Energy saving method for array multi-modal biometric feature acquisition and recognition device

Abstract

The present application relates to a kind of array multimodal biometric feature acquisition and identification equipment energy-saving and cost-reducing method.The method can be by one or several groups of binocular color camera for face ranging, and according to the ranging result and the position of personnel eyes in image, the height of personnel eyes is calculated, so as to determine to open part of iris camera and infrared light in system, complete acquisition and identification task, finally reach the effect of energy saving and cost reduction.

Description

Technical Field

[0001] This invention relates to the field of biometric acquisition and recognition, and in particular to an energy-saving and consumption-reducing method for an array-type multimodal biometric acquisition and recognition device. Background Technology

[0002] With the continuous advancement of technology, people have placed higher demands on the accuracy, security, and convenience of identity verification. Facial recognition technology has developed rapidly in recent years, becoming the preferred solution for non-contact biometric identification. Iris recognition technology, as a type of biometric technology, has gradually become a research and application hotspot due to its high precision and non-contact advantages.

[0003] Unlike facial recognition, iris recognition requires the use of specific camera equipment to capture the entire eye. Near-infrared cameras are typically used because near-infrared light better highlights the texture of the iris while reducing interference from ambient light. Early recognition devices often had specific requirements for the acquisition distance and method, such as capturing irises at a fixed distance, position, or angle. With technological advancements, some systems employ fully automatic adaptive technology, automatically locating and focusing on the iris, improving user experience and success rates.

[0004] Existing multimodal biometric acquisition and recognition devices are mainly divided into dedicated acquisition devices, adaptive acquisition devices, and array-type acquisition devices. Dedicated acquisition devices generally require the active cooperation of the person being acquired, collecting facial and iris data at a fixed distance and angle. The devices have a narrow range of adaptability and a poor user experience. For example, handheld dedicated acquisition devices have a fixed acquisition distance of about 15cm, requiring the user to actively hold the device and collect data at a fixed distance. Adaptive acquisition devices can collect facial and iris information from people of different heights without requiring deliberate cooperation, but generally require the addition of a mechanical rotation device to automatically track the eye position by rotating to different angles. For example, in access control or gate systems, when a person is standing still, the device primarily locates the eye through facial detection and controls the motor of the rotation device to rotate, aligning the iris camera with the angle of the eye for facial and iris data collection. Array-type acquisition devices use multiple iris cameras and infrared lights arranged in an array, allowing for real-time collection of iris information from people of different heights without requiring deliberate cooperation.

[0005] In array-based multimodal biometric acquisition and recognition devices, the components with higher power consumption are mainly the iris camera and infrared lights. The face acquisition component can use a wide-angle lens to cover the face acquisition needs of people of different heights. However, the iris region has a relatively small imaging area. To cover the iris acquisition needs of people of different heights, multiple sets of iris cameras and corresponding infrared lights need to be activated simultaneously and work together to complete the iris acquisition task. This approach requires that the iris cameras and infrared lights be activated simultaneously. In actual iris acquisition, only one or two sets of iris cameras and infrared lights may be used, increasing power consumption and leading to a significant waste of energy. Summary of the Invention

[0006] To address the issues of increased power consumption and energy waste in the aforementioned array-type multimodal biometric acquisition and recognition devices, this invention provides a method for real-time face ranging using one or more sets of binocular color cameras, calculating the height of the person's eyes based on the ranging results and the position of the person's eyes in the image, determining the activation of some iris cameras and infrared lights in the system, and ultimately completing the acquisition and recognition task.

[0007] To address the aforementioned issues of increased power consumption and energy waste, this invention provides a method for real-time switching of a portion of an iris camera and infrared lights, the method comprising the following steps: The first step is to measure distance using binocular cameras: Based on the principle of triangulation, binocular color cameras with pre-calibrated relative positions are used to measure distance to the face. Based on the distance measurement results, the size of the scene to be captured, and the field of view of a single camera, the number of binocular cameras that need to be activated can be calculated.

[0008] The second step is to calculate the height of the target person's eyes: The target detection model is used to detect and track the coordinate position of the target person's eyes in the image in real time. Based on this coordinate and the distance measurement results in the first step, the height difference between the eyes and the camera installation position can be calculated, thereby calculating the height position of the target person's eyes.

[0009] The third step is to control the iris camera and infrared lights: Based on the results of the person's eye height position in the second step, one or more sets of iris cameras and infrared lights at the corresponding height positions can be turned on to collect and recognize irises.

[0010] Preferably, the binocular color camera has hardware frame synchronization function, resolution of not less than 2 million pixels, field of view of not less than 70 degrees, distortion of less than 0.1%, and baseline length of not less than 60mm.

[0011] Preferably, the target detection model is trained using deep learning or machine learning to detect faces and provides at least 5 key point results, which can accurately determine the coordinates of both eyes and calculate the depth information of both eyes.

[0012] Preferably, the iris camera and infrared light control are configured such that the iris camera uses a MIPI interface, has an 8-megapixel resolution, and is equipped with an infrared filter of 800nm ​​or higher. The on / off state of each iris camera can be controlled individually via the main control board. The infrared light provides an 810nm near-infrared light source, with a narrow half-angle of ±13 degrees, and meets the halogen-free standard. The on / off state of each infrared light can be controlled individually via the main control board or a microcontroller.

[0013] This invention provides a method for facial ranging using one or more sets of binocular color cameras, and for calculating eye height based on the ranging results and the position of the person's eyes in the image. This allows for selective activation of only a portion of the iris cameras and infrared lights, avoiding the need to activate all iris cameras and infrared lights each time. Compared to previous array-type multimodal biometric acquisition and recognition devices, this invention significantly reduces functionality and avoids energy waste by selectively activating only some iris cameras and infrared lights.

