In the context of the rapid development of science and technology and the modernization of the legal system, criminal activities are becoming more and more intelligent and technological, which also puts forward higher requirements for criminal technology. The current criminal technology equipment is relatively backward, and the technical level is not high enough, resulting in a low utilization rate of trace material evidence extraction, which directly affects the role of criminal technology in the investigation and solving of cases. In recent years, fingerprint recognition algorithms and image edge detection algorithms have been widely used in various fields. This work studied the application of fingerprint image fuzzy edge recognition algorithm in criminal technology, in order to improve the level of criminal technology and the utilization rate of physical evidence extraction. The criminal technology system is upgraded and optimized by combining fingerprint recognition algorithm and image edge detection algorithm. And fuzzy theory is added to ensure the feasibility of the research. The experimental results show that the fuzzy edge recognition algorithm of fingerprint image can improve the level of criminal technology and the utilization rate of material evidence to a certain extent. The utilization rate is increased by 7.04%. The recognition accuracy of the fuzzy recognition method is also 13.2% higher than that of the methods in the literature.
In the field of criminal investigation, the use of criminal technology is very extensive and its role is also very huge. Criminal technology can provide an important scientific basis for determining the nature of a case and provide relevant evidence for determining criminal facts. With the increase in international exchange opportunities and the adjustment of the knowledge structure and way of thinking of criminal technicians, the intensity of criminal science and technology research has been strengthened. In addition, the technology and changing types of criminal activities have put forward higher requirements on the science and legitimacy of trace investigation techniques and inspection and identification techniques. Emphasizing evidence rather than credulous confessions has become the general trend of criminal work. In recent years, the increasingly mature fingerprint recognition technology has also provided an opportunity for the development of criminal technology. Fingerprint recognition is an important technology in criminal work. Applying fuzzy edge recognition algorithm to fingerprint image recognition can improve the recognition effect and anti-noise performance.
In recent years, the application of fingerprint identification technology has become more and more mature, and many scholars have achieved good research results in the field of fingerprint identification. Wang et al. proposed a fingerprint segmentation enhancement method based on Gabor filter response, and the research results demonstrated the stability of the proposed method . Zhendong et al. proposed a new method of fingerprint reference point location based on directional coherence analysis, and the test results confirmed that this method can provide high-precision reference points for all types of fingerprint location . Zhou proposed a fingerprint feature priority matching method based on the structural features of fingerprint features, and further applied the genetic algorithm to the point matching stage, and finally found that the method achieved good results in automatic fingerprint recognition systems . Xie proposed a histogram partitioning and median filtering fingerprint identification algorithm in his paper, and then confirmed that the algorithm is suitable for different fingerprints with different backgrounds, resolutions, and sizes through the ensemble averaging of mean square errors . Lee et al. discussed a fingerprint recognition algorithm combined with filters, and the study found that the method showed good performance in both the accuracy and efficiency of fingerprint extraction . Mao et al. designed a fingerprint recognition algorithm using the wavelet transform principle, and achieved a fingerprint recognition rate of 91.4% in the test . Yan and Song proposed a novel fingerprint alignment and matching scheme based on geometric minutiae structure. Finally, the scheme achieved faster performance and higher accuracy of fingerprint recognition system . The above research work on fingerprint identification technology is relatively specific, but the fingerprint identification algorithm has not been applied to criminal technology. With the increasing maturity of criminal technology, it has become a key factor for solving cases. Zazulin investigated the use of CI Solvent Black 3 dye for fingerprint localization in criminal technology. The results have showed that CI Solvent Black 3 can be successfully applied to localize and visualize recent and non-recent latent fingerprints on porous surfaces . Vatsenko discussed the application prospects and theoretical methods of artificial intelligence in the field of criminal technology. Research showed that artificial intelligence is conducive to the upgrading and optimization of criminal investigation intelligence systems . Corda and Lageson discussed the importance of data mining technology in criminal investigation and confirmed that data mining technology has a good effect in preventing criminal crimes . Hadjimatheou discussed the application of DNA technology in criminal technology. Studies showed that DNA technology plays an important role in catching criminals and solving crimes . Tani analyzed the use of neuroimaging technology in criminal work and found that the technology can avoid wrongful convictions for wrongful punishment of innocent parties and prevent dangerous criminals from being released back into the society . Vardanyan and Andreev discussed the application of VoIP technology in criminal technology forensics, and finally confirmed that VoIP-based criminal forensics methods can provide a useful reference for relevant evidence investigations . Kocak and Dandin proposed a method of criminal identification based on neural network technology. The results showed that the method can identify individuals who belong to the same gang or drug-trafficking circle . These studies on criminal technology are relatively detailed, but they do not involve the application of fingerprint image fuzzy edge recognition algorithm in criminal technology.
