Papers by Jitendra Chaudhari
Plant Diseases Detection and Classification Using Machine Learning, Deep Learning, Spectroscopy
Lecture notes in networks and systems, 2023
International Journal of Integrated Engineering, Jun 21, 2022
In surgery, minimally invasive techniques (MIT) are generally safer than open surgery and typical... more In surgery, minimally invasive techniques (MIT) are generally safer than open surgery and typically faster recovery. This biological photographic surgery has increased interest in LED-based treatments. LEDs have now become essential in medical and dental technology. But the demands placed on these devices are extreme. Minimal size, large and application-specific colour rendering index, efficient temperature control, usability, and excellent disinfection opportunities are all important. An endoscopy is a process where the doctor uses specialized instruments to look and operate on the body's internal parts like organs and vessels. It allows experts to view disease within the body without making a large body cut. Endoscopy surgery requires an average of 45 minutes. It involves the use of an external illumination source. Considering intense illuminance and colour rendering index (Ra) greater than 95, Xenon, Halogen, and Metal halide lamps are recently used as an illumination source in minimally invasive techniques. These sources emit a broad visible frequency spectrum,
Highly-selective Ridge Gap Waveguide Based Filters for Multi-band Satellite Applications
Progress in Electromagnetics Research M, 2023
Engineering Computations, Jun 6, 2020
Purpose-In clinical analysis, medical image segmentation is an important step to study the anatom... more Purpose-In clinical analysis, medical image segmentation is an important step to study the anatomical structure. This helps to diagnose and classify abnormality in the image. The wide variations in the image modality and limitations in the acquisition process of instruments make this segmentation challenging. This paper aims to propose a semi-automatic model to tackle these challenges and to segment medical images. Design/methodology/approach-The authors propose Legendre polynomial-based active contour to segment region of interest (ROI) from the noisy, low-resolution and inhomogeneous medical images using the soft computing and multi-resolution framework. In the first phase, initial segmentation (i.e. prior clustering) is obtained from low-resolution medical images using fuzzy C-mean (FCM) clustering and noise is suppressed using wavelet energy-based multi-resolution approach. In the second phase, resultant segmentation is obtained using the Legendre polynomialbased level set approach. Findings-The proposed model is tested on different medical images such as x-ray images for brain tumor identification, magnetic resonance imaging (MRI), spine images, blood cells and blood vessels. The rigorous analysis of the model is carried out by calculating the improvement against noise, required processing time and accuracy of the segmentation. The comparative analysis concludes that the proposed model withstands the noise and succeeds to segment any type of medical modality achieving an average accuracy of 99.57%. Originality/value-The proposed design is an improvement to the Legendre level set (L2S) model. The integration of FCM and wavelet transform in L2S makes model insensitive to noise and intensity inhomogeneity and hence it succeeds to segment ROI from a wide variety of medical images even for the images where L2S failed to segment them.
Circuit World, Jul 15, 2020
Purpose-Synthetic aperture radar (SAR) imaging is the most computational intensive algorithm and ... more Purpose-Synthetic aperture radar (SAR) imaging is the most computational intensive algorithm and this makes its implementation challenging for real-time application. This paper aims to present the chirp-scaling algorithm (CSA) for real-time SAR applications, using advanced field programmable gate array (FPGA) processor. Design/methodology/approach-A chirp signal is generated and compressed using range Doppler algorithm in MATAB for validation. Fast Fourier transform (FFT) and multiplication operations with complex data types are the major units requiring heavy computation. Therefore, hardware acceleration is proposed and implemented on NEON-FPGA processor using NE10 and CEPHES library. Findings-The heuristic analysis of the algorithm using timing analysis and resource usage is presented. It has been observed that FFT execution time is reduced by 61% by boosting the performance of the algorithm and speed of multiplication operation has been doubled because of the optimization. Originality/value-Very few literatures have presented the FPGA-based SAR imaging implementation, where analysis of windowing technique was a major interest. This is a unique approach to implement the SAR CSA using a hybrid approach of hardware-software integration on Zynq FPGA. The timing analysis propagates that it is suitable to use this model for real-time SAR applications.
