21: recording comparison threshold values of the image processing equipment or each target object, for example, comparing the similarity of each facial image for recording, recording the ID of the target object, the ID of the image processing equipment, the ID of the delivery site, the comparison score and the snapshot time, accessing the 5 fields into a MySQL database with a dynamic threshold value, and traversing the record through each target object in the base by an algorithm;
s22: acquiring a comparison threshold value of the current image processing equipment or each target object according to the comparison score distribution result;
s23: comparing the current comparison threshold with the recorded comparison threshold, and taking the larger value as an updated comparison threshold;
s24: and according to the updated comparison threshold, dynamically adjusting the comparison threshold of the image processing equipment or each target object. In the dynamic process of face recognition, the current comparison threshold value and the recorded comparison threshold value are continuously compared and updated, and in order to reduce the false recognition rate, the larger value of the current comparison threshold value and the recorded comparison threshold value is taken as the updated comparison threshold value so as to adapt to different actual application environments and working condition requirements.
In some implementations, the step of dynamically adjusting the comparison threshold S2 of the image processing apparatus or each target object according to the comparison score distribution result further includes:
traversing a base library of the image processing equipment, if no face image of the target object exists, acquiring the maximum value of the non-personal comparison score, and taking the maximum value of the non-personal comparison score as a comparison threshold of the image processing equipment, so that the image processing equipment is conveniently applied to an actual or dynamic application scene, and a higher passing rate and a lower false recognition rate are ensured;
or traversing each target object, acquiring the maximum value of the non-personal comparison scores of the corresponding target objects, and taking the maximum value of the non-personal comparison scores as the comparison threshold of the target objects, so that the corresponding comparison threshold is set for each target object conveniently, and the method is applied to actual or dynamic application scenes to ensure higher passing rate and lower false recognition rate.
Referring to fig. 6, the present invention further provides a dynamic threshold management system, including:
the acquisition module 10 is used for obtaining a comparison score distribution result through similarity comparison of the face images;
and the adjusting module 20 is configured to dynamically adjust the comparison threshold of the image processing device or each target object according to the comparison score distribution result. In order to overcome the influence of actual working conditions such as application environment, application equipment, quality of an underlying library and the like on the passing rate and the false recognition rate, the comparison threshold value of the image processing equipment or each target object is dynamically adjusted according to the distribution rule of the comparison score distribution result of the target object which is the user or is not the user, and the higher passing rate and the lower false recognition rate are guaranteed.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result includes:
and acquiring the maximum value of the non-personal comparison score according to the comparison score distribution result, and taking the maximum value of the non-personal comparison score as a comparison threshold of the image processing equipment or each target object.
Optionally, after the step of obtaining a comparison score distribution result through similarity comparison of face images, the method further includes:
and judging the waveform of the comparison score distribution result, and skipping the dynamic adjustment of the image processing equipment or the comparison threshold of each target object if the waveform is three peaks or more.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
judging the waveform of the comparison score distribution result, if the waveform is a double-peak, acquiring the maximum value of the comparison score in the first waveform and taking the maximum value of the non-personal comparison score as the comparison threshold of the image processing equipment or each target object, wherein the first waveform is the waveform with a smaller comparison score.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
judging the waveform of the comparison score distribution result, and if the waveform is a single peak, determining the mean value of the comparison score distribution result of the waveform;
and if the mean value of the comparison score distribution results is smaller than a preset threshold value, acquiring the maximum value of the comparison scores in the waveform and taking the maximum value of the non-personal comparison scores as the comparison threshold value of the image processing equipment or each target object.
Optionally, the step of determining the mean of the comparison score distribution result of the waveform includes:
and fitting the comparison score distribution result through a normal distribution curve algorithm, and determining the mean value of the comparison score distribution result.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
recording comparison threshold values of the image processing equipment or each target object;
acquiring a comparison threshold value of the current image processing equipment or each target object according to the comparison score distribution result;
comparing the current comparison threshold with the recorded comparison threshold, and taking the larger value as an updated comparison threshold;
and according to the updated comparison threshold, dynamically adjusting the comparison threshold of the image processing equipment or each target object.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
and traversing a base library of the image processing equipment, if no face image of the target object exists, acquiring the maximum value of the non-personal comparison score, and taking the maximum value of the non-personal comparison score as a comparison threshold of the image processing equipment.
