1 Introduction Fingerprint recognition technology extracts detailed feature points by analyzing the local features of fingerprints to reliably confirm personal identity. Fingerprint identification not only has many unique information security advantages, but more importantly, it has high practicability and feasibility.
At present, most fingerprint identification systems collect fingerprint images into a computer and use computers to identify them. The independent fingerprint identification system produced by some foreign companies is relatively expensive. These have limited the popularity of fingerprint recognition technology. Therefore, the independent fingerprint identification system with fast research, high recognition rate and low cost has great market prospect and important scientific research value.
This paper proposes a new type of fingerprint recognition system based on DSP. The hardware uses DSP's high-speed processing capability to build a high-speed data processing platform. The software refers to the processing characteristics of DSP and hardware logic, and improves the traditional fingerprint algorithm to meet real-time. Sex and reliability requirements.
2 hardware system structure
The principle block diagram of the system is shown in Figure (1):
?
Figure (1) system structure block diagram
The system can be divided into three parts: image acquisition module, image processing and recognition module and output module.
2.1 Image Acquisition Module
In the image acquisition module, since the fingerprint recognition system does not need to observe images in real time, the requirements on the sensor are not very high, and the general black and white digital CMOS sensor can meet the requirements. This system uses a 3 megapixel high-definition black-and-white sensor as an image acquisition device, which is very suitable for use as a fingerprint image sensor. Mainly considering the advantages of low cost, high resolution and good reliability of CMOS devices. The disadvantage is that the image quality may deteriorate when the fingers sweat more or dry. In the image recognition process, the GABOR-based enhancement algorithm is adopted, which can basically overcome the impact.
2.2 Image Processing and Identification Module
The structure of image processing and recognition module is related to the overall level of system performance. The architecture of FPGA+DSP is conducive to constructing efficient data processing flow and facilitating the allocation of processing tasks, improving system parallelism and resource utilization. The SRAM, SDRAM, and FLASH in the system are directly connected to the DSP for use: FLASH is used to store programs and some fixed table data; SDRAM is used as DSP system memory for system program operation; SRAM is high-speed data storage area. , used to store the temporary variables generated by the program run. The DDR SDRAM is specially used to store the collected fingerprint data and some large-capacity data blocks calculated by the pixel point gradient data in the pre-processing process, and is directly connected to the FPGA, which is the highest-speed memory area in the system. In addition to being the extended bus interface of the DSP processor, FPGA also shares some data processing tasks, because only one DSP is not suitable for all computing and control tasks. When processing fingerprint data, it often encounters some cumbersome addition and subtraction. Operation and ratio logic operations, usually this part is handled by the FPGA, taking into account the particularity of the fingerprint processing algorithm, but also to achieve the DDR control function.
Due to the large amount of mathematical operations in the fingerprint recognition process, the program design inevitably requires a large storage space. In order to improve the overall performance, it is necessary to hand over the heavy computing tasks to the DSP, and the image acquisition part should be occupied as little as possible. DSP time. In addition, by using the gap of image acquisition or image acquisition, a simple and cumbersome operation by hardware can share the processing tasks of the DSP, improve the parallelism of processing, and meet the requirements of real-time. This system adopts TMS320VC5402, which has fast calculation speed and high cost performance. The 8bits grayscale fingerprint image collected in the system, each pixel occupies one byte, the image size is 512 & TImes; 512 pixels size, storing one frame of image requires 256k bytes of storage space. The DSP unit is the core of the entire fingerprint processing system and is responsible for real-time processing of fingerprints.
2.3 output module
As an independent fingerprint identification system, the data recognized by the system can be directly displayed through the LCD. When designing the system, the system can also be used as a terminal, that is, an Ethernet interface is extended through the FPGA as a large fingerprint recognition system terminal that needs to transmit fingerprint database data through the network.
3 fingerprint recognition algorithm
The fingerprint identification algorithm is the core of fingerprint recognition. The process of fingerprint recognition algorithm used in this system is shown in Figure (2).
Figure (2) fingerprint identification algorithm flow
Image enhancement is the core problem that fingerprint image preprocessing needs to solve. The main purpose of fingerprint image enhancement is to eliminate noise, improve image quality and facilitate feature extraction. Because the fingerprint texture consists of interphase ridges and valley lines. These textures contain a lot of information, such as texture orientation, texture density, and so on. Such information is different in different areas of the fingerprint image. Fingerprint image enhancement algorithms are implemented using regional differences in image information. The traditional fingerprint image enhancement is to use the texture direction information of the image to construct a directional filter template to achieve filtering. The simplicity of filter construction and the complexity of fingerprint image complexity limit the effectiveness of its effects. In this system, the fingerprint image texture frequency information is referenced, and the GABOR transform is used as a template for the filter, which can simultaneously analyze the direction of the local structure of the image and the spatial frequency of the image, thus greatly improving the enhancement. The effect of the algorithm.
3.1 ridge direction
Except for the singular area, the fingerprint image is in a sufficiently small area, and the texture approximates a line parallel to each other. This is the directional characteristic of the fingerprint image. The directional feature is one of the most obvious features in the fingerprint image. It intuitively reflects the basic morphological features of the fingerprint image in a simplified form, and thus is widely used in the classification, enhancement and feature extraction of fingerprint images.
The method of extracting the ridge direction is:
(1) Divide the fingerprint image into sub-blocks small enough to satisfy the condition that the textures in the block are approximately parallel.
"Lithium battery" refers to a battery made of lithium metal or lithium alloy as a negative electrode material, using a non-aqueous electrolyte solution.It has a high energy density.Compared with high-capacity nickel-cadmium batteries, the energy density is twice as high.High voltage. The average service voltage is 3.6v, which is three times higher than nickel-cadmium and nickel-hydride batteries.The use voltage is even and the high capacity, the widespread use temperature -20 degrees -60 degrees, the charge and discharge life is long, after 500 discharges its capacity at least has more than 70%.Due to the characteristics of high energy density, high voltage and stable operation, lithium battery is widely used.
Lithium Ion Battery Pack,12V Lithium Ion Battery Pack,12V Lithium Battery Pack,Lithium Battery Pack
Xinxiang Taihang Jiaxin Electric Tech Co., Ltd , https://www.chargers.be