In order to improve the level of criminal technology and the utilization rate of physical evidence extraction, this study applied the fingerprint image fuzzy edge recognition algorithm to criminal technology, aiming to innovate and upgrade the criminal technology system. When the fingerprint image is recognized, the fuzzy theory and filter image enhancement methods are used to ensure the accuracy of fingerprint image recognition. The final experimental results showed that the fingerprint image fuzzy edge recognition algorithm has achieved good results in fingerprint image recognition, and the fingerprint recognition rate and matching rate have been improved a lot, which provides important suggestions for the upgrading and optimization of criminal technology.
2 Fingerprint recognition in criminal technology
2.1 Fingerprint identification system
Fingerprint recognition refers to the classification and comparison of the fingerprints of the identified objects. Fingerprint recognition system is a typical pattern recognition system, including fingerprint image acquisition, processing, feature extraction, and comparison modules. With the acceleration of the social information process, the application of fingerprint identification in the criminal field is becoming more and more mature . Figure 1 shows a common fingerprint identification system in criminal work, and its identification process is relatively complicated. Interactive query is an important link between users and fingerprint recognition. On the one hand, the user’s fingerprint should be stored, and on the other hand, the recognition result should be fed back to the user in time. Fingerprint collection is the first step of the whole system. After the fingerprint collector collects the fingerprint from the suspect, it will transmit the fingerprint image to the fingerprint processor. The fingerprint processor needs to perform preprocessing, feature extraction, feature encoding, etc., on the fingerprint. After all these steps are completed, it will send a matching identification request to the fingerprint feature database. After the database successfully matches the fingerprint, the fingerprint identification is officially completed.
2.2 Fingerprint image recognition preprocessing algorithm
In the fingerprint recognition algorithm, the fingerprint image preprocessing algorithm is the most important part. In criminal work, fingerprint image collection often has problems of low resolution and insufficient smoothness, and the effect of fingerprint collection will be affected by external and human factors such as the incoherent texture and chapped dry and wet fingerprint, which requires preprocessing of collected fingerprint images. The specific function of preprocessing is to try to eliminate the wrong information caused by these factors and keep only the most original fingerprint lines.
There are many ways to collect fingerprints. The fingerprints collected by the police on criminal detention, administrative detention, suspects of committing crimes, drug-related persons, etc., are collectively referred to as fingerprinting. In the process of collecting fingerprints, some fingerprint collection systems will automatically judge the quality and finger position of the collected fingerprints to ensure that the collected fingerprint images meet the three-element requirements of high quality, no dislocation, and no repetition. The specific acquisition quality control functions include fingerprint wet test, fingerprint image quality judgment, fingerprint image automatic centering, fingerprint image angle automatic correction, fingerprint image automatic background removal, repeated fingerprint judgment, plane and scroll corresponding finger position judgment, triangle and center acquisition incomplete judgment, fingerprint collection area judgment, etc. The fingerprints left by the suspect at the crime scene are called scene fingerprints, and are usually abbreviated as LT in English. On-site fingerprints are finger marks left unintentionally by suspects when committing a crime. Usually, there are uneven marks, blurred textures, and cluttered backgrounds. The preprocessing algorithm can improve the quality of the input fingerprint image, remove the noise in the image, and convert the fingerprint trajectory into a clear scatter plot, so as to extract the correct fingerprint features and improve the accuracy of the comparison results. Figure 2 shows the process of fingerprint preprocessing, including input image, normalization, filter enhancement, binarization, and refinement.
