Machine Learning Approaches for Gender Identification Using Fingerprint Biometrics: Role of Ridge Flow, Minutiae, and Multi-resolution DWT Features | Chapter 2 | New Horizons of Science, Technology and Culture Vol. 3

Fingerprints serve as an extraordinary biological signature that encapsulates both identity and subtle gender-specific characteristics through their complex structural and spectral properties. This study introduces an advanced computational framework for gender classification by synergistically combining three distinct fingerprint feature domains: ridge geometry for macroscopic pattern analysis, minutiae distribution for microscopic feature examination, and frequency decomposition through sophisticated wavelet transformation. The methodology processes high-resolution fingerprint images through a multi-stage analytical pipeline that precisely quantifies ridge length variations (capturing minimum, maximum, and average measurements), systematically enumerates minutiae points (including ridge terminations and bifurcations), and performs multi-resolution spectral analysis using a six-level discrete wavelet transform to isolate discriminative frequency components. Validated on a carefully balanced dataset of 100 subjects (50 males and 50 females), the extracted features are intelligently organised into gender-specific clusters through an optimised stratification process, yielding an impressive overall classification accuracy of 88.28%. Notably, the right ring finger demonstrated exceptional diagnostic performance with 95.46% accuracy, a finding consistent with established embryological research on androgen-influenced ridge formation patterns. The technical sophistication of this approach lies in its ability to achieve high accuracy without relying on computationally intensive deep learning architectures, making it particularly suitable for real-world applications where efficiency is crucial. Beyond its immediate results, this research opens promising avenues for future investigation, including the incorporation of additional discriminative features such as sweat pore distribution and three-dimensional ridge curvature analysis, as well as expansion to larger, more diverse demographic datasets to enhance generalizability. By demonstrating that fingerprints contain a wealth of underutilised gender information, this work makes a significant contribution to the field of soft biometrics, with important implications for forensic science, security systems, and demographic research, while simultaneously establishing a foundation for future exploration of ancillary biometric markers embedded within fingerprint patterns. The balanced integration of robust methodology, empirical validation, and practical applicability positions this research as a valuable reference point for both academic investigation and applied biometric solutions, bridging the gap between theoretical innovation and real-world implementation in the evolving landscape of gender classification technologies.

 

Author(s) Details

Sayed Abulhasan Quadri
SECAB Institute of Engineering and Technology, Vijayapura, India.

 

Chandrakant P. Divate
SECAB Institute of Engineering and Technology, Vijayapura, India.

Tabasum Guledgudd
SECAB Institute of Engineering and Technology, Vijayapura, India.

Sayed Abdulhayan
PACE College, Mangalore, India.

 

Please see the book here:- https://doi.org/10.9734/bpi/nhstc/v3/5745

Unlocking Fingerprint Intelligence: Extracting Ridge, Minutiae, and DWT Features | Chapter 7 | New Horizons of Science, Technology and Culture Vol. 2

A fingerprint image captures the unique spatial pattern of ridges and valleys on the human fingertip, serving as a powerful and widely adopted A fingerprint image is a digital representation of the intricate and unique spatial configuration of ridges and valleys found on the human fingertip. These patterns are distinct for every individual and remain virtually unchanged throughout a person’s life, making fingerprints one of the most reliable forms of biometric identification. Their inherent individuality and permanence have made fingerprint recognition systems indispensable across a wide range of applications, including forensic investigations, national identity verification programs, secure access control systems, and personal device authentication.

 

This chapter, inspired by advancements in biometric sciences, anthropometry, and computational pattern recognition, investigates refined and more efficient methods of extracting rich and diverse features from fingerprint images. The emphasis lies on enhancing the accuracy and reliability of classification and identification tasks by focusing on extracting ridge information, minutiae patterns, and Discrete Wavelet Transform (DWT) features. These advanced features not only facilitate accurate fingerprint matching but also enable the derivation of soft biometric indicators such as gender, age, and potentially even blood type. This opens up promising avenues for the development of lightweight, non-invasive, and cost-effective biometric classification systems, which are particularly valuable in resource-constrained settings.