Wavelet features embedded convolutional neural network for multiscale ear recognition
Journal of Electronic Imaging, Aug 28, 2020
Abstract. The ear has emerged as a new biometric trait to recognize humans from their profile fac... more Abstract. The ear has emerged as a new biometric trait to recognize humans from their profile faces. Stability over the years, noninvasive capturing process, expressionless images, and significant variation in shape among individuals make the ear a suitable choice when compared with other biometrics. Convolutional neural network (CNN)’s capability to learn and discriminate specific features irrespective of image variation makes it the most suitable choice for ear recognition in comparison to local geometrical feature extraction methods. The recognition performance affecting factors such as occlusion, image resolution, and head rotation during ear acquisition in an uncontrolled environment makes it a challenging task, and the use of spatial features only in CNN limits the recognition rate. We explored the various CNN configurations and propose the spectral–spatial feature-based CNN. An embedding algorithm is proposed to fuse multilevel spectral information from the image domain with spatial features extracted at each deep layer of the CNN network. The poor convergence problem of CNN is tackled by introducing batch normalization after every convolution. The analysis of the result shows that the proposed framework is superior among all CNN achieving 98.15% and 78.88% accuracy on the Annotated Web Ears with 1000 images and earVN1.0 with 28,412 images, respectively. In addition to fine-tuning and configuring the layers of CNN, the fusion of missing spectral features and spatial features can strengthen the CNN.
Design of Membrane Based Unit Cell of Large Reflectarray Antenna for SAR System
IIUM Engineering Journal, Jan 4, 2022
Palmprints can be characterized by their texture and the patterns of that texture dominate in a v... more Palmprints can be characterized by their texture and the patterns of that texture dominate in a vertical direction. Therefore, the energy of the coefficients in the transform domain is more concentrated in the vertical sideband. Using this idea, this paper proposes the characterization of the texture features of the palmprint using zerocrossing signatures based on the dyadic discrete wavelet transform (DWT) to effectively identify an individual. A zero-crossing signature of 4 x 256 was generated from the lower four resolution levels of dyadic DWT in the enrolment process and stored in the database to identify the person in recognition mode. Euclidean distance was determined to find the best fit for query palmprints zero-crossing signature from the dataset. The proposed algorithm was tested on the PolyU dataset containing 6000 multi-spectral images. The proposed algorithm achieved 96.27% accuracy with a lower recognition time of 0.76 seconds. ABSTRAK: Pengesan Tapak Tangan boleh dikategorikan berdasarkan ciri-ciri tekstur dan corak pada tekstur yang didominasi pada garis tegak. Oleh itu, pekali tenaga di kawasan transformasi adalah lebih penuh pada jalur-sisi menegak. Berdasarkan idea ini, cadangan kajian ini adalah berdasarkan ciri-ciri tekstur pada tapak tangan dan tanda pengenalan sifar-silang melalui transformasi gelombang kecil diadik yang diskret (DWT) bagi mengecam individu. Pada mod pengecaman, tanda pengenalan sifar-silang 4 x 256 yang terhasil daripada tahap diadik resolusi empat terendah DWT digunakan dalam proses kemasukan dan simpanan di pangkalan data bagi mengenal pasti individu. Jarak Euklidan yang terhasil turut digunakan bagi memperoleh padanan tapak tangan paling sesuai melalui tanda pengenalan sifar-silang dari set data. Algoritma yang dicadangkan ini diuji pada set data PolyU yang mengandungi 6000 imej pelbagaispektrum. Algoritma yang dicadangkan ini berjaya mencapai ketepatan sebanyak 96.27% dengan durasi pengecaman berkurang sebanyak 0.76 saat.
The Open Biomedical Engineering Journal, Dec 31, 2021
Background: The advancement in convolutional neural network (CNN) has reduced the burden of exper... more Background: The advancement in convolutional neural network (CNN) has reduced the burden of experts using the computer-aided diagnosis of human breast cancer. However, most CNN networks use spatial features only. The inherent texture structure present in histopathological images plays an important role in distinguishing malignant tissues. This paper proposes an alternate CNN network that integrates Local Binary Pattern (LBP) based texture information with CNN features. Methods: The study propagates that LBP provides the most robust rotation, and translation-invariant features in comparison with other texture feature extractors. Therefore, a formulation of LBP in context of convolution operation is presented and used in the proposed CNN network. A nontrainable fixed set binary convolutional filters representing LBP features are combined with trainable convolution filters to approximate the response of the convolution layer. A CNN architecture guided by LBP features is used to classify the histopathological images.
Development of Biomass Green Champo Leaf DRAM Memory Cell
Smart innovation, systems and technologies, 2021
Supervised Feature Reduction Technique for Biometric Recognition Using Palm print Modalities
Bioscience biotechnology research communications, Mar 25, 2020
International journal of engineering research and technology, Nov 5, 2015
In this article, compact and wideband directional coupler has been proposed based on substrate in... more In this article, compact and wideband directional coupler has been proposed based on substrate integrated waveguide technique for X-band applications. The bandwidth of directional coupler has enlarged by tapering the coupling section. This coupler consists of two narrow apertures on the common broadside wall of two adjacent SIWs and four microstrips to waveguide transition line. Attractive features including compact size and planar form make this coupler structure easily integrated in antenna beam-forming networks. The coupling is about 7 dB at 9 GHz to 12 GHz frequency, the isolation is below 15dB over the frequency range of 9-12 GHz, and the return loss is better than 15dB. Design considerations and results are discussed and presented. A simulation has been carried out by Ansoft High frequency structure simulator (HFSS).