Optionally, the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further includes:
and traversing each target object, acquiring the maximum value of the non-personal comparison scores of the corresponding target object, and taking the maximum value of the non-personal comparison scores as the comparison threshold of the target object.
The present invention provides an apparatus comprising: one or more processors; and one or more machine readable media having instructions stored thereon that, when executed by the one or more processors, cause the apparatus to perform one or more of the methods described.
The present disclosure provides one or more machine-readable media having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform one or more of the described methods.
An embodiment of the present application further provides an apparatus, which may include: one or more processors; and one or more machine readable media having instructions stored thereon that, when executed by the one or more processors, cause the apparatus to perform the method of fig. 1. In practical applications, the device may be used as a terminal device, and may also be used as a server, where examples of the terminal device may include: the mobile terminal includes a smart phone, a tablet computer, an electronic book reader, an MP3 (Moving Picture Experts Group Audio Layer III) player, an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop, a vehicle-mounted computer, a desktop computer, a set-top box, an intelligent television, a wearable device, and the like.
The present embodiment also provides a non-volatile readable storage medium, where one or more modules (programs) are stored in the storage medium, and when the one or more modules are applied to a device, the device may execute instructions (instructions) included in the data processing method in fig. 4 according to the present embodiment.
Fig. 7 is a schematic diagram of a hardware structure of a terminal device according to an embodiment of the present application. As shown, the terminal device may include: an input device 1100, a first processor 1101, an output device 1102, a first memory 1103, and at least one communication bus 1104. The communication bus 1104 is used to implement communication connections between the elements. The first memory 1103 may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and the first memory 1103 may store various programs for performing various processing functions and implementing the method steps of the present embodiment.
Alternatively, the first processor 1101 may be, for example, a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components, and the first processor 1101 is coupled to the input device 1100 and the output device 1102 through a wired or wireless connection.
Optionally, the input device 1100 may include a variety of input devices, such as at least one of a user-oriented user interface, a device-oriented device interface, a software programmable interface, a camera, and a sensor. Optionally, the device interface facing the device may be a wired interface for data transmission between devices, or may be a hardware plug-in interface (e.g., a USB interface, a serial port, etc.) for data transmission between devices; optionally, the user-facing user interface may be, for example, a user-facing control key, a voice input device for receiving voice input, and a touch sensing device (e.g., a touch screen with a touch sensing function, a touch pad, etc.) for receiving user touch input; optionally, the programmable interface of the software may be, for example, an entry for a user to edit or modify a program, such as an input pin interface or an input interface of a chip; the output devices 1102 may include output devices such as a display, audio, and the like.
In this embodiment, the processor of the terminal device includes a function for executing each module of the speech recognition apparatus in each device, and specific functions and technical effects may refer to the above embodiments, which are not described herein again.
Fig. 8 is a schematic hardware structure diagram of a terminal device according to an embodiment of the present application. FIG. 8 is a specific embodiment of FIG. 7 in an implementation. As shown, the terminal device of the present embodiment may include a second processor 1201 and a second memory 1202.
The second processor 1201 executes the computer program code stored in the second memory 1202 to implement the method described in fig. 4 in the above embodiment.
The second memory 1202 is configured to store various types of data to support operations at the terminal device. Examples of such data include instructions for any application or method operating on the terminal device, such as messages, pictures, videos, and so forth. The second memory 1202 may include a Random Access Memory (RAM) and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.
Optionally, a second processor 1201 is provided in the processing assembly 1200. The terminal device may further include: communication component 1203, power component 1204, multimedia component 1205, speech component 1206, input/output interfaces 1207, and/or sensor component 1208. The specific components included in the terminal device are set according to actual requirements, which is not limited in this embodiment.
The processing component 1200 generally controls the overall operation of the terminal device. The processing assembly 1200 may include one or more second processors 1201 to execute instructions to perform all or part of the steps of the data processing method described above. Further, the processing component 1200 can include one or more modules that facilitate interaction between the processing component 1200 and other components. For example, the processing component 1200 can include a multimedia module to facilitate interaction between the multimedia component 1205 and the processing component 1200.