[0014] Other features and advantages of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0015] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the following detailed description to explain the invention, but do not constitute a limitation thereof. In the drawings: Figure 1 is a three-dimensional structural diagram of the array arrangement of the iris camera and infrared lamps in the array-type multimodal biometric acquisition and recognition device according to the embodiment of the present invention.

[0016] Figure 2 is a schematic diagram of the structure of the array-type multimodal biometric acquisition and recognition device for calculating eye height according to the embodiment of the present invention.

[0017] Figure 3 This is a schematic diagram illustrating the application scenario of the array-type multimodal biometric acquisition and recognition device described in the embodiment of the present invention.

[0018] Figure 4 This is a flowchart illustrating the workflow of the array-type multimodal biometric acquisition and recognition device described in the embodiment of the present invention.

[0019] Explanation of reference numerals in the attached figures: In the attached diagram, 1 is an infrared light, 2 is a camera, and 3 is a rangefinder and face recognition camera. Figure 2 H is the installation height of the face camera in cm, θ is the VFOV of the face camera in degrees, dis is the distance between the person being captured and the camera in cm, h is the vertical resolution of the face camera in pixels, and y is the position of the face in the image in pixels. Detailed Implementation

[0020] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0021] In this invention, unless otherwise stated, directional terms such as "up," "down," "left," and "right" generally refer to the up, down, left, and right as shown in the accompanying drawings; "inner" and "outer" refer to the inner and outer contours relative to the outline of each component itself.

[0022] For array-type iris capture and recognition equipment to capture the irises of people between 150cm and 200cm in height (within a 50cm height range) in real time, multiple iris cameras and infrared supplementary lights (such as...) are required. Figure 1 ).

[0023] The array arrangement can use one or more rows of cameras to increase the lateral acquisition range; depending on the acquisition height requirements, multiple rows of cameras can be used to simultaneously acquire irises at different heights. Without affecting the acquisition effect, multiple array cameras can be arranged more compactly, using curved or spherical base plates, and the final acquisition device can be made in different sizes and shapes.

[0024] The aforementioned device requires all cameras and infrared lights to be operational when collecting iris scans. However, only one or a few sets of cameras and infrared lights may actually be used, resulting in resource waste and reduced lifespan of the cameras and infrared lights. This patent adds a face-collecting camera and a ranging module to the device. By analyzing the position of the face in the image and the distance results from the ranging module, the eye height of the person being scanned (e.g., ...) can be calculated. Figure 2 Then, based on the eye height information, it determines to activate one or more sets of cameras and infrared lights in the array to collect iris images. This method can greatly reduce the power consumption of the device and increase its lifespan.

[0025] Based on the face position and distance measurement results, the formula for calculating eye height is as follows: The height range that the face camera can collect data from is: Hdis = arctan(θ / 2)*dis*2 Eye height (cm) = H - Hdis / 2 + (1 - y / h) * Hdis = H + (1 / 2 - y / h)Hdis Once the eye height of the person being scanned is calculated, and the installation height of the array iris camera is known, it becomes possible to determine which set of cameras or infrared lights to use for data collection or identification. Only these cameras and infrared lights are activated, while the remaining components can remain in standby or off, achieving energy conservation and reduced consumption.

[0026] Array-type iris acquisition and recognition equipment scenarios such as Figure 3 .

[0027] The process of controlling the camera and infrared lights to perform iris capture or recognition is as follows: Figure 4 .

[0028] Workflow: Once the personnel enter the data collection area, the face camera and ranging module begin working, detecting the face coordinates in the image and tracking them in real time. Simultaneously, the ranging module provides the distance between the face and the device. Then, based on the face coordinates and distance, the eye height of the person being collected is calculated, thereby determining which set or several sets of iris cameras and infrared lights to activate. Iris data collection then proceeds until a qualified iris image is obtained or the collection timeout occurs, at which point the data collection task ends.

[0029] The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the specific details of the above embodiments. Within the scope of the technical concept of the present invention, various simple modifications can be made to the technical solution of the present invention, and these simple modifications all fall within the protection scope of the present invention.

[0030] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the present invention will not describe the various possible combinations separately.

[0031] Furthermore, various different embodiments of the present invention can be combined in any way, as long as they do not violate the spirit of the present invention, they should also be regarded as the content disclosed by the present invention.

Claims

1. A method for energy saving and consumption reduction in an array-type multimodal biometric acquisition and recognition device, characterized in that: The energy-saving and consumption-reducing method includes detecting the distance to a human face target using a binocular color camera and calculating the height of the person's eyes; by calculating the height of the person's eyes, controlling only the iris camera and infrared lights in the corresponding height area to be activated, thereby achieving the purpose of energy saving and consumption reduction.

2. The energy-saving and consumption-reducing method for an array-type multimodal biometric acquisition and recognition device as described in claim 1, characterized in that: The binocular color camera collects, detects, and tracks the coordinates of a person's face in real time. It calculates the depth information of the eye position in the face using the principle of triangulation, thereby obtaining the distance between the person's eyes. Based on the coordinates of the person's eyes in the image, it calculates the height of the person's eyes relative to the binocular color camera.

3. The energy-saving and consumption-reducing method for an array-type multimodal biometric acquisition and recognition device as described in claim 1, characterized in that: Based on the calculated height of the person's eyes relative to the binocular color camera, the main control board or microcontroller controls the switching of some iris cameras and infrared lights in the corresponding height area to avoid turning on all cameras and infrared lights.

Images