3 Application of fingerprint edge detection algorithm and fuzzy restoration in criminal technology
3.1 Edge detection algorithm
Edge detection is a relatively common phenomenon in image processing and computer vision, and its main purpose is to identify points in digital images with significant changes in brightness . The so-called edge refers to the set of pixels around which the grayscale of the pixels changes sharply. It is the most basic feature of the image. The edge exists between the target, the background, and the region. Therefore, it is the most important basis for image segmentation. Commonly used operators in edge detection algorithms are Canny operator, Prewitt operator, and Sobel operator. The Sobel edge detection algorithm is the most efficient algorithm in edge detection. The edge detection algorithm usually has directionality, which is divided into horizontal edge and vertical edge detection. Figure 3 is an application example of edge detection. Bidirectional slope coefficients in detection must be determined before detection, i.e., , . Next the gradient image is calculated. The edge points are actually the points where the grayscale jumps violently into the image. The brightest part of the gradient image can be regarded as part of a simple edge.
The Sobel operator usually uses a filter to filter the image to obtain the gradient image. After the filter is defined, the gradient image in the vertical and vertical directions can be obtained by rotating the filter with the image to obtain a gradient image.
3.2 Edge detection algorithm based on fingerprint image
When criminal staff obtain criminal’s fingerprint images, they often use gradient changes to sharpen the image. But this method will enhance the tone and lines at the same time, which brings recognition difficulties. However, the Sobel operator in edge detection does not have such a problem. Due to the introduction of the averaging factor, the Sobel operator can achieve a smoothing effect when processing random noise in the image, and because it has a difference between two rows or two columns, the image elements on both sides of the edge will be enhanced. The edges will appear thicker and brighter. The fingerprint image edge detection process is shown in Figure 4. First, the fingerprint samples of criminal suspects are detected and located, and then the fingerprint image is input for image enhancement, feature extraction, and edge refinement. The subsequent processing is performed by criminal personnel for fingerprint matching.
3.3 Fuzzy theory
3.3.1 Common fuzzy structural elements
The fuzzy structure element is a fuzzy set on the real number field , and its membership function is marked as , meeting the following properties:
is a single increasing right continuous function in the interval and is a single decreasing left continuous function in the interval ;
When or , .
If the membership function of a fuzzy structural element has in the interval and is a continuous strict single increasing function in , and is a continuous strict single decreasing function in the interval , then is called a regular fuzzy structural element; If , is called symmetric fuzzy structural element.
3.3.2 Fuzzy inference system and fuzzy rule table
Taking the fuzzy control rules of the model as an example, assume that the two inputs are and , and the fuzzy rules of single output have the following forms:
, where is the label of the input membership function and is the label of the output membership function, where the label is the language quantity. The overall architecture of the fuzzy inference system is shown in Figure 5. The work of the fuzzy controller is specified by the fuzzy knowledge base, including rules and membership functions. According to the current sampled input signal of the control system, the input is first fuzzified, and the clear value is converted to the fuzzy value, and then the fuzzy approximate reasoning is performed. The reasoning result is converted into the clear value through anti fuzzification and used as the current control output.
Table 1 is the rule table of the fuzzy controller. The two input signals are, respectively, the error and error change rate of the measured value of the controlled system, one output signal is the variation of control output. The labels NB, NM, NS, ZR, PS, PN, and PB, respectively, indicate that the signal is negative large, negative medium, negative small, zero, positive small, positive medium, and positive large. The single point method is commonly used for input fuzzification, that is, to calculate the membership value of the input membership function according to the current input value.