 

Fingerprint-based systems offer several key advantages over other biometric modalities, such as iris scans, facial recognition, or voice analysis. They typically require less storage space, involve simpler data acquisition procedures, and demand relatively low computational resources. These attributes make fingerprint recognition an ideal candidate for large-scale biometric applications, especially in densely populated or economically limited regions. The methodology explored in this chapter revolves around an automated framework that systematically analyses the spatial and structural features of fingerprints. It leverages both spatial domain and frequency domain analysis techniques to achieve a high-fidelity representation of fingerprint traits. By focusing on the precise extraction of ridge flows and minutiae points such as bifurcations and endings, and further enriching this representation with wavelet-based descriptors, the approach ensures robustness across various acquisition conditions, including variations in scanner types, resolutions, lighting conditions, and finger orientation.

 

Unlike traditional systems that rely solely on features such as ridge counts, thickness, and basic minutiae, the proposed approach employs enhanced feature extraction strategies that significantly improve identification accuracy. Through the application of Discrete Wavelet Transform, fingerprint images are analysed at multiple resolutions, enabling the capture of both global and fine-grained local details. This multiresolution capability allows the system to identify subtle fingerprint variations that might otherwise go undetected, making the overall classification more precise and resilient. Further, ridge structure is assessed in terms of quantifiable metrics like minimum, maximum, and average ridge lengths across the fingerprint. These measurements add another layer of distinguishing information, especially useful in scenarios where individuals have similar minutiae layouts but different ridge formations. In addition to these features, a rich set of minutiae descriptors-such as the number of ridge bifurcations, ridge endings, and total minutiae points-is extracted to enhance the discriminatory capability of the system.

 

By integrating these diverse features-spatial, geometric, and frequency-based-into a cohesive fingerprint recognition pipeline, this chapter presents a powerful and holistic approach to automated fingerprint classification. The comprehensive feature representation facilitates accurate and efficient matching of test fingerprint samples with stored templates, making the system suitable for use in high-security environments, law enforcement databases, and scalable authentication solutions.

 

In essence, this chapter contributes to the ongoing evolution of biometric technologies by introducing refined feature extraction techniques that enhance the reliability and versatility of fingerprint-based systems. The emphasis on improved accuracy, computational efficiency, and adaptability underscores the relevance of these techniques in shaping the future of secure and intelligent biometric identification.

 

Author(s) Details

 

Sayed Abulhasan Quadri
SECAB Institute of Engineering and Technology, Vijayapura, India.

 

Chandrakant P. Divate
SECAB Institute of Engineering and Technology, Vijayapura, India.

 

Tabasum Guledgudd
SECAB Institute of Engineering and Technology, Vijayapura, India.

 

Sayed Abdulhayan
PACE College, Mangalore, India.

 

 

Please see the book here:- https://doi.org/10.9734/bpi/nhstc/v2/5744

Application of the Novel Wavelet Ann Method for Segregating Bearing Faults in Three-phase Induction Motor | Chapter 2 | Current Approaches in Engineering Research and Technology Vol. 10

Induction motors are a critical component of many industrial processes and are frequently integrated into commercially available equipment. Safety, reliability, efficiency, and performance are some of the major concerns of induction motors.

Three-phase induction motors are the ‘workhorses’ of industry and are the most widely used electrical machines. For this reason, the detection of motor failures is very important. Bearing problems are one of the major causes of drive failures. Early detection of bearing faults allows replacements of the bearings rather than replacement of the motor. The present contribution reports experimental results for monitoring bearing faults in induction motors. Motor line currents have been analyzed using modern signal processing and data reduction tools combining Park’s Transformation and Discrete Wavelet Transform (DWT). Feed Forward Artificial Neural (FFANN) based data classification tool is used for fault characterization based on DWT features extracted from Park’s Current Vector Pattern. An online algorithm is tested successfully on a three-phase induction motor and experimental results are presented to demonstrate the effectiveness of the proposed method which can reliably distinguish the inner race and outer race defects of the bearing. It is observed that for five processing elements in the hidden layer, 100% classification accuracy is achieved for healthy and faulty conditions.