The power supply component 1204 provides power to the various components of the terminal device. The power components 1204 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the terminal device.
The multimedia components 1205 include a display screen that provides an output interface between the terminal device and the user. In some embodiments, the display screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the display screen includes a touch panel, the display screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, 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 associated with the touch or slide operation.
The voice component 1206 is configured to output and/or input voice signals. For example, the voice component 1206 includes a Microphone (MIC) configured to receive external voice signals when the terminal device is in an operational mode, such as a voice recognition mode. The received speech signal may further be stored in the second memory 1202 or transmitted via the communication component 1203. In some embodiments, the speech component 1206 further comprises a speaker for outputting speech signals.
The input/output interface 1207 provides an interface between the processing component 1200 and peripheral interface modules, which may be click wheels, buttons, etc. These buttons may include, but are not limited to: a volume button, a start button, and a lock button.
The sensor component 1208 includes one or more sensors for providing various aspects of status assessment for the terminal device. For example, the sensor component 1208 may detect an open/closed state of the terminal device, relative positioning of the components, presence or absence of user contact with the terminal device. The sensor assembly 1208 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact, including detecting the distance between the user and the terminal device. In some embodiments, the sensor assembly 1208 may also include a camera or the like.
The communication component 1203 is configured to facilitate communications between the terminal device and other devices in a wired or wireless manner. The terminal device may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In one embodiment, the terminal device may include a SIM card slot therein for inserting a SIM card therein, so that the terminal device may log onto a GPRS network to establish communication with the server via the internet.
As can be seen from the above, the communication component 1203, the voice component 1206, the input/output interface 1207 and the sensor component 1208 involved in the embodiment of fig. 8 can be implemented as the input device in the embodiment of fig. 7.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. A dynamic threshold management method, comprising:
obtaining a comparison score distribution result through similarity comparison of the face images;
according to the comparison score distribution result, dynamically adjusting the comparison threshold of the image processing equipment or each target object, wherein the steps comprise: acquiring the maximum value of the non-personal comparison score according to the comparison score distribution result, and taking the maximum value of the non-personal comparison score as a comparison threshold value of the image processing equipment or each target object; judging the waveform of the comparison score distribution result, and skipping the dynamic adjustment of the image processing equipment or the comparison threshold of each target object if the waveform is three wave crests and more than three wave crests;
according to the comparison score distribution result, the step of dynamically adjusting the comparison threshold of the image processing device or each target object further comprises the following steps: judging the waveform of the comparison score distribution result, and if the waveform is a single peak, determining the mean value of the comparison score distribution result of the waveform; if the mean value of the comparison score distribution results is smaller than a preset threshold value, acquiring the maximum value of the comparison scores in the waveform and taking the maximum value of the non-personal comparison scores as the comparison threshold value of the image processing equipment or each target object;
according to the comparison score distribution result, the step of dynamically adjusting the comparison threshold of the image processing device or each target object further comprises the following steps:
judging the waveform of the comparison score distribution result, if the waveform is a double-peak, acquiring the maximum value of the comparison score in the first waveform and taking the maximum value of the non-personal comparison score as the comparison threshold of the image processing equipment or each target object, wherein the first waveform is a waveform with a smaller comparison score;
the step of determining the mean of the alignment score distribution results of the waveform comprises:
and fitting the comparison score distribution result through a normal distribution curve algorithm, and determining the mean value of the comparison score distribution result.
2. The dynamic threshold management method according to claim 1, wherein the step of dynamically adjusting the comparison threshold of the image processing apparatus or each target object according to the comparison score distribution result further comprises:
recording comparison threshold values of the image processing equipment or each target object;
acquiring a comparison threshold value of the current image processing equipment or each target object according to the comparison score distribution result;
comparing the current comparison threshold with the recorded comparison threshold, and taking the larger value as an updated comparison threshold;
and according to the updated comparison threshold, dynamically adjusting the comparison threshold of the image processing equipment or each target object.
3. The dynamic threshold management method according to claim 1, wherein the step of dynamically adjusting the comparison threshold of the image processing apparatus or each target object according to the comparison score distribution result further comprises:
and traversing a base library of the image processing equipment, if no face image of the target object exists, acquiring the maximum value of the non-personal comparison score, and taking the maximum value of the non-personal comparison score as a comparison threshold of the image processing equipment.