3.4 Examples of applications in criminal technology
In the practice of fingerprint technology application, the use of automatic fingerprint identification technology in the criminal field is to detect cases. The criminal investigators compare the fingerprints left at the crime scene and the fingerprints of the suspects (sample fingerprints) with the files of each archive to obtain a large number of fingerprints with high similarity (alternative fingerprints), and then the suspect is identified through the fingerprint. By judging and investigating one by one, experts determine whether the sample fingerprint is consistent with the candidate fingerprint, and then find the murderer . Figure 6 is an application frame of the police fingerprint identification system based on fingerprint image fuzzy edge identification algorithm. Criminal officers look for fingerprints at the crime scene, input suspicious fingerprints into the fingerprint system, and then process and compare the fingerprint owners through algorithms. On the other hand, criminal officers collect, fuzzy identify, edge detect the fingerprints of suspicious persons, and after investigation, compare the fingerprints with the fingerprint owners found before, and finally implement arrests.
4 Mathematical model of fingerprint image recognition in criminal technology
4.1 Mathematical modeling
For a grayscale image of , the mathematical modeling process of the fingerprint image is as follows.
4.1.1 Calculation of fingerprint image intensity field
Supposing the fingerprint image function is and the intensity field is , the gray field is , which represents the size of the gray value of the pixel at this point.
4.1.2 Calculation of fingerprint image gradient field
For , the partial derivative of is , and the gradient vector can be obtained as .
Let be at the point of , let be at the point of , then
4.1.3 Calculation of fingerprint image orientation field
220.127.116.11 Mathematical modeling of ideal direction field size
If , , among them, , is the unit vector of orthogonal coordinates.
Then, , The direction field size of is .
18.104.22.168 Mathematical modeling of actual direction field size
In a fingerprint image, in order to represent the relationship between a particular pixel and the fingerprint image, the memory must be allocated for surrounding pixels. When defining any pixel point, the surrounding information need to be used to add point information. That is to say, add up the surrounding gray points first, then calculate the average, and the authenticity of the image will be higher. Supposing it to be:
Then, the size of the direction field is the mathematical model accurately shows the direction field of the real fingerprint image from a statistical point of view. The partial derivative of in the model is represented by the Sobel operator, which is expressed as:
4.2 Field-based fingerprint image enhancement algorithm
Using the modeling of the fingerprint field and the visualization model of the Gabor wavelet function mentioned above, the visualization model of the field-based fingerprint image enhancement can be established, and its mathematical model can be obtained at the same time. Finally, the field-based fingerprint image enhancement algorithm can be realized.
The Gabor wavelet function is obtained by repeating the Gaussian activity and the triangular activity. According to the structure of these two functions, the Gabor wavelet function produces periodic oscillations . The field-based fingerprint enhancement mathematical model derived from the Gabor wavelet enhancement physical model is as follows:
The field-based one-dimensional expression is given as follows:
The field-based two-dimensional (2D) expression is given as follows:
and the formula is specified as follows:
where is the Gaussian diffusion factor, the mathematical meaning is the standard deviation; is the width scale factor, indicating the frequency of the wave; is the coordinate axis scale factor, and the mathematical geometric meaning is the ratio of the long and short axes of the ellipse plane at the bottom of the image.
The rotation formula of the coordinate axis is given as follows:
where is the rotation factor, the mathematical geometric meaning represents the angle between the direction vector of the point and the positive direction of the -axis, and the physical meaning is the direction field of the point.
4.3 Fingerprint image frequency domain enhancement
The frequency domain enhancement method is to modify the transformed coefficients in a certain transform domain of the image, such as the coefficients of Fourier transform, DCT transform, etc., to operate the image, and then inverse transform to obtain the processed image. Generally, the frequency domain enhancement algorithm can be divided into several algorithms according to the different switching methods, including the enhancement algorithms based on wavelet transform, enhancement algorithms based on fast Fourier transform (FFT), and enhancement algorithms based on short time Fourier transform (STFT) . In practical applications, the latter two algorithms are the most commonly used.