Experimental results are presented to demonstrate the effectiveness of the proposed methodology. The study concluded that the proposed methodology is useful in identifying inner race and outer race defects of bearings in induction motors with 100   percent accuracy.

 

Author (s) Details

Anjali. U Jawadekar
Department of Electrical Engineering, S.S.G.M. College of Engineering Shegaon, India.

 

Mukesh Ravindra Chavan
Department of Electrical Engineering, S.S.G.M. College of Engineering Shegaon, India.

 

Please see the book here:- https://doi.org/10.9734/bpi/caert/v10/2639

Elucidation of Visual Motor Imagery EEG Data Using Feature Streamlining with Machine Learning | Chapter 8 | Mathematics and Computer Science: Contemporary Developments Vol. 9

Visual motor imagery (VMI) is a cognitive process where individuals visualize performing a motor task without actual movement. Electroencephalography (EEG) data is often used to analyze brain activity associated with VMI. However, the high dimensionality and complexity of EEG data pose challenges for effective analysis. This study focuses on streamlining EEG features using advanced machine-learning techniques to enhance the accuracy and efficiency of VMI classification. We applied feature selection and extraction methods to identify the most relevant features from EEG signals, followed by the implementation of various machine learning algorithms to classify VMI tasks. Our results demonstrate that feature streamlining significantly reduces computational load while maintaining high classification accuracy. The streamlined features, combined with optimized machine learning models, provide a robust framework for interpreting VMI-related EEG data, paving the way for improved brain-computer interface (BCI) systems. This approach has potential applications in neurorehabilitation, cognitive training, and enhancing user interaction in BCI technologies. Classifying motor imagery in the EEG is crucial for identifying serious illnesses. The diversity of the motor imagery EEG data hampered the rate of categorization. The motor imagery EEG classification rate is increased using the feature optimization procedure. A deep neural network-based classifier for motor imagery EEG categorization was suggested in this article. The design deep neural network is a three-layer neural network model that incorporates the teacher learning-based optimization and feature optimization technique. The EEG data's noise and artefacts are reduced using a teacher learning-based optimization technique, which also enhances the input vectors for DNN. The suggested approach has been tested on datasets from the third and fourth BCI competitions and has been simulated in MATLAB settings. The evaluation's findings indicate that the suggested technique is quite effective at compressing the current motor.

 

Author (s) Details

Virendra Kumar Tiwari
Lakshmi Narain College of Technology (MCA), Bhopal, India.

 

Priyanka Singh
Lakshmi Narain College of Technology Excellence, Bhopal, India.

 

Vinita Keer
Lakshmi Narain College of Technology Excellence, Bhopal, India.

 

Gaurav Kishor Saxena
Lakshmi Narain College of Technology (MCA), Bhopal, India.

 

Sandeep Dubey
Lakshmi Narain College of Technology Excellence, Bhopal, India.

 

Please see the book here:- https://doi.org/10.9734/bpi/mcscd/v9/3416

Application of the Novel Wavelet Ann Method for Segregating Bearing Faults in Three-phase Induction Motor | Chapter 2 | Current Approaches in Engineering Research and Technology Vol. 10

 

