JournalTOCs

Trends in Opto-Electro & Optical Communications
Number of Followers: 1

Full-text available via subscription

Subscription journal
ISSN (Print) 2347-9957 - ISSN (Online) 2231-0401
Published by STM Journals

[67 journals]

Adaptive Linear Gabor Response Pattern for Palm-print Recognition
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Poonam Poonia, Dr. Pawan K. Ajmera
  Pages: 1 - 12
  Abstract: The advancement of the information society has increased the demand for secure identity systems in a wide range of applications, including financial transactions, forensics, border control, computer security, and law enforcement. Biometrics is an alternative method for accurate and trustworthy authentication in a highly networked society. It is the science of using behavioural (gait, keystroke, signature, etc.) and physiological (face, ear, finger, palmprint, DNA etc.) attributes to validate an individual's identity. The special attributes on which the biometric recognition system is developed are known as modalities or identifiers. Recently, research in hand biometrics has shifted to examining the value of palm-prints in real-world contexts such as smartphones, ATMs, and notebooks. Palm prints are one of the most reliable biometrics available. The palm-print is considered as a bit of texture and texture-based feature extraction method has been presented during this work. This work proposes a palm-print recognition system that extracts textural characteristics by adjusting the optimum Gabor filter settings, named as adaptive linear Gabor response pattern (ALGRP). A distinct Gabor filter orientation is used to create a histogram for each sub-block of an image, and the sub-blocks of images are then concatenated to create a feature vector. The matching was made translation and rotation-invariant by using the normalized hamming distance. The proficiency of the proposed technique has been assessed on three publicly available palm-print databases. Test results exhibited that the method accomplished good performance with an EER of 0.094% and 0.13% on PolyU and IIT-Delhi databases respectively. We show that the proposed method outperforms the existing ones in terms of performance.
  PubDate: 2022-07-26
  Issue No: Vol. 12, No. 2 (2022)
Fingerprint Recognition for Crime Scenes Using Deep Learning
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: P. Mani Bharadwaj, J. Sai Teja, P. Srivally, B. Sai Reddy
  Pages: 13 - 18
  Abstract: Crime-scene fingerprint photos are crucial hints for resolving ongoing cases. Using deep machine learning and convolutional neural networks, we provide a comprehensive crime scene fingerprint identification method in this research (CNN). Precision photography and sophisticated physical and chemical processing techniques are used to collect images from crime scenes, which are then kept as databases. It can be challenging to categorize the photographs taken from the crime scene because they are frequently insufficient. The fingerprint images need to be pre-processed using the appropriate enhancement techniques, and features are then extracted from the fingerprint images. Pre-processed data features are sent into the CNN as training and testing input. According to testing findings on the database using Open CV-Python, it is 80% accurate to identify a partial or complete fingerprint in the criminal database
  PubDate: 2022-07-26
  Issue No: Vol. 12, No. 2 (2022)
LBP-HOG-Statistical-Wavelet Transform Feature Based MCA Classifier
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Sneha V. V
  Pages: 19 - 30
  Abstract: Face recognition systems use computer algorithms choose specific, recognizable features on a person’s face. With a mathematical representation, the information is compared to data on other faces acquired in a face recognition database. The distance between the eyes or the shape of the chin are two examples of these characteristics. The job of matching several facial modes, such as visible and near infrared images, is known as heterogeneous face recognition. The main problems with HFR are the insufficient training samples and the severe lack of modality compatibility. Since the same person’s face images from several image modalities are linked to the same face object, there need to be a mutual component that reflects the intrinsic features of the face that are independent of the image modalities. To infer the mutual components for reliable heterogeneous face recognition, a Mutual Component Analysis (MCA) is proposed in this study and also tried other feature extraction methods to compare the performance. This performance is shown by using NB classifier
  PubDate: 2022-09-21
  Issue No: Vol. 12, No. 2 (2022)
Recognition of Thyroid Nodules Using Hierarchical Temporal Awareness
Networking Scanning
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Vaibhav Srivastava
  Pages: 31 - 35
  Abstract: Contrast-enhanced ultrasonography (CEUS), a preferred imaging technique for thyroid nodule diagnosis, is able to reveal the vascular distribution within a thyroid nodule right away. With the aim of mining pathologically-related enhancing dynamics and creating predictions in one step without taking into account a native diagnostic dependency, a number of learning-based algorithms have recently been created. In clinics, separating benign from malignant nodules is always done before identifying pathological types. In the current study, we introduce a novel hierarchical temporal attention network (HiTAN), which combines dynamic enhanced deep features and nodule identification into the a complex hierarchy.This method, in particular, orders a two-stage classification job for diagnosing nodules, with diagnostic reliance modelled by Gated Recurrent Units (GRUs). We also create a local-to-global temporal aggregation (LGTA) operator along the hierarchical prediction path to accomplish a full temporal fusion. Local temporal information is defined precisely as recurrent enhancement patterns in the perfusion representation direction identified at the division level.
  PubDate: 2022-10-27
  Issue No: Vol. 12, No. 2 (2022)
Non-linear Photonic Crystals and their Applications: A Review
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Anirudh Banerjee
  Pages: 36 - 39
  Abstract: The nonlinear photonic crystals (NLPCs) are periodic material structures in which nonlinear materials are used for photonic structure formation. In nonlinear photonic crystals, the optical response mainly depends on the intensity of the light beam that propagates through the photonic crystal. These structures show new optical properties with improved or enhanced or new functionalities that cannot be observed in linear photonic crystals. In addition to this, using nonlinear materials in photonic crystal formation can offer additional control of the response in devices based on nonlinear photonic crystals. Therefore, nonlinear photonic crystals are at the forefront in optics research. In this paper, recent research works and applications in the field of nonlinear photonic crystals are reviewed. Works related to trapping light inside the nonlinear 1-D photonic crystal, group velocity behavior, advancement in optical processes by storing light, generation of anomalous band gaps, fabrication of highly efficient and small size devices, design of sensor to detect liquid analytes, study of properties of nonlinear GeO2 doped photonic crystal fiber, study of Kerr nonlinear photonic crystals, designing highly non-linear photonic crystal based optical fiber made from polystyrene, supercontinuum generation, nonlinear photonic crystal fiber with circular air rings, optical limiters based on a photonic crystal with embedded nonlinear rods, generation of SH optical vortices, nonlinear photonic crystal asymmetric hybrid Fabry-Perot resonator, Bragg reflector based on strip waveguide were reviewed in this paper.
  PubDate: 2022-10-27
  Issue No: Vol. 12, No. 2 (2022)
Digital Entry of Bank Related Slips Using Character Recognition
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Harsh Ahuja, Aditya R.
  Pages: 30 - 35
  Abstract: Standing in long queues in bank for small work like depositing the money is very frustrating and also wastes a lot of time. The bank employee handles all the work such as making the entry of money deposited or credit from the account manually by typing information such as account number, amount, etc. and due this creates long queues in banks for such small tasks. Thus, we have come up with a solution which saves time of both, the customer and the bank employees. In this paper we are going to present an idea, to use a camera, to read the entries in the deposit slips of bank, such as account no., amount, count of each denomination, etc. and enter it in the database. This concept is implemented using Handwritten text recognition (HCR) which is a basic machine learning technique using Convolutional Neural Network. Here, concepts of image processing are also used to enhance the quality of image captured to ensure that all the digits are recognised accurately.
  PubDate: 2022-06-22
  Issue No: Vol. 12, No. 1 (2022)