The FFT-based image enhancement algorithm first performs FFT transformation on the image to obtain a modified frequency image, then filters the frequency image in different ways, and finally performs Fourier transform on the filtered image to obtain an enhanced image. As shown in equations (9) and (10), is a bandpass filter with a bandpass center of and a bandwidth of . In the algorithm, the convex cosine function is used as the direction filter, and its width and center are and .
The algorithm takes into account the curvature characteristics of fingerprint ridges. When a certain point is a singular point, the curvature of the ridge near the point is relatively high, and the change in the direction field at this point is also very sharp. A band pass filter with a fixed orientation angle cannot be used, as false features will be generated. Since then, some people have improved the algorithm, using the linear function of the distance from the ridge to the singular point as a pair filter, which can improve the enhancement effect to a certain extent. However, this algorithm also has some defects. Like the previous algorithm, when the quality of the fingerprint image is low, it is difficult to locate the singular point accurately and quickly.
The implementation method of the STFT method is to truncate the window function in the time domain, perform Fourier transform on the window signal, that is, obtain the Fourier transform at this moment, and constantly move the center of the window. The Fourier transforms at different times can be obtained, and the collection of these Fourier transforms is the short-time Fourier transform. The obtained graph is called a time-frequency graph.
It is found that the effect is better when the fingerprint image is enhanced using the STFT method . For the enhancement of the 2D fingerprint image in the STFT method, the conversion from the spatial domain to the frequency domain is shown in formula (11), among them represents the original image, represents the 2D window function, and the position of the 2D window is represented by and , and and represent the spatial frequency parameters.
4.4 Fingerprint image enhancement based on wavelet transform
Wavelet transform is a local time-frequency analysis algorithm, the time window and frequency window can be changed, but the size of these windows will not change . For a 2D fingerprint image, assuming its size is , which is represented by , the standard 2D discrete wavelet transform is decomposed as follows:
In the formula, is the wavelet decomposition stage, is the low-pass filter, and is the high-pass filter. It can be seen from the recurrence from equations (12)–(15) that only the low-pass component is decomposed each time, and the low-pass component CP 0 obtained by the previous-level decomposition is decomposed into four dimensions again in the next level decomposition. The exact same image components continue to be decomposed until the required decomposition level p is reached. represents the double low components of the original fingerprint image, that is, the low frequency components in the horizontal and vertical directions. represents the double high component of the original image, that is, the high-frequency components in the horizontal and vertical directions, while and represent the horizontal low-frequency component, the vertical high-frequency component, and the horizontal high-frequency component, and the vertical-low frequency component, respectively.
Image normalization is the most important part of image augmentation. Image normalization is to adjust the grayscale pixel value and variance value of the real fingerprint image to the expected range . The normalization process is as follows:
where is the average value of pixels, is the normalized fingerprint image quality average, is the grayscale average of each pixel in the original image, and is the quality variance of each pixel in the original image. and are the pre-set image grayscale mean and image variance values.
The locality principle points out  that the position of the fingerprint image represents the direction field, and the direction of the fingerprint ridges is basically consistent within a certain range. The Sobel operator is used to calculate the horizontal gradient value and the vertical gradient value of the pixel point of each fingerprint sub-block, and then the local direction of the sub-block centered on point 5 is calculated by using formulas (17)–(19).
where represents the local ridge line direction of the sub-block whose center point is at , and represents the total side length of the sub-block. Because the fingerprint image has a strong gradient feature, this feature can be used to separate the sub-images obtained after wavelet transform decomposition. The method divides each sub-image into sub-blocks first, takes , and then uses the formulas (20) and (21) to process.
where and are the gradient values of the sub-block pixels along the -axis and -axis, respectively, and and are the results obtained from the operations of formulas (17) and (18). After calculating the value of all sub-blocks, it is compared with the preset threshold . When , this sub-block is the background area, and the area mask is marked, otherwise the sub-block is the foreground area, and the area mask is marked.