Induction motors are a critical component of many industrial processes and are frequently integrated into commercially available equipment. Safety, reliability, efficiency, and performance are some of the major concerns of induction motors.
Three-phase induction motors are the ‘workhorses’ of industry and are the most widely used electrical machines. For this reason, the detection of motor failures is very important. Bearing problems are one of the major causes of drive failures. Early detection of bearing faults allows replacements of the bearings rather than replacement of the motor. The present contribution reports experimental results for monitoring bearing faults in induction motors. Motor line currents have been analyzed using modern signal processing and data reduction tools combining Park’s Transformation and Discrete Wavelet Transform (DWT). Feed Forward Artificial Neural (FFANN) based data classification tool is used for fault characterization based on DWT features extracted from Park’s Current Vector Pattern. An online algorithm is tested successfully on a three-phase induction motor and experimental results are presented to demonstrate the effectiveness of the proposed method which can reliably distinguish the inner race and outer race defects of the bearing. It is observed that for five processing elements in the hidden layer, 100% classification accuracy is achieved for healthy and faulty conditions.
Experimental results are presented to demonstrate the effectiveness of the proposed methodology. The study concluded that the proposed methodology is useful in identifying inner race and outer race defects of bearings in induction motors with 100   percent accuracy.

 

Author(s)details:-

 

Dr. Anjali. U Jawadekar
Department of Electrical Engineering, S.S.G.M. College of Engineering Shegaon, India.

 

Mukesh Ravindra Chavan
Department of Electrical Engineering, S.S.G.M. College of Engineering Shegaon, India.

 

Please See the book here :- https://doi.org/10.9734/bpi/caert/v10/2

Determination of Power Quality Events Using DWT and DTCWT Wavelets | Chapter 3 | Research Highlights in Science and Technology Vol. 8

 This chaoter judge PQ event algorithm seeing dual tree wavelets and the results are distinguished with wavelets. Power quality disturbances (PQ) are produce with the growth of nonlinear loads, to a degree solid-state switching supplies, electronically switched ploys, industrial rectifiers, and inverters. Warped voltage waveforms unfavorably affect electronic ploys, such as electrical method failures, disk crashes, and microcontroller breakdowns It is shown that the shift invariant feature of dual tree wavelets is beneficial for classifying events in a variety of PQ signals accompanying non-stationary occurrences. The strength levels of the Dual Tree Complex Wavelet Transform (DTCWT) are able to distinguish between many occurrences as well as various sags, swells, tone of sound, interrupts, and flickers.  The classification veracity using DTCWT energy bands is enhanced by more than 90%. DTCWT filters selected in this place paper are suitable for PQ event discovery as well as classification. The recommendation PQ signal with PQ event to a degree sag, swell, transient, harmonics and flicker happen at random intervals in actual time for action or event. The feature detection algorithm needs to discover the presence of event from the physiognomy detected from sub bands and too characterize the occurrence by providing information on time of incident, event duration, force and gradient.

Author(s) Details:

E. Prathibha,
Adama Science and Technology University, Ethiopia.

A. Manjunatha,
Sri Krishna Institute of Technology, Bangalore, Karnataka, India.

R. Likhitha,
Nitte Meenakshi Institute of Technology, India.

Md. Irfan Ali,
Adama Science and Technology University, Ethiopia.

Please see the link here: https://stm.bookpi.org/RHST-V8/article/view/11539

Watermarking the Digital Image Using Hybrid Approach | Chapter 7 | Research Developments in Science and Technology Vol. 9

Digital watermarking capabilities can now be improved in various ways, including resilience, imperceptibility, authentication, tamper-proofing, etc. This essay will concentrate on a novel method for optimally robustly incorporating a transparent digital watermark onto an original image (cover content). Depending on the methods used for error control, determine how to extract the high-quality digital watermark from the flagged image. How to protect the watermark from the impacts that the watermarked image's processing produces. How to identify and rebuild the watermarked document's tamper region image based on the cutting-edge watermarking method. We presented a hybrid strategy (which combines the DWT, SVD, and NN) to create a new intelligent model for digital watermarking that will be utilised to safeguard the copyright of the digital content and to find and recover the tampered/forged regions in the watermarked image. The experimental findings demonstrate the usefulness of the suggested system and its superior attack robustness.