Comparative study of radon based low resolution palmprint image matching
This paper presents comparative study of palmprint matching algorithms for low resolution and noi... more This paper presents comparative study of palmprint matching algorithms for low resolution and noisy images. The principal lines and wrinkles are the only features easily extractable under low resolution. Therefore widely used Radon based approach has been studied and presented in this paper. Based on the computational complexity and fast matching, four different approaches are studied.
Progress in Electromagnetics Research M, 2021
A band-pass filter using spoof surface plasmon polaritons (SSPPs) and half-mode substrate integra... more A band-pass filter using spoof surface plasmon polaritons (SSPPs) and half-mode substrate integrated waveguide (HMSIW) for Ka-band RADAR application is proposed. In order to achieve the band-pass response, an HMSIW structure with high pass response and SSPPs with band-stop response are combined. Moreover, to investigate effects of geometric dimensions on the frequency characteristics of the proposed band-pass filter are examined by parametric analysis. It has been observed that lower cutoff and upper frequencies can be individually controlled just by changing the structural parameters. High Frequency Structure Simulator (HFSS) software was utilized to simulate the proposed structure. HFSS is the simulation tool for complex 3-D geometries and uses the finite element method (FEM). To validate the functionality, the proposed band-pass filter is fabricated on the dielectric material RT duroid 5880 with the dielectric constant ε r = 2.2, height h = 0.508 mm, and dissipation factor tan δ = 4× 10 −4. The measured result shows return loss better than −10 dB and insertion loss less than 1.25 dB with the 3 dB fractional bandwidth (FBW) of 44.02% at the center frequency of 7.95 GHz.
HMSIW- and QMSIW-based antenna for wireless communication application
Circuit World, Jan 25, 2021
Purpose The purpose of this paper is to design and develop half-mode substrate-integrated wavegui... more Purpose The purpose of this paper is to design and develop half-mode substrate-integrated waveguide (HMSIW)- and quarter-mode substrate-integrated waveguide (QMSIW)-based antennas for wireless communication application. The developed antennas offer advantages in terms of compactness, high gain and better isolation between the ports. Design/methodology/approach Initially, the tri-band substrate-integrated waveguide-based antenna is designed using a slot on the ground plane. Then, the same structure has been bisected into two parts for the development of the HMSIW structure. Again the concept of the slot is used for the realization of a dual-band antenna. QMSIW-based structure is designed with further dividing HMSIW structure into two parts. Simulation has been carried out with the use of a high-frequency structure simulator (HFSS) software, which used a finite element-based solver for the full-wave analysis. Findings The proposed HMSIW-based dual-band antenna resonates at two different frequencies, namely, 5.81 GHz with 4.5 dBi gain and at 6.19 GHz with 6.8 dBi gain. Isolation between two ports is 20 dB. The overall dimensions of the proposed model are 0.39 λ × 0.39 λ. Similarly, QMSIW-based antenna is resonated at 5.66 GHz of the frequency with the 3 dBi gain. Frequency tuning is also carried out with the change in the slot dimension to use the proposed antenna in various C (4–8 GHz) band applications. Originality/value The proposed antennas can use C band wireless frequency application. The proposed structure provides better performance in terms of isolation between the ports, small size, high front-to-back ratio and higher gain. It is fabricated for the proof of concept with the RT Duroid 5880 substrate material having a 2.2 permittivity. Measured results show a similar kind of performance as a simulated one.
Fusion Engineering and Design, Dec 1, 2020
The microwave interferometer is a device that works in the millimeter-wave frequency range, and i... more The microwave interferometer is a device that works in the millimeter-wave frequency range, and it is used to measure the plasma density. The instability in the frequency source at the transmitter section of the interferometer affects the accuracy of the phase measurement in the receiver section. The phase-locked loop (PLL) circuit is a substantial unit in the generation of highly stable frequency. This paper proposes a highly stable frequency source generator for the D-band Microwave interferometer. The design, development, and analysis of the PLL system with the frequency signal of 6.9 GHz and 7.0 is presented in this paper. Two alternate approaches using the dielectric resonator oscillator (DRO) and Frequency synthesizer are presented to design the PLL circuit. The stability is achieved using a 7 GHz DRO in the transmitter section, which is phase-locked with a 6.9 GHz voltage controlled oscillator (VCO) at the receiver section in the proposed first design and a frequency synthesizer is used instead of DRO in the proposed second design. The developed circuit is analysed in terms of parameters like phase noise performance, output power level, development cost, design complexity, and operating frequency range. The PLL in the receiver section is configured using FPGA to analyze the circuit performance at various frequency offset. DRO generates the power of 17.62 dB m at a frequency of 7.0 GHz. The DRO and synthesizer circuit provides excellent phase noise performance of-120 dBc/Hz and-93 dBc/Hz, respectively, at the transmitter section and-94.12 dBc/Hz at the receiver section. Indigenous methods have been made for the development of PLLs. It will be used to develop a D-band microwave interferometer to measure the electron density of fusion plasma at the Institute for plasma research (IPR)-Government of India.