5 Application results of fingerprint image fuzzy edge recognition algorithm in criminal technology
First, ten fingerprint samples A, B, C, D, E, F, G, H, I, and J are selected for fingerprint identification accuracy comparison. The identification method is the fuzzy method proposed in this work .
It can be seen from Figure 7 that there is still a large difference in fingerprint recognition accuracy between the two methods. By contrast, the recognition accuracy of fuzzy method is 13.2% higher than that of literature .
This study focuses on the introduction of the Sobel operator when using the fingerprint image fuzzy edge recognition algorithm. In order to confirm that the Sobel operator is the most efficient operator in edge detection, ten fingerprint samples in the criminal system and the Canny operator mentioned above are extracted to compare their efficiency with Prewitt operator. The ten sample numbers are: 001, 002, 003, 004, 005, 006, 007, 008, 009, and 010. The comparison results are shown in Figure 8.
In order to fully verify the application of fingerprint image fuzzy edge recognition algorithm in criminal technology, four different types of fingerprint images in criminal department fingerprint samples are selected as experimental objects, including bow, skip, bucket, and hybrid.
First, four different types of fingerprint images in the fingerprint samples of criminal departments were selected as the experimental objects, including the arch pattern, the skip pattern, the bucket pattern, and the mixed pattern. In order to ensure the rigor of the experiment, the Linux algorithm, FPGA algorithm and STM32 algorithm commonly used in the field of fingerprint recognition are added to this test, and compared with the algorithm proposed in this study. Using fingerprint image fuzzy edge recognition algorithm and Linux algorithm, FPGA algorithm, STM32 algorithm conducted fingerprint image recognition experiments. Using different types of fingerprint images, the fingerprint image recognition accuracy of several algorithms is compared, and the comparison results are shown in Table 2 .
|Image/frame||Fingerprint image blurred edge recognition/%||Linux algorithm/%||FPGA algorithm/%||STM32 algorithm/%|
It can be seen from Table 2 that the recognition accuracy based on the fingerprint image fuzzy edge recognition algorithm is significantly higher than that of other algorithms in the four different types of fingerprint image recognition. This also confirms that adding edge detection and blur reduction to the fingerprint recognition algorithm has a good effect.
In the criminal technology department, the fingerprint image processing of criminal suspects is related to the efficiency of the entire criminal work. In order to verify the specific effect of the fingerprint image fuzzy edge recognition algorithm, the Linux algorithm, FPGA algorithm, STM32 algorithm and the algorithm in this study mentioned above were analyzed from the three aspects of fingerprint image recognition speed (recognition amount), recognition accuracy rate, and matching accuracy rate, and experimental comparisons were carried out. Fingerprint samples were provided by criminal departments, and the specific test time is divided into hours and minutes.
Figure 9 shows the number of fingerprint images processed by different algorithms at different times. It can be seen from the histogram that with the increase in time, the number of fingerprints processed by these algorithms is also increasing. The processing quantity of the fingerprint image fuzzy edge recognition algorithm has always been in the leading position, and the other three algorithms fluctuated slightly, but not much.
It can be seen from Figure 10 that the recognition accuracy of several algorithms fluctuates with time. The recognition accuracy of fingerprint image fuzzy edge recognition algorithm has little fluctuation and high accuracy. The accuracy of the other three algorithms is lower than this algorithm, and the fluctuation is large, which shows that the fingerprint recognition effect of the fingerprint image fuzzy edge recognition algorithm is relatively good.
Figure 11 shows the accuracy of fingerprint matching after fingerprint identification for different algorithms in different time periods. The fingerprint matching accuracy fluctuates quite a bit, but this is a normal phenomenon. With the increase in time, the workload of fingerprint matching will be larger and larger, and the error will also increase. But in general, the fingerprint matching accuracy of the fingerprint image fuzzy edge recognition algorithm is still good.