Author (s) Details

B. Manjula
Department of Computer Science, Kakatiya University, Warangal, Telangana, India

R. Lakshman Naik
Department of IT, KUCE&T, Kakatiya University, Warangal, Telangana, India.

V. Bapuji
Department of MCA, Vaageswari College of Engineering. Karimnagar, Telangana, India.

View Book :- https://stm.bookpi.org/RDST-V9/article/view/7552

A Study on Speaker Independent Emotion Recognition from Speech Signals| Chapter 2 | Advanced Aspects of Engineering Research Vol. 12

 In this work, the spectral feature MFCC is used for high accuracy, and the prosody feature Pitch is used in conjunction with two other features, Cepstrum and DWT, to create an Emotion- Specific Feature Set. In recent years, a great study has been conducted to improve human-machine interaction in the area of Speech Emotion Recognition. The Speaker's age, gender, and emotional state are all revealed in his or her speech. Emotion recognition is the difficult challenge of recognising a single emotion from a speaker. The database in question is Telugu-Database, which covers four emotions: joyful, angry, sad, and neutral, and is prompted by two male and female speakers. Different combinations of traits are utilised to identify the associated emotion, and these features are referred to as Emotionspecific characteristics. When these characteristics are taken into consideration, the rate of combination identification improves. The DWT, Cepstrum, MFCC, and MFCC features are used to extract function information. as well as Pitch After feature extraction, the data is classified using a back-propagation neural network technique, and the results are reviewed. The study found that increasing the number of nodes in the network and the number of iterations increases the recognition rate above 90%, that combining feature sets gives a better emotion recognition rate than using individual feature sets, and that the feature set combination DWT+Pitch+Cepstrum produced an individual emotion recognition rate of over 95%.

Author (s) Details

Dr. B. Rajasekhar
JNTUA, Anantapuramu, India.

M. Kamaraju
Department of Electronics and Communication Engineering, Gudlavalleru Engineering College, Gudlavalleru, India.

V. Sumalatha
Department of Electronics and Communication Engineering, JNTU College of Engineering, Anantapuramu, India.

View Book :-  https://stm.bookpi.org/AAER-V12/article/view/1279

Analysis of Different Filtering Methods for Preprocessing and GLCM Feature Extraction Using Wavelet in Mammogram Images | Chapter 15 | Innovations in Medicine and Medical Research Vol. 3

Breast cancer is a stand-out surrounded by the most widely perceived diseases and has a high rate of mortality around the world, significantly risking the health of the females. Among existing all modalities of medical scans, mammography is the most preferred modality for preliminary examination of breast cancer. To assist radiologists, a computer-aided diagnosis (CAD) is enhancing and important medical systems for mammographic lesion analysis. In mammogram images, micro-calcifications are one of the imperative signs for breast cancer detection. Mammographic medical scan may present unwanted noise and CAD systems are very sensitive to noise. Early stage detection for any medical image analysis application like brain tumor detection, breast cancer detection is considered as an important step. Micro calcification is small calcium deposits in the breast region and mammogram images are of low contrast. Thus, in this work, different types of filtering techniques used for noise reduction and image enhancement for medical image processing are analyzed on mini-MIAS mammogram image databases. Anisotropic diffusion with wavelet filtering method shows best results for enhancement and noise removal of the image. This filtered image is segmented; region of interest (ROI) is extracted through global Thresholding technique with discrete wavelet transform (DWT). Gray level cooccurrence matrix is used to extract the important features. Here, seven features are extracted for different categories of micro calcified images like normal, benign, malignant. Results show that from extracted features the values of malignant and micro calcified images are same whereas normal and benign are same. This proposed methodology can help to categorize different classes of images. 

Author(s) Details

Neha N. Ganvir
Department of Electronics Engineering, Sinhgad Institute of Technology and Science (SITS), Narhe, Sinhgad Technical Education Society (STES), Pune, India.  

Dr. D. M. Yadav
Pune University, India.

View Book :- http://bp.bookpi.org/index.php/bpi/catalog/book/178