4. The dynamic threshold management method according to claim 1, wherein the step of dynamically adjusting the comparison threshold of the image processing apparatus or each target object according to the comparison score distribution result further comprises:
and traversing each target object, acquiring the maximum value of the non-personal comparison scores of the corresponding target object, and taking the maximum value of the non-personal comparison scores as the comparison threshold of the target object.
5. A dynamic threshold management system, comprising:
the acquisition module is used for acquiring a comparison score distribution result through similarity comparison of the face images;
the adjusting module is used for dynamically adjusting the comparison threshold of the image processing equipment or each target object according to the comparison score distribution result, acquiring the maximum value of the non-personal comparison score according to the comparison score distribution result, taking the maximum value of the non-personal comparison score as the comparison threshold of the image processing equipment or each target object, judging the waveform of the comparison score distribution result, and skipping the dynamic adjustment of the comparison threshold of the image processing equipment or each target object if the waveform is three peaks and more than three peaks; according to the comparison score distribution result, the step of dynamically adjusting the comparison threshold of the image processing device or each target object further comprises the following steps: judging the waveform of the comparison score distribution result, and if the waveform is a single peak, determining the mean value of the comparison score distribution result of the waveform; if the mean value of the comparison score distribution results is smaller than a preset threshold value, acquiring the maximum value of the comparison scores in the waveform and taking the maximum value of the non-personal comparison scores as the comparison threshold value of the image processing equipment or each target object;
according to the comparison score distribution result, the step of dynamically adjusting the comparison threshold of the image processing device or each target object further comprises the following steps:
judging the waveform of the comparison score distribution result, if the waveform is a double-peak, acquiring the maximum value of the comparison score in the first waveform and taking the maximum value of the non-personal comparison score as the comparison threshold of the image processing equipment or each target object, wherein the first waveform is a waveform with a smaller comparison score;
the step of determining the mean of the alignment score distribution results of the waveform comprises:
and fitting the comparison score distribution result through a normal distribution curve algorithm, and determining the mean value of the comparison score distribution result.
6. The dynamic threshold management system of claim 5, wherein the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further comprises:
recording comparison threshold values of the image processing equipment or each target object;
acquiring a comparison threshold value of the current image processing equipment or each target object according to the comparison score distribution result;
comparing the current comparison threshold with the recorded comparison threshold, and taking the larger value as an updated comparison threshold;
and according to the updated comparison threshold, dynamically adjusting the comparison threshold of the image processing equipment or each target object.
7. The dynamic threshold management system of claim 5, wherein the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further comprises:
and traversing a base library of the image processing equipment, if no face image of the target object exists, acquiring the maximum value of the non-personal comparison score, and taking the maximum value of the non-personal comparison score as a comparison threshold of the image processing equipment.
8. The dynamic threshold management system of claim 5, wherein the step of dynamically adjusting the comparison threshold of the image processing device or each target object according to the comparison score distribution result further comprises:
and traversing each target object, acquiring the maximum value of the non-personal comparison scores of the corresponding target object, and taking the maximum value of the non-personal comparison scores as the comparison threshold of the target object.
9. An electronic device, comprising:
one or more processors; and
one or more machine-readable media having instructions stored thereon that, when executed by the one or more processors, cause the apparatus to perform the method recited by one or more of claims 1-4.