The purpose of introducing the fingerprint image fuzzy edge recognition algorithm in criminal technology is to optimize and upgrade the fingerprint recognition system, so as to improve the level of criminal technology and improve the utilization rate of physical evidence. Figure 12 shows the comparison chart of the utilization ratio of physical evidence before and after the introduction of the fingerprint image fuzzy edge recognition algorithm.
It can be seen from Figure 12 that during these 10 days, the utilization of physical evidence in both methods showed a fluctuating trend, which is because the daily criminal workload was different. After the introduction of the fingerprint image fuzzy edge recognition algorithm, the utilization rate of physical evidence has been significantly improved, which is 7.04% higher than that before the introduction.
Criminal technology has a very important position in criminal work, which can improve the technical support for criminal investigators and bring convenience to the investigation work. However, with the rapid development of information technology, criminals’ criminal methods are becoming more and more advanced, which brings difficulties to criminal work, which requires innovation, optimization, and upgrading of criminal technology. In this study, the fuzzy edge recognition algorithm of fingerprint image is introduced in criminal technology, aiming to improve the level of criminal technology and improve the utilization rate of physical evidence in criminal work. After relevant experiments, the fuzzy edge recognition algorithm of fingerprint image proposed in this study has achieved good results in fingerprint image recognition, which provides an important reference value for the development of criminal technology.
Funding information: This study was supported by Program for Young Innovative Research Team in Shandong University of Political Science and Law and the popularize Research Project of Shandong University of Political Science and Law [Project No. 201713B].
Conflict of interest: The authors declare that there are no conflicts of interest regarding the publication of this article.
Data availability statement: The data that support the findings of this study are available from the corresponding author upon reasonable request.
 K. J. Wang, X. L. Xing, and H. T. Cui, “Recognition algorithm research of the touchless fingerprint images,” Acta Electron. Sin., vol. 45, no. 11, pp. 2633–2640, 2017.Search in Google Scholar
 W. U. Zhendong, Y. Wang, and J. Zhang, “Fouling and damaged fingerprint recognition based on deep learning,” Dianzi Yu Xinxi Xuebao/J. Electron. Inf. Technol., vol. 39, no. 7, pp. 1585–1591, 2017.Search in Google Scholar
 Q. Zhou, “Singular point region enhancement of fingerprint image based on symmetric phase consistency,” J. Intell. Fuzzy Syst., vol. 38, no. 1, pp. 1–9, 2020.10.3233/JIFS-179836Search in Google Scholar
 J. Xie, “A study of fingerprint recognition algorithm of networking embedded system,” Agro Food Ind. Hi Tech., vol. 28, no. 1, pp. 60–63, 2017.Search in Google Scholar
 K. Lee, J. Na, J. Sohn, S. Sohn, and S. Lee, “Image recognition algorithm for maintenance data digitization: CNN and FCN,” Trans. Korean Soc. Noise Vib. Eng., vol. 30, no. 2, pp. 136–142, 2020.10.5050/KSNVE.2020.30.2.136Search in Google Scholar
 C. Mao, W. Meng, and C. Shi, “A crop disease image recognition algorithm based on feature extraction and image segmentation,” Traitement du. Signal, vol. 37, no. 2, pp. 341–346, 2020.10.18280/ts.370221Search in Google Scholar
 X. Yan and X. Song, “An image recognition algorithm for defect detection of underground pipelines based on convolutional neural network,” Traitement du. Signal, vol. 37, no. 1, pp. 45–50, 2020.10.18280/ts.370106Search in Google Scholar
 A. I. Zazulin, “Functions of digital information and technologies in criminal proceedings,” Siberian Law Rev, vol. 17, no. 1, pp. 75–82, 2020.10.19073/2658-7602-2020-17-1-75-82Search in Google Scholar
 A. Vatsenko, “Application of computer technologies in criminalistic identification of personality (by the Example of DNA Analysis),” Bull. Sci. Pract., vol. 6, no. 5, pp. 409–412, 2020.10.33619/2414-2948/54/54Search in Google Scholar
 A. Corda and S. E. Lageson, “Disordered punishment: Workaround technologies of criminal records disclosure and the rise of a new penal entrepreneurialism,” Br. J. Criminol., vol. 60, no. 2, pp. 245–264, 2020.10.1093/bjc/azz039Search in Google Scholar
 K. Hadjimatheou, “Surveillance technologies, wrongful criminalisation, and the presumption of innocence,” Philos. Technol., vol. 30, no. 1, pp. 1–16, 2017.10.1007/s13347-016-0218-2Search in Google Scholar
 M. Tani, “Cyber-physical integrated analysis technology for criminal investigation support,” NEC Tech. J., vol. 12, no. 2, pp. 85–88, 2018.Search in Google Scholar
 A. V. Vardanyan and A. S. Andreev, “Unmanned aerial vehicles as a segment of digital technologies in the criminal and post-criminal reality,” Russian J. Criminol., vol. 12, no. 6, pp. 785–794, 2018.10.17150/2500-4255.2018.12(6).785-794Search in Google Scholar
 H. Kocak and A. N. Dandin, “The criminal effects of information technologies in social and administrative area,” Afyon Kocatepe Üniversitesi Sos. Bilimler Derg., vol. 19, no. 1, pp. 137–152, 2017.10.5578/jss.57198Search in Google Scholar
 M. Neloy, M. Das, and P. Barua, “An intelligent obstacle and edge recognition system using bug algorithm,” Am. Sci. Res. J. Eng. Technol. Sci., vol. 64, no. 1, pp. 133–143, 2020.Search in Google Scholar
 M. Kocevar, B. Kotnik, and A. Chowdhury, “Real-time fingerprint image enhancement with a two-stage algorithm and block-local normalization,” J. Real. Time Image Process., vol. 13, no. 4, pp. 773–782, 2017.10.1007/s11554-014-0440-zSearch in Google Scholar
 F. G. Hashad, O. Zahran, and E. El-Rabaie, “Fusion-based encryption scheme for cancelable fingerprint recognition,” Multimed. Tools Appl., vol. 78, no. 19, pp. 27351–27381, 2019.10.1007/s11042-019-7580-xSearch in Google Scholar
 B. T. Ahmed and O. Younis, “Fingerprint authentication using shark smell optimization algorithm,” UHD J. Sci. Technol., vol. 4, no. 2, pp. 28–39, 2020.10.21928/uhdjst.v4n2y2020.pp28-39Search in Google Scholar
 Y. Cao, W. Gong, and B. Zhang, “Two-dimensional compressed sensing using two-dimensional random permutation for image encryption-then-compression applications,” IEICE Trans. Fundam. Electron. Commun. Comput. Sci., vol. 101, no. 2, pp. 526–530, 2018.10.1587/transfun.E101.A.526Search in Google Scholar
 Y. Xu, G. Lu, and Y. Lu, “Fingerprint pore comparison using local features and spatial relations,” IEEE Trans. Circuits Syst. Video Technol., vol. 29, no. 10, pp. 2927–2940, 2019.10.1109/TCSVT.2018.2875147Search in Google Scholar
 Z. Liu, A. Basso, and L. Begeja, “Method and apparatus for automated analysis and identification of a person in image and video content,” Langmuir Acs J. Surf. Colloids, vol. 26, no. 10, pp. 6908–6918, 2017.Search in Google Scholar
 T. Sabharwal and R. Gupta, “Facial marks for enhancing facial recognition after plastic surgery,” Int. J. Inf. Technol., vol. 13, no. 1, pp. 391–396, 2021.10.1007/s41870-020-00566-xSearch in Google Scholar
 C. N. Vanitha, S. Suwathika, and A. Mathura, “Facial recognition processing using uniform pattern histogram with AI in multimedia applications,” Solid. State Technol., vol. 64, no. 2, pp. 788–798, 2021.Search in Google Scholar
© 2023 the author(s), published by De Gruyter
This work is licensed under the Creative Commons Attribution 4.0 International License.