Circuit World, Jul 4, 2020
Purpose-This paper aims to present, design and implement a novel half-mode substrate integrated w... more Purpose-This paper aims to present, design and implement a novel half-mode substrate integrated waveguide (HMSIW)-based narrow bandpass filter, which offers advantages like low insertion loss, compact size and high selectivity. Proposed filter will be used in the K-band automotive radar application. Design/methodology/approach-The filtering response in the proposed design is achieved by inserting inductive posts in the HMSIW cavity. Ansoft high frequency structure Simulator (HFSS) is used for the simulation of the proposed structure, which is a three-dimensional full-wave solver using the finite element method (FEM). The proposed filter is fabricated on the dielectric material RT duroid 5,880 with the dielectric constant e r = 2.2, dissipation factor t and = 4 Â 10-4 and height h = 0.508 mm. Findings-Frequency tuning is also carried out by changing the lateral distance between two inductive posts. Moreover, a comparison of the proposed structure with the previously published work is presented. Proposed method provides the unique advantages such as low insertion loss, high selectivity and compact in size. Originality/value-Indigenous method has been used for the development of the filter. Proposed filter will be used in transmitter subsystem of the K-band radar system operating at the center frequency of 11.2 GHz. Measurement results are well-matched with the simulated one. Obtained measured result shows return loss of 20.39 dB and insertion loss of 1.59 dB with 3 dB fractional bandwidth (FBW) of 2.58% at the center frequency of 11.2 GHz.
Circuit World, Aug 5, 2019
Purpose-The digital down converter (DDC) is a principal component in modern communication systems... more Purpose-The digital down converter (DDC) is a principal component in modern communication systems. The DDC process traditionally entails quadrature down conversion, bandwidth reducing filters and commensurate sample rate reduction. To avoid group delay, distortion linear phase FIR filters are used in the DDC. The filter performance specifications related to deep stopband attenuation, small in-band ripple and narrow transition bandwidth lead to filters with a large number of coefficients. To reduce the computational workload of the filtering process, filtering is often performed as a two-stage process, the first stage being a down sampling Hoegenauer (or cascade-integrated comb) filter and a reduced sample rate FIR filter. An alternative option is an M-Path polyphase partition of a band cantered FIR filter. Even though IIR filters offer reduced workload to implement a specific filtering task, the authors avoid using them because of their poor group delay characteristics. This paper aims to propose the design of M-path, approximately linear phase IIR filters as an alternative option to the M-path FIR filter. Design/methodology/approach-Two filter designs are presented in the paper. The first approach uses linear phase IIR low pass structure to reduce the filter's coefficient. Whereas the second approach uses multipath polyphase structure to design approximately linear phase IIR filter in DDC. Findings-The authors have compared the performance and workload of the proposed polyphase structured IIR filters with state-of-the-art filter design used in DDC. The proposed design is seen to satisfy tight design specification with a significant reduction in arithmetic operations and required power consumption. Originality/value-The proposed design is an alternate solution to the M-path polyphase FIR filter offering very less number of coefficients in the filter design. Proposed DDC using polyphase structured IIR filter satisfies the requirement of linear phase with the least number of computation cost in comparison with other DDC structure.
Image Segmentation and Classification for Medical Image Processing
International journal on future revolution in computer science & communication engineering, Jan 31, 2019
Segmentation and labeling remains the weakest step in many medical vision applications. This pape... more Segmentation and labeling remains the weakest step in many medical vision applications. This paper illustrates an approach based on watershed transform which are designed to solve typical problems encountered in various applications, and which are controllable through adaptation of their parameters. Two of these modules are presented: the lung cancer detection, a method for the segmentation of cancer regions from CT images, a watershed algorithm for image segmentation and brain tumor detection from MRI images. Various GLCM features along with some statistical features are used for classification using Neural network and Support Vector Machine (SVM). We describe the principles of the algorithms and illustrate their generic properties by discussing the results of both applications in 2D MRI images of Brain tumor and CT images of lung cancer.
An Abnormal Activity Detection Using Harris corner, Optical Flow and Dynamic Thresholding
Turkish Online Journal of Qualitative Inquiry, Aug 4, 2021
Uploads
Papers by Jitendra Chaudhari