10. A machine-readable medium having stored thereon instructions, which when executed by one or more processors, cause an apparatus to perform the method of one or more of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110195658.2A CN112906574B (en) | 2020-07-16 | 2020-07-16 | Dynamic threshold management method and system |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010683491.XA CN111898495B (en) | 2020-07-16 | 2020-07-16 | Dynamic threshold management method, system, device and medium |
| CN202110195658.2A CN112906574B (en) | 2020-07-16 | 2020-07-16 | Dynamic threshold management method and system |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010683491.XA Division CN111898495B (en) | 2020-07-16 | 2020-07-16 | Dynamic threshold management method, system, device and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112906574A CN112906574A (en) | 2021-06-04 |
| CN112906574B true CN112906574B (en) | 2022-03-01 |
Family
ID=73192061
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110195658.2A Active CN112906574B (en) | 2020-07-16 | 2020-07-16 | Dynamic threshold management method and system |
| CN202010683491.XA Active CN111898495B (en) | 2020-07-16 | 2020-07-16 | Dynamic threshold management method, system, device and medium |
| CN202110192083.9A Active CN112906568B (en) | 2020-07-16 | 2020-07-16 | Dynamic threshold management method, system, electronic device and medium |
Family Applications After (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010683491.XA Active CN111898495B (en) | 2020-07-16 | 2020-07-16 | Dynamic threshold management method, system, device and medium |
| CN202110192083.9A Active CN112906568B (en) | 2020-07-16 | 2020-07-16 | Dynamic threshold management method, system, electronic device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN112906574B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113469015A (en) * | 2021-06-29 | 2021-10-01 | 浙江大华技术股份有限公司 | Face recognition method and device, electronic equipment and computer storage medium |
| CN115588216A (en) * | 2021-07-06 | 2023-01-10 | 中兴通讯股份有限公司 | Face recognition method, face recognition equipment and storage medium |
| CN113255631B (en) * | 2021-07-15 | 2021-10-15 | 浙江大华技术股份有限公司 | Similarity threshold updating method, face recognition method and related device |
| CN113688708A (en) * | 2021-08-12 | 2021-11-23 | 北京数美时代科技有限公司 | Face recognition method, system and storage medium based on probability characteristics |
| CN113807319A (en) * | 2021-10-15 | 2021-12-17 | 云从科技集团股份有限公司 | Face recognition optimization method, device, equipment and medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103563374A (en) * | 2011-05-27 | 2014-02-05 | 索尼公司 | Image-processing device and method |
| CN106022032A (en) * | 2015-03-30 | 2016-10-12 | 欧姆龙株式会社 | Individual identification device, and identification threshold setting method |
Family Cites Families (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7492943B2 (en) * | 2004-10-29 | 2009-02-17 | George Mason Intellectual Properties, Inc. | Open set recognition using transduction |
| JP2006277415A (en) * | 2005-03-29 | 2006-10-12 | Sanyo Electric Co Ltd | Registration method and device, and authentication method and device |
| US8712109B2 (en) * | 2009-05-08 | 2014-04-29 | Microsoft Corporation | Pose-variant face recognition using multiscale local descriptors |
| CN103136533B (en) * | 2011-11-28 | 2015-11-25 | 汉王科技股份有限公司 | Based on face identification method and the device of dynamic threshold |
| US11089247B2 (en) * | 2012-05-31 | 2021-08-10 | Apple Inc. | Systems and method for reducing fixed pattern noise in image data |
| CN106156776A (en) * | 2015-04-18 | 2016-11-23 | 宁波中国科学院信息技术应用研究院 | A kind of illumination recognition methods in traffic video monitoring |
| CN106295672B (en) * | 2015-06-12 | 2019-10-29 | 中移信息技术有限公司 | A kind of face identification method and device |
| CN106169071B (en) * | 2016-07-05 | 2019-06-21 | 厦门理工学院 | A kind of Work attendance method and system based on dynamic human face and chest card recognition |
| US10062152B2 (en) * | 2016-07-27 | 2018-08-28 | Sharp Laboratories Of America, Inc. | System for conversion of low dynamic range images to high dynamic range images |
| CN108241836A (en) * | 2016-12-23 | 2018-07-03 | 同方威视技术股份有限公司 | For the method and device of safety check |
| CN107452113A (en) * | 2017-08-09 | 2017-12-08 | 郝建 | Intelligent access system with face identification functions |
| CN108875493B (en) * | 2017-10-12 | 2021-04-27 | 北京旷视科技有限公司 | Method and device for determining similarity threshold in face recognition |
| CN108875522B (en) * | 2017-12-21 | 2022-06-10 | 北京旷视科技有限公司 | Face clustering method, device and system and storage medium |
| CN108805048B (en) * | 2018-05-25 | 2020-01-31 | 腾讯科技（深圳）有限公司 | face recognition model adjusting method, device and storage medium |
| US11391819B2 (en) * | 2018-07-18 | 2022-07-19 | Qualcomm Incorporate | Object verification using radar images |
| CN109614881B (en) * | 2018-11-19 | 2021-04-27 | 中国地质大学（武汉） | Biometric authentication method and device capable of adaptively adjusting threshold value and storage device |
| CN109741369B (en) * | 2019-01-03 | 2021-07-23 | 北京邮电大学 | Method and system for robot to track target pedestrian |
| CN110059596B (en) * | 2019-04-03 | 2020-07-07 | 北京字节跳动网络技术有限公司 | Image identification method, device, medium and electronic equipment |
| CN110276243A (en) * | 2019-05-07 | 2019-09-24 | 平安科技（深圳）有限公司 | Score mapping method, face comparison method, device, equipment and storage medium |
| CN110705475B (en) * | 2019-09-30 | 2022-05-17 | 北京地平线机器人技术研发有限公司 | Method, apparatus, medium, and device for target object recognition |
| CN110929619A (en) * | 2019-11-15 | 2020-03-27 | 云从科技集团股份有限公司 | Target object tracking method, system and device based on image processing and readable medium |
| CN111178162B (en) * | 2019-12-12 | 2023-11-07 | 北京迈格威科技有限公司 | Image recognition method, device, computer equipment and storage medium |
-
2020
- 2020-07-16 CN CN202110195658.2A patent/CN112906574B/en active Active
- 2020-07-16 CN CN202010683491.XA patent/CN111898495B/en active Active
- 2020-07-16 CN CN202110192083.9A patent/CN112906568B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103563374A (en) * | 2011-05-27 | 2014-02-05 | 索尼公司 | Image-processing device and method |
| CN106022032A (en) * | 2015-03-30 | 2016-10-12 | 欧姆龙株式会社 | Individual identification device, and identification threshold setting method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112906568A (en) | 2021-06-04 |
| CN112906574A (en) | 2021-06-04 |
| CN111898495A (en) | 2020-11-06 |
| CN112906568B (en) | 2021-11-12 |
| CN111898495B (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112906574B (en) | Dynamic threshold management method and system | |
| CN108920070B (en) | Screen splitting method and device based on special-shaped display screen, storage medium and mobile terminal | |
| CN111310725A (en) | Object identification method, system, machine readable medium and device | |
| CN111914693A (en) | Face posture adjusting method, system, device, equipment and medium | |
| CN111142650B (en) | Screen brightness adjusting method, screen brightness adjusting device and terminal | |
| CN111626229A (en) | Object management method, device, machine readable medium and equipment | |
| CN110766837A (en) | Control method and device for passing equipment, machine readable medium and equipment | |
| CN111178455B (en) | Image clustering method, system, device and medium | |
| CN112529939A (en) | Target track matching method and device, machine readable medium and equipment | |
| CN107223226B (en) | Apparatus and method for multi-touch input | |
| CN111091152A (en) | Image clustering method, system, device and machine readable medium | |
| CN112417197B (en) | Sorting method, sorting device, machine readable medium and equipment | |
| CN107862010B (en) | Method and device for acquiring information of application system of Internet of things and mobile terminal | |
| CN112051270B (en) | Power transmission line defect detection method, system, equipment and medium | |
| CN111813988B (en) | HNSW node deletion method, system, device and medium for image feature library | |
| CN111710011B (en) | Cartoon generation method and system, electronic device and medium | |
| CN111626369B (en) | Face recognition algorithm effect evaluation method and device, machine readable medium and equipment | |
| CN112347982A (en) | Video-based unsupervised difficult case data mining method, device, medium and equipment | |
| CN111626223A (en) | Equipment state detection method and device, electronic equipment and medium | |
| CN111915422A (en) | Wind control model scheduling method and device, machine readable medium and equipment | |
| CN112069184A (en) | Vector retrieval method, system, device and medium | |
| CN111224936B (en) | User abnormal request detection method, system, device and machine readable medium | |
| CN116468883B (en) | High-precision image data volume fog recognition method and device | |
| CN110766842B (en) | Passing equipment control method and device, machine readable medium and equipment | |
| CN111711760B (en) | Camera lens module shielding control method and device based on infrared control